测试完成yolov5
This commit is contained in:
Dinger
parent
92a67d656e
commit
dab76027c6
|
|
@ -4,7 +4,7 @@
|
|||
<content url="file://$MODULE_DIR$">
|
||||
<excludeFolder url="file://$MODULE_DIR$/venv" />
|
||||
</content>
|
||||
<orderEntry type="jdk" jdkName="Python 3.8 (code)" jdkType="Python SDK" />
|
||||
<orderEntry type="jdk" jdkName="Python 3.7 (graduation_project)" jdkType="Python SDK" />
|
||||
<orderEntry type="sourceFolder" forTests="false" />
|
||||
</component>
|
||||
</module>
|
||||
|
|
@ -1,4 +1,4 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (code)" project-jdk-type="Python SDK" />
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7 (graduation_project)" project-jdk-type="Python SDK" />
|
||||
</project>
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,349 @@
|
|||
# coding=utf-8
|
||||
import torch
|
||||
import torchvision
|
||||
import torch.nn as nn
|
||||
import os
|
||||
import time
|
||||
import numpy as np
|
||||
import math
|
||||
import random
|
||||
import cv2.cv2 as cv2
|
||||
|
||||
|
||||
def autopad(k, p=None): # kernel, padding
|
||||
# Pad to 'same'
|
||||
if p is None:
|
||||
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
|
||||
return p
|
||||
|
||||
|
||||
class Conv(nn.Module):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super(Conv, self).__init__()
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(self.conv(x)))
|
||||
|
||||
def fuseforward(self, x):
|
||||
return self.act(self.conv(x))
|
||||
|
||||
|
||||
class Ensemble(torch.nn.ModuleList):
|
||||
'''模型集成'''
|
||||
|
||||
def __init__(self):
|
||||
super(Ensemble, self).__init__()
|
||||
|
||||
def forward(self, x, augment=False):
|
||||
y = []
|
||||
for module in self:
|
||||
y.append(module(x, augment)[0])
|
||||
# y = torch.stack(y).max(0)[0] # max ensemble
|
||||
# y = torch.stack(y).mean(0) # mean ensemble
|
||||
y = torch.cat(y, 1) # nms ensemble
|
||||
return y, None # inference, train output
|
||||
|
||||
|
||||
class YOLOV5(object):
|
||||
def __init__(self, conf_thres=0.25,
|
||||
iou_thres=0.45,
|
||||
classes=None,
|
||||
imgsz=640,
|
||||
weights="./yolov5s.pt"):
|
||||
# 超参数设置
|
||||
self.conf_thres = conf_thres # 置信度阈值
|
||||
self.iou_thres = iou_thres # iou阈值
|
||||
self.classes = classes # 分类个数
|
||||
self.imgsz = imgsz # 归一化大小
|
||||
# Load model
|
||||
self.device = torch.device('cpu')
|
||||
self.model = self.attempt_load(weights, map_location=self.device) # load FP32 model
|
||||
self.stride = int(self.model.stride.max()) # model stride
|
||||
self.imgsz = self.check_img_size(imgsz, s=self.stride) # check img_size
|
||||
|
||||
def attempt_load(self, weights, map_location=None):
|
||||
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
|
||||
model = Ensemble()
|
||||
for w in weights if isinstance(weights, list) else [weights]:
|
||||
ckpt = torch.load(w, map_location=map_location) # load
|
||||
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
|
||||
|
||||
# Compatibility updates
|
||||
for m in model.modules():
|
||||
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
|
||||
m.inplace = True # pytorch 1.7.0 compatibility
|
||||
elif type(m) is Conv:
|
||||
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
|
||||
|
||||
if len(model) == 1:
|
||||
return model[-1] # return model
|
||||
else:
|
||||
print('Ensemble created with %s\n' % weights)
|
||||
for k in ['names', 'stride']:
|
||||
setattr(model, k, getattr(model[-1], k))
|
||||
return model # return ensemble
|
||||
|
||||
def make_divisible(self, x, divisor):
|
||||
# Returns x evenly divisible by divisor
|
||||
return math.ceil(x / divisor) * divisor
|
||||
|
||||
def check_img_size(self, img_size, s=32):
|
||||
# Verify img_size is a multiple of stride s
|
||||
new_size = self.make_divisible(img_size, int(s)) # ceil gs-multiple
|
||||
if new_size != img_size:
|
||||
print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
|
||||
return new_size
|
||||
|
||||
def letterbox(self, img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True,
|
||||
stride=32):
|
||||
# Resize and pad image while meeting stride-multiple constraints
|
||||
shape = img.shape[:2] # current shape [height, width]
|
||||
if isinstance(new_shape, int):
|
||||
new_shape = (new_shape, new_shape)
|
||||
|
||||
# Scale ratio (new / old)
|
||||
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
|
||||
if not scaleup: # only scale down, do not scale up (for better test mAP)
|
||||
r = min(r, 1.0)
|
||||
|
||||
# Compute padding
|
||||
ratio = r, r # width, height ratios
|
||||
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
|
||||
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
|
||||
if auto: # minimum rectangle
|
||||
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
|
||||
elif scaleFill: # stretch
|
||||
dw, dh = 0.0, 0.0
|
||||
new_unpad = (new_shape[1], new_shape[0])
|
||||
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
|
||||
|
||||
dw /= 2 # divide padding into 2 sides
|
||||
dh /= 2
|
||||
|
||||
if shape[::-1] != new_unpad: # resize
|
||||
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
|
||||
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
|
||||
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
|
||||
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
|
||||
return img, ratio, (dw, dh)
|
||||
|
||||
def box_iou(self, box1, box2):
|
||||
# https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
|
||||
"""
|
||||
Return intersection-over-union (Jaccard index) of boxes.
|
||||
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
|
||||
Arguments:
|
||||
box1 (Tensor[N, 4])
|
||||
box2 (Tensor[M, 4])
|
||||
Returns:
|
||||
iou (Tensor[N, M]): the NxM matrix containing the pairwise
|
||||
IoU values for every element in boxes1 and boxes2
|
||||
"""
|
||||
|
||||
def box_area(box):
|
||||
# box = 4xn
|
||||
return (box[2] - box[0]) * (box[3] - box[1])
|
||||
|
||||
area1 = box_area(box1.T)
|
||||
area2 = box_area(box2.T)
|
||||
|
||||
# inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
|
||||
inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
|
||||
return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter)
|
||||
|
||||
def xywh2xyxy(self, x):
|
||||
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
|
||||
y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
|
||||
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
|
||||
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
|
||||
return y
|
||||
|
||||
def non_max_suppression(self, prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False,
|
||||
multi_label=False,
|
||||
labels=()):
|
||||
"""Runs Non-Maximum Suppression (NMS) on inference results
|
||||
|
||||
Returns:
|
||||
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
|
||||
"""
|
||||
|
||||
nc = prediction.shape[2] - 5 # number of classes
|
||||
xc = prediction[..., 4] > conf_thres # candidates
|
||||
|
||||
# Settings
|
||||
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
|
||||
max_det = 300 # maximum number of detections per image
|
||||
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
|
||||
time_limit = 10.0 # seconds to quit after
|
||||
redundant = True # require redundant detections
|
||||
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
|
||||
merge = False # use merge-NMS
|
||||
|
||||
t = time.time()
|
||||
output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
|
||||
for xi, x in enumerate(prediction): # image index, image inference
|
||||
# Apply constraints
|
||||
# x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
|
||||
x = x[xc[xi]] # confidence
|
||||
|
||||
# Cat apriori labels if autolabelling
|
||||
if labels and len(labels[xi]):
|
||||
l = labels[xi]
|
||||
v = torch.zeros((len(l), nc + 5), device=x.device)
|
||||
v[:, :4] = l[:, 1:5] # box
|
||||
v[:, 4] = 1.0 # conf
|
||||
v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
|
||||
x = torch.cat((x, v), 0)
|
||||
|
||||
# If none remain process next image
|
||||
if not x.shape[0]:
|
||||
continue
|
||||
|
||||
# Compute conf
|
||||
x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
|
||||
|
||||
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
|
||||
box = self.xywh2xyxy(x[:, :4])
|
||||
|
||||
# Detections matrix nx6 (xyxy, conf, cls)
|
||||
if multi_label:
|
||||
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
|
||||
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
|
||||
else: # best class only
|
||||
conf, j = x[:, 5:].max(1, keepdim=True)
|
||||
x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
|
||||
|
||||
# Filter by class
|
||||
if classes is not None:
|
||||
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
|
||||
|
||||
# Apply finite constraint
|
||||
# if not torch.isfinite(x).all():
|
||||
# x = x[torch.isfinite(x).all(1)]
|
||||
|
||||
# Check shape
|
||||
n = x.shape[0] # number of boxes
|
||||
if not n: # no boxes
|
||||
continue
|
||||
elif n > max_nms: # excess boxes
|
||||
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
|
||||
|
||||
# Batched NMS
|
||||
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
|
||||
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
|
||||
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
|
||||
if i.shape[0] > max_det: # limit detections
|
||||
i = i[:max_det]
|
||||
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
|
||||
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
|
||||
iou = self.box_iou(boxes[i], boxes) > iou_thres # iou matrix
|
||||
weights = iou * scores[None] # box weights
|
||||
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
|
||||
if redundant:
|
||||
i = i[iou.sum(1) > 1] # require redundancy
|
||||
|
||||
output[xi] = x[i]
|
||||
if (time.time() - t) > time_limit:
|
||||
print(f'WARNING: NMS time limit {time_limit}s exceeded')
|
||||
break # time limit exceeded
|
||||
|
||||
return output
|
||||
|
||||
def clip_coords(self, boxes, img_shape):
|
||||
# Clip bounding xyxy bounding boxes to image shape (height, width)
|
||||
boxes[:, 0].clamp_(0, img_shape[1]) # x1
|
||||
boxes[:, 1].clamp_(0, img_shape[0]) # y1
|
||||
boxes[:, 2].clamp_(0, img_shape[1]) # x2
|
||||
boxes[:, 3].clamp_(0, img_shape[0]) # y2
|
||||
|
||||
def scale_coords(self, img1_shape, coords, img0_shape, ratio_pad=None):
|
||||
# Rescale coords (xyxy) from img1_shape to img0_shape
|
||||
if ratio_pad is None: # calculate from img0_shape
|
||||
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
|
||||
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
|
||||
else:
|
||||
gain = ratio_pad[0][0]
|
||||
pad = ratio_pad[1]
|
||||
|
||||
coords[:, [0, 2]] -= pad[0] # x padding
|
||||
coords[:, [1, 3]] -= pad[1] # y padding
|
||||
coords[:, :4] /= gain
|
||||
self.clip_coords(coords, img0_shape)
|
||||
return coords
|
||||
|
||||
def plot_one_box(self, x, img, color=None, label=None, line_thickness=3):
|
||||
# Plots one bounding box on image img
|
||||
tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
|
||||
color = color or [random.randint(0, 255) for _ in range(3)]
|
||||
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
|
||||
cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
|
||||
if label:
|
||||
tf = max(tl - 1, 1) # font thickness
|
||||
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
|
||||
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
|
||||
cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled
|
||||
cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
|
||||
|
||||
def infer(self, image, agnostic_nms=False, draw_flag=False):
|
||||
# read image
|
||||
# image=cv2.imread(img_path)
|
||||
|
||||
# Padded resize
|
||||
img = self.letterbox(image, self.imgsz, stride=self.stride)[0]
|
||||
|
||||
# Convert
|
||||
img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
|
||||
img = np.ascontiguousarray(img)
|
||||
|
||||
img = torch.from_numpy(img).to(self.device)
|
||||
img = img.float() # uint8 to fp16/32
|
||||
img /= 255.0 # 0 - 255 to 0.0 - 1.0
|
||||
if img.ndimension() == 3:
|
||||
img = img.unsqueeze(0)
|
||||
|
||||
# Inference
|
||||
pred = self.model(img, augment=False)[0]
|
||||
|
||||
# Apply NMS
|
||||
pred = self.non_max_suppression(pred, self.conf_thres, self.iou_thres, classes=None, agnostic=agnostic_nms)
|
||||
|
||||
# Process detections
|
||||
s = ""
|
||||
s += '%gx%g ' % img.shape[2:] # print string
|
||||
result = []
|
||||
for i, det in enumerate(pred): # detections per image
|
||||
# Rescale boxes from img_size to im0 size
|
||||
det[:, :4] = self.scale_coords(img.shape[2:], det[:, :4], image.shape).round()
|
||||
|
||||
for *xyxy, conf, cls in reversed(det):
|
||||
x1, y1, x2, y2 = int(xyxy[0]), int(xyxy[1]), int(xyxy[2]), int(xyxy[3])
|
||||
result.append([x1, y1, x2, y2])
|
||||
if draw_flag:
|
||||
names = self.model.module.names if hasattr(self.model, 'module') else self.model.names
|
||||
colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
|
||||
for *xyxy, conf, cls in reversed(det):
|
||||
label = f'{names[int(cls)]} {conf:.2f}'
|
||||
self.plot_one_box(xyxy, image, label=label, color=colors[int(cls)], line_thickness=3)
|
||||
# Print results
|
||||
# for c in det[:, -1].unique():
|
||||
# n = (det[:, -1] == c).sum() # detections per class
|
||||
# s += f"{n}{'s' * (n > 1)}, " # add to string
|
||||
|
||||
# Write results
|
||||
# Get names and colors
|
||||
|
||||
# 显示预测结果
|
||||
# print(s)
|
||||
# print(result)
|
||||
# cv2.namedWindow("result",0)
|
||||
# cv2.imshow("result", image)
|
||||
# cv2.waitKey(0) # 1 millisecond
|
||||
# return image
|
||||
# 后处理
|
||||
return result
|
||||
153
identify.py
153
identify.py
|
|
@ -1,5 +1,5 @@
|
|||
import time
|
||||
from mem_top import mem_top
|
||||
from pymouse import PyMouse
|
||||
import cv2
|
||||
import mediapipe as mp
|
||||
import math
|
||||
|
|
@ -12,8 +12,9 @@ import util
|
|||
|
||||
|
||||
class Identify:
|
||||
def __init__(self, v):
|
||||
self.v = v
|
||||
def __init__(self, value, array):
|
||||
self.value = value
|
||||
self.array = array
|
||||
self.left_hand_flag = False
|
||||
self.right_hand_flag = False
|
||||
self.result = 0
|
||||
|
|
@ -32,7 +33,8 @@ class Identify:
|
|||
self.last_control_flag = 0
|
||||
self.page_up_count = 0
|
||||
self.page_down_count = 0
|
||||
self.step = 0
|
||||
self.step_up = 0
|
||||
self.step_down = 0
|
||||
self.last_wrist_point = (0, 0)
|
||||
self.now_time = 0
|
||||
self.lase_time = 0
|
||||
|
|
@ -44,6 +46,8 @@ class Identify:
|
|||
max_num_hands=2,
|
||||
min_detection_confidence=0.75,
|
||||
min_tracking_confidence=0.75)
|
||||
self.mp_face = mp.solutions.face_detection
|
||||
self.face_detection = self.mp_face.FaceDetection(min_detection_confidence=0.5)
|
||||
|
||||
def begin(self):
|
||||
capture = cv2.VideoCapture(0)
|
||||
|
|
@ -68,6 +72,10 @@ class Identify:
|
|||
if flag:
|
||||
self.flag = flag
|
||||
now_time = time.time()
|
||||
self.array[0] = self.position_x
|
||||
self.array[1] = self.position_y
|
||||
self.array[2] = self.image_width
|
||||
self.array[3] = self.image_height
|
||||
if now_time - last_time < 1:
|
||||
continue
|
||||
last_time = now_time
|
||||
|
|
@ -81,13 +89,16 @@ class Identify:
|
|||
# if cv2.waitKey(1) & 0xFF == ord('q'):
|
||||
# break
|
||||
# control_flag = flag
|
||||
self.v.value = self.flag
|
||||
self.value.value = self.flag
|
||||
# print("self.v.value = " + str(self.flag))
|
||||
print("final_control_flag = " + str(self.flag))
|
||||
self.flag = 0
|
||||
capture.release()
|
||||
cv2.destroyAllWindows()
|
||||
|
||||
# def face_detect(self):
|
||||
# results = self.face_detection.process(self.rgb_image)
|
||||
|
||||
def deal_with_image(self):
|
||||
self.image = cv2.flip(self.image, 1)
|
||||
self.rgb_image = cv2.cvtColor(self.image, cv2.COLOR_BGR2RGB)
|
||||
|
|
@ -103,10 +114,11 @@ class Identify:
|
|||
self.image_height, self.image_width, c = self.image.shape
|
||||
cx, cy = int(hand_landmarks.x * self.image_width), int(hand_landmarks.y * self.image_height)
|
||||
self.left_hand_points.append((cx, cy))
|
||||
self.is_identify = True
|
||||
self.mp_drawing.draw_landmarks(
|
||||
self.image, self.identify_results.multi_hand_landmarks[i], self.mp_hands.HAND_CONNECTIONS)
|
||||
self.left_hand_flag = True
|
||||
# self.mp_drawing.draw_landmarks(
|
||||
# self.image, self.identify_results.multi_hand_landmarks[i], self.mp_hands.HAND_CONNECTIONS)
|
||||
if self.identify_results.multi_handedness[i].classification[0].score > 0.5:
|
||||
self.left_hand_flag = True
|
||||
self.is_identify = True
|
||||
|
||||
else:
|
||||
for hand_landmarks in self.identify_results.multi_hand_landmarks[i].landmark:
|
||||
|
|
@ -115,9 +127,11 @@ class Identify:
|
|||
cx, cy = int(hand_landmarks.x * self.image_width), int(hand_landmarks.y * self.image_height)
|
||||
self.right_hand_points.append((cx, cy))
|
||||
self.is_identify = True
|
||||
self.mp_drawing.draw_landmarks(
|
||||
self.image, self.identify_results.multi_hand_landmarks[i], self.mp_hands.HAND_CONNECTIONS)
|
||||
self.right_hand_flag = True
|
||||
# self.mp_drawing.draw_landmarks(
|
||||
# self.image, self.identify_results.multi_hand_landmarks[i], self.mp_hands.HAND_CONNECTIONS)
|
||||
if self.identify_results.multi_handedness[i].classification[0].score > 0.5:
|
||||
self.right_hand_flag = True
|
||||
self.is_identify = True
|
||||
|
||||
def hand_angle(self):
|
||||
'''
|
||||
|
|
@ -171,6 +185,12 @@ class Identify:
|
|||
not self.is_finger_straight[3] and not self.is_finger_straight[4]
|
||||
|
||||
def judge_one(self):
|
||||
if self.left_hand_flag:
|
||||
self.position_x = self.left_hand_points[8][0]
|
||||
self.position_y = self.left_hand_points[8][1]
|
||||
elif self.right_hand_flag:
|
||||
self.position_x = self.right_hand_points[8][0]
|
||||
self.position_y = self.right_hand_points[8][1]
|
||||
return self.is_finger_straight[1] and not self.is_finger_straight[2] and \
|
||||
not self.is_finger_straight[3] and not self.is_finger_straight[4]
|
||||
|
||||
|
|
@ -190,51 +210,6 @@ class Identify:
|
|||
return self.is_finger_straight[1] and self.is_finger_straight[2] and \
|
||||
self.is_finger_straight[3] and self.is_finger_straight[4]
|
||||
|
||||
# def judge_five(self):
|
||||
# self.hand_angle()
|
||||
# return util.Util.is_straight(self.angle_list[1]) and util.Util.is_straight(
|
||||
# self.angle_list[2]) and util.Util.is_straight(self.angle_list[3]) and util.Util.is_straight(
|
||||
# self.angle_list[4])
|
||||
|
||||
# def judge_open(self):
|
||||
# self.hand_angle()
|
||||
# # angle_ = vector_2d_angle(
|
||||
# # ((int(points[0][0]) - int(points[5][0])), (int(points[0][1]) - int(points[5][1]))),
|
||||
# # ((int(points[5][0]) - int(points[8][0])), (int(points[5][1]) - int(points[8][1])))
|
||||
# # )
|
||||
# return not util.Util.is_straight(self.angle_list[1]) and util.Util.is_straight(
|
||||
# self.angle_list[2]) and util.Util.is_straight(self.angle_list[3]) and util.Util.is_straight(
|
||||
# self.angle_list[4])
|
||||
#
|
||||
# def judge_up(self):
|
||||
# self.hand_angle()
|
||||
# angle_ = util.Util.vector_2d_angle(
|
||||
# ((int(self.hand_points[0][0]) - int(self.hand_points[5][0])),
|
||||
# (int(self.hand_points[0][1]) - int(self.hand_points[5][1]))),
|
||||
# ((int(self.hand_points[5][0]) - int(self.hand_points[8][0])),
|
||||
# (int(self.hand_points[5][1]) - int(self.hand_points[8][1])))
|
||||
# )
|
||||
# return util.Util.is_straight(
|
||||
# self.angle_list[1] and not util.Util.is_straight(self.angle_list[2]) and not util.Util.is_straight(
|
||||
# self.angle_list[3]) and not util.Util.is_straight(self.angle_list[4])) and angle_ <= 40
|
||||
#
|
||||
# def judge_down(self):
|
||||
# self.hand_angle()
|
||||
# return util.Util.is_straight(self.angle_list[1]) and util.Util.is_straight(
|
||||
# self.angle_list[2]) and not util.Util.is_straight(self.angle_list[3]) and not util.Util.is_straight(
|
||||
# self.angle_list[4])
|
||||
#
|
||||
# def judge_end(self):
|
||||
# self.hand_angle()
|
||||
# return not util.Util.is_straight(self.angle_list[1]) and not util.Util.is_straight(
|
||||
# self.angle_list[2]) and not util.Util.is_straight(self.angle_list[3]) and not util.Util.is_straight(
|
||||
# self.angle_list[4])
|
||||
|
||||
# def judge_one(self):
|
||||
# self.hand_angle()
|
||||
# return util.Util.is_straight(self.angle_list[1]) and not util.Util.is_straight(
|
||||
# self.angle_list[2]) and not util.Util.is_straight(self.angle_list[3]) and not util.Util.is_straight(
|
||||
# self.angle_list[4])
|
||||
def judge_step_one(self, is_left):
|
||||
if is_left:
|
||||
if self.judge_five() and self.left_hand_points[8][0] < self.left_hand_points[0][0] and \
|
||||
|
|
@ -265,19 +240,30 @@ class Identify:
|
|||
return True
|
||||
return False
|
||||
|
||||
def judge_step_three(self):
|
||||
if self.left_hand_flag:
|
||||
if self.left_hand_points[20][1] < self.left_hand_points[0][1]:
|
||||
return True
|
||||
else:
|
||||
if self.right_hand_points[20][1] < self.right_hand_points[0][1]:
|
||||
return True
|
||||
return False
|
||||
|
||||
def judge_page_up(self):
|
||||
if not self.right_hand_flag:
|
||||
return False
|
||||
if self.step == 0:
|
||||
if self.step_up == 0:
|
||||
self.lase_time = time.time()
|
||||
if self.step == 0 and self.judge_step_one(False):
|
||||
self.step = 1
|
||||
elif self.step == 1 and self.judge_step_two(False):
|
||||
self.step = 3
|
||||
elif self.step == 2 and self.judge_zero():
|
||||
self.step = 3
|
||||
elif self.step == 3:
|
||||
self.step = 0
|
||||
if self.step_up == 0 and self.judge_step_three():
|
||||
self.step_up = 4
|
||||
if self.step_up == 4 and self.judge_step_one(False):
|
||||
self.step_up = 1
|
||||
elif self.step_up == 1 and self.judge_step_two(False):
|
||||
self.step_up = 3
|
||||
elif self.step_up == 2 and self.judge_zero():
|
||||
self.step_up = 3
|
||||
elif self.step_up == 3:
|
||||
self.step_up = 0
|
||||
now_time = time.time()
|
||||
if now_time - self.lase_time < 3:
|
||||
self.lase_time = now_time
|
||||
|
|
@ -290,16 +276,21 @@ class Identify:
|
|||
def judge_page_down(self):
|
||||
if not self.left_hand_flag:
|
||||
return False
|
||||
if self.step == 0:
|
||||
if self.step_down == 0:
|
||||
self.lase_time = time.time()
|
||||
if self.step == 0 and self.judge_step_one(True):
|
||||
self.step = 1
|
||||
elif self.step == 1 and self.judge_step_two(True):
|
||||
self.step = 3
|
||||
elif self.step == 2 and self.judge_zero():
|
||||
self.step = 3
|
||||
elif self.step == 3:
|
||||
self.step = 0
|
||||
if self.step_down == 0 and self.judge_step_three():
|
||||
self.step_down = 4
|
||||
print("step = 1")
|
||||
if self.step_down == 4 and self.judge_step_one(True):
|
||||
self.step_down = 1
|
||||
print("step = 2")
|
||||
elif self.step_down == 1 and self.judge_step_two(True):
|
||||
self.step_down = 3
|
||||
print("step = 3")
|
||||
elif self.step_down == 2 and self.judge_zero():
|
||||
self.step_down = 3
|
||||
elif self.step_down == 3:
|
||||
self.step_down = 0
|
||||
now_time = time.time()
|
||||
if now_time - self.lase_time < 3:
|
||||
self.lase_time = now_time
|
||||
|
|
@ -309,16 +300,24 @@ class Identify:
|
|||
return False
|
||||
return False
|
||||
|
||||
def judge_end(self):
|
||||
if self.left_hand_flag and self.right_hand_flag and self.judge_zero():
|
||||
return True
|
||||
return False
|
||||
|
||||
def judge_control(self):
|
||||
if self.is_identify:
|
||||
if self.judge_one():
|
||||
if self.judge_two():
|
||||
return 1
|
||||
elif self.judge_page_up():
|
||||
return 2
|
||||
elif self.judge_page_down():
|
||||
# print("down!down!down!down!down!down!down!down!down!down!down!down!down!down!down!down!down!down!")
|
||||
return 3
|
||||
elif self.judge_zero():
|
||||
elif self.judge_one():
|
||||
return 4
|
||||
elif self.judge_zero():
|
||||
return 5
|
||||
else:
|
||||
print("other")
|
||||
else:
|
||||
|
|
|
|||
83
main.py
83
main.py
|
|
@ -1,29 +1,12 @@
|
|||
import multiprocessing
|
||||
import tkinter
|
||||
|
||||
import cv2
|
||||
|
||||
import identify
|
||||
from identify import *
|
||||
from tkinter.filedialog import *
|
||||
import threading
|
||||
# import pymouse
|
||||
from tkinter import *
|
||||
from tkinter import ttk
|
||||
import tkinter.filedialog as dir
|
||||
import queue
|
||||
from tkinter.messagebox import showinfo
|
||||
import win32com
|
||||
|
||||
from win32com.client import Dispatch
|
||||
from pptx import Presentation
|
||||
from selenium import webdriver
|
||||
from selenium.webdriver.common.keys import Keys
|
||||
import win32con
|
||||
import win32api
|
||||
import time
|
||||
import os
|
||||
import string
|
||||
|
||||
window = tkinter.Tk()
|
||||
window.title('窗口标题')
|
||||
|
|
@ -72,10 +55,14 @@ def control_ppt_end():
|
|||
|
||||
def control_open_pencil():
|
||||
win32api.keybd_event(17, 0, 0, 0) # 代表按下f键
|
||||
win32api.keybd_event(80, 0, 0, 0) # 代表按下f键
|
||||
win32api.keybd_event(82, 0, 0, 0) # 代表按下f键
|
||||
time.sleep(0.02)
|
||||
win32api.keybd_event(17, 0, win32con.KEYEVENTF_KEYUP, 0) # 释放f键
|
||||
win32api.keybd_event(80, 0, win32con.KEYEVENTF_KEYUP, 0) # 释放f键
|
||||
win32api.keybd_event(82, 0, win32con.KEYEVENTF_KEYUP, 0) # 释放f键
|
||||
|
||||
|
||||
def control_writing(m, position_x, position_y):
|
||||
m.move(position_x, position_y)
|
||||
|
||||
|
||||
def control_draw():
|
||||
|
|
@ -93,17 +80,33 @@ def control_draw():
|
|||
#
|
||||
|
||||
|
||||
def control_thread(v, flag):
|
||||
def control_thread(value, array):
|
||||
last_time = 0.0
|
||||
step = 0
|
||||
mouse = PyMouse()
|
||||
|
||||
while 1:
|
||||
# print("step = " + str(step))
|
||||
# print("control_thread")
|
||||
now_time = time.time()
|
||||
# time.sleep(0.1)
|
||||
# print(end - start)
|
||||
|
||||
control_flag = v.value
|
||||
# print("***********array************")
|
||||
# print(array)
|
||||
# print("***********array************")
|
||||
control_flag = value.value
|
||||
if step == 2:
|
||||
if control_flag == 4:
|
||||
# print("inininininininininininininininininininininininin")
|
||||
position_x = int(mouse.screen_size()[0] / array[2] * array[0])
|
||||
position_y = int(mouse.screen_size()[1] / array[3] * array[1])
|
||||
control_writing(mouse, position_x, position_y)
|
||||
elif control_flag == 5:
|
||||
step = 1
|
||||
control_ppt_end()
|
||||
last_time = now_time
|
||||
# print("step to 11111111111111111")
|
||||
continue
|
||||
if now_time - last_time < 1:
|
||||
continue
|
||||
last_time = now_time
|
||||
|
|
@ -113,6 +116,7 @@ def control_thread(v, flag):
|
|||
# time.sleep(0.05)
|
||||
# start = time.time()
|
||||
print("control_flag = " + str(control_flag))
|
||||
# print("main.step = " + str(step))
|
||||
if step == 0 and control_flag == 1:
|
||||
control_ppt_begin()
|
||||
# print("control_flag == 1")
|
||||
|
|
@ -121,11 +125,15 @@ def control_thread(v, flag):
|
|||
if control_flag == 2:
|
||||
control_page_up()
|
||||
# print("control_flag == 2")
|
||||
if control_flag == 3:
|
||||
elif control_flag == 3:
|
||||
control_page_down()
|
||||
# print("control_flag == 3")
|
||||
if control_flag == 4:
|
||||
elif control_flag == 4:
|
||||
control_open_pencil()
|
||||
step = 2
|
||||
elif control_flag == 5:
|
||||
control_ppt_end()
|
||||
# print("end!end!end!end!end!end!end!end!end!end!end!")
|
||||
# print("control_flag == 4")
|
||||
step = 0
|
||||
# if control_flag == 5:
|
||||
|
|
@ -134,23 +142,32 @@ def control_thread(v, flag):
|
|||
# control_draw()
|
||||
|
||||
|
||||
def identify_thread(v, flag):
|
||||
identify = Identify(v)
|
||||
def identify_thread(value, array):
|
||||
identify = Identify(value, array)
|
||||
identify.begin()
|
||||
|
||||
|
||||
def show_thread(value, array):
|
||||
return 0
|
||||
|
||||
|
||||
def open_file():
|
||||
file_path = askopenfilename(title=u'选择文件', initialdir=(os.path.expanduser('H:/')))
|
||||
file_path = askopenfilename(title=u'选择文件')
|
||||
# file_path = askopenfilename(title=u'选择文件', initialdir=(os.path.expanduser('H:/')))
|
||||
open_ppt(file_path)
|
||||
v = multiprocessing.Value('i', 0)
|
||||
p1 = multiprocessing.Process(target=identify_thread, args=(v, 0))
|
||||
p2 = multiprocessing.Process(target=control_thread, args=(v, 0))
|
||||
value = multiprocessing.Value('i', 0)
|
||||
array = multiprocessing.Array('i', 4)
|
||||
# array2 = multiprocessing.Array()
|
||||
p1 = multiprocessing.Process(target=identify_thread, args=(value, array))
|
||||
p2 = multiprocessing.Process(target=control_thread, args=(value, array))
|
||||
# p3 = multiprocessing.Process(target=show_thread, args=(value, array))
|
||||
p1.start()
|
||||
p2.start()
|
||||
# p3.start()
|
||||
# identify_t = threading.Thread(target=identify_thread)
|
||||
# # print("control_flag1 = " + str(control_flag))
|
||||
# print("control_flag1 = " + str(control_flag))
|
||||
# control_t = threading.Thread(target=control_thread)
|
||||
# # print("control_flag2 = " + str(control_flag))
|
||||
# print("control_flag2 = " + str(control_flag))
|
||||
# identify_t.setDaemon(True)
|
||||
# control_t.setDaemon(True)
|
||||
# identify_t.start()
|
||||
|
|
@ -161,7 +178,7 @@ def open_ppt(file_path):
|
|||
ppt = Dispatch('PowerPoint.Application')
|
||||
ppt.Visible = 1 # 后台运行
|
||||
ppt.DisplayAlerts = 0 # 不显示，不警告
|
||||
# pptSel = ppt.Presentations.Open(file_path)
|
||||
ppt.Presentations.Open(file_path)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
|
|
|||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,469 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Common modules
|
||||
"""
|
||||
|
||||
import logging
|
||||
import math
|
||||
import warnings
|
||||
from copy import copy
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import requests
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from PIL import Image
|
||||
from torch.cuda import amp
|
||||
|
||||
from utils.datasets import exif_transpose, letterbox
|
||||
from utils.general import colorstr, increment_path, make_divisible, non_max_suppression, save_one_box, \
|
||||
scale_coords, xyxy2xywh
|
||||
from utils.plots import Annotator, colors
|
||||
from utils.torch_utils import time_sync
|
||||
|
||||
LOGGER = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def autopad(k, p=None): # kernel, padding
|
||||
# Pad to 'same'
|
||||
if p is None:
|
||||
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
|
||||
return p
|
||||
|
||||
|
||||
class Conv(nn.Module):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(self.conv(x)))
|
||||
|
||||
def forward_fuse(self, x):
|
||||
return self.act(self.conv(x))
|
||||
|
||||
|
||||
class DWConv(Conv):
|
||||
# Depth-wise convolution class
|
||||
def __init__(self, c1, c2, k=1, s=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
|
||||
|
||||
|
||||
class TransformerLayer(nn.Module):
|
||||
# Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
|
||||
def __init__(self, c, num_heads):
|
||||
super().__init__()
|
||||
self.q = nn.Linear(c, c, bias=False)
|
||||
self.k = nn.Linear(c, c, bias=False)
|
||||
self.v = nn.Linear(c, c, bias=False)
|
||||
self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
|
||||
self.fc1 = nn.Linear(c, c, bias=False)
|
||||
self.fc2 = nn.Linear(c, c, bias=False)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
|
||||
x = self.fc2(self.fc1(x)) + x
|
||||
return x
|
||||
|
||||
|
||||
class TransformerBlock(nn.Module):
|
||||
# Vision Transformer https://arxiv.org/abs/2010.11929
|
||||
def __init__(self, c1, c2, num_heads, num_layers):
|
||||
super().__init__()
|
||||
self.conv = None
|
||||
if c1 != c2:
|
||||
self.conv = Conv(c1, c2)
|
||||
self.linear = nn.Linear(c2, c2) # learnable position embedding
|
||||
self.tr = nn.Sequential(*[TransformerLayer(c2, num_heads) for _ in range(num_layers)])
|
||||
self.c2 = c2
|
||||
|
||||
def forward(self, x):
|
||||
if self.conv is not None:
|
||||
x = self.conv(x)
|
||||
b, _, w, h = x.shape
|
||||
p = x.flatten(2).unsqueeze(0).transpose(0, 3).squeeze(3)
|
||||
return self.tr(p + self.linear(p)).unsqueeze(3).transpose(0, 3).reshape(b, self.c2, w, h)
|
||||
|
||||
|
||||
class Bottleneck(nn.Module):
|
||||
# Standard bottleneck
|
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_, c2, 3, 1, g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class BottleneckCSP(nn.Module):
|
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
|
||||
self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
|
||||
self.cv4 = Conv(2 * c_, c2, 1, 1)
|
||||
self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3)
|
||||
self.act = nn.LeakyReLU(0.1, inplace=True)
|
||||
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
|
||||
|
||||
def forward(self, x):
|
||||
y1 = self.cv3(self.m(self.cv1(x)))
|
||||
y2 = self.cv2(x)
|
||||
return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
|
||||
|
||||
|
||||
class C3(nn.Module):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c1, c_, 1, 1)
|
||||
self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2)
|
||||
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
|
||||
# self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
|
||||
|
||||
def forward(self, x):
|
||||
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
|
||||
|
||||
|
||||
class C3TR(C3):
|
||||
# C3 module with TransformerBlock()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = TransformerBlock(c_, c_, 4, n)
|
||||
|
||||
|
||||
class C3SPP(C3):
|
||||
# C3 module with SPP()
|
||||
def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = SPP(c_, c_, k)
|
||||
|
||||
|
||||
class C3Ghost(C3):
|
||||
# C3 module with GhostBottleneck()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.m = nn.Sequential(*[GhostBottleneck(c_, c_) for _ in range(n)])
|
||||
|
||||
|
||||
class SPP(nn.Module):
|
||||
# Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
|
||||
def __init__(self, c1, c2, k=(5, 9, 13)):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
|
||||
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
|
||||
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
|
||||
|
||||
|
||||
class SPPF(nn.Module):
|
||||
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
|
||||
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_ * 4, c2, 1, 1)
|
||||
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
|
||||
y1 = self.m(x)
|
||||
y2 = self.m(y1)
|
||||
return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
|
||||
|
||||
|
||||
class Focus(nn.Module):
|
||||
# Focus wh information into c-space
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
|
||||
# self.contract = Contract(gain=2)
|
||||
|
||||
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
|
||||
return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
|
||||
# return self.conv(self.contract(x))
|
||||
|
||||
|
||||
class GhostConv(nn.Module):
|
||||
# Ghost Convolution https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
|
||||
super().__init__()
|
||||
c_ = c2 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, k, s, None, g, act)
|
||||
self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
|
||||
|
||||
def forward(self, x):
|
||||
y = self.cv1(x)
|
||||
return torch.cat([y, self.cv2(y)], 1)
|
||||
|
||||
|
||||
class GhostBottleneck(nn.Module):
|
||||
# Ghost Bottleneck https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
|
||||
super().__init__()
|
||||
c_ = c2 // 2
|
||||
self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1), # pw
|
||||
DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
|
||||
GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
|
||||
self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
|
||||
Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
|
||||
|
||||
def forward(self, x):
|
||||
return self.conv(x) + self.shortcut(x)
|
||||
|
||||
|
||||
class Contract(nn.Module):
|
||||
# Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h, w = x.size() # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(b, c, h // s, s, w // s, s) # x(1,64,40,2,40,2)
|
||||
x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40)
|
||||
return x.view(b, c * s * s, h // s, w // s) # x(1,256,40,40)
|
||||
|
||||
|
||||
class Expand(nn.Module):
|
||||
# Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h, w = x.size() # assert C / s ** 2 == 0, 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(b, s, s, c // s ** 2, h, w) # x(1,2,2,16,80,80)
|
||||
x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2)
|
||||
return x.view(b, c // s ** 2, h * s, w * s) # x(1,16,160,160)
|
||||
|
||||
|
||||
class Concat(nn.Module):
|
||||
# Concatenate a list of tensors along dimension
|
||||
def __init__(self, dimension=1):
|
||||
super().__init__()
|
||||
self.d = dimension
|
||||
|
||||
def forward(self, x):
|
||||
return torch.cat(x, self.d)
|
||||
|
||||
|
||||
class AutoShape(nn.Module):
|
||||
# YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
|
||||
conf = 0.25 # NMS confidence threshold
|
||||
iou = 0.45 # NMS IoU threshold
|
||||
classes = None # (optional list) filter by class
|
||||
multi_label = False # NMS multiple labels per box
|
||||
max_det = 1000 # maximum number of detections per image
|
||||
|
||||
def __init__(self, model):
|
||||
super().__init__()
|
||||
self.model = model.eval()
|
||||
|
||||
def autoshape(self):
|
||||
LOGGER.info('AutoShape already enabled, skipping... ') # model already converted to model.autoshape()
|
||||
return self
|
||||
|
||||
def _apply(self, fn):
|
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
|
||||
self = super()._apply(fn)
|
||||
m = self.model.model[-1] # Detect()
|
||||
m.stride = fn(m.stride)
|
||||
m.grid = list(map(fn, m.grid))
|
||||
if isinstance(m.anchor_grid, list):
|
||||
m.anchor_grid = list(map(fn, m.anchor_grid))
|
||||
return self
|
||||
|
||||
@torch.no_grad()
|
||||
def forward(self, imgs, size=640, augment=False, profile=False):
|
||||
# Inference from various sources. For height=640, width=1280, RGB images example inputs are:
|
||||
# file: imgs = 'data/images/zidane.jpg' # str or PosixPath
|
||||
# URI: = 'https://ultralytics.com/images/zidane.jpg'
|
||||
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
|
||||
# PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3)
|
||||
# numpy: = np.zeros((640,1280,3)) # HWC
|
||||
# torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
|
||||
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
|
||||
|
||||
t = [time_sync()]
|
||||
p = next(self.model.parameters()) # for device and type
|
||||
if isinstance(imgs, torch.Tensor): # torch
|
||||
with amp.autocast(enabled=p.device.type != 'cpu'):
|
||||
return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
|
||||
|
||||
# Pre-process
|
||||
n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs]) # number of images, list of images
|
||||
shape0, shape1, files = [], [], [] # image and inference shapes, filenames
|
||||
for i, im in enumerate(imgs):
|
||||
f = f'image{i}' # filename
|
||||
if isinstance(im, (str, Path)): # filename or uri
|
||||
im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
|
||||
im = np.asarray(exif_transpose(im))
|
||||
elif isinstance(im, Image.Image): # PIL Image
|
||||
im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
|
||||
files.append(Path(f).with_suffix('.jpg').name)
|
||||
if im.shape[0] < 5: # image in CHW
|
||||
im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
|
||||
im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3) # enforce 3ch input
|
||||
s = im.shape[:2] # HWC
|
||||
shape0.append(s) # image shape
|
||||
g = (size / max(s)) # gain
|
||||
shape1.append([y * g for y in s])
|
||||
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
|
||||
shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)] # inference shape
|
||||
x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs] # pad
|
||||
x = np.stack(x, 0) if n > 1 else x[0][None] # stack
|
||||
x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
|
||||
x = torch.from_numpy(x).to(p.device).type_as(p) / 255. # uint8 to fp16/32
|
||||
t.append(time_sync())
|
||||
|
||||
with amp.autocast(enabled=p.device.type != 'cpu'):
|
||||
# Inference
|
||||
y = self.model(x, augment, profile)[0] # forward
|
||||
t.append(time_sync())
|
||||
|
||||
# Post-process
|
||||
y = non_max_suppression(y, self.conf, iou_thres=self.iou, classes=self.classes,
|
||||
multi_label=self.multi_label, max_det=self.max_det) # NMS
|
||||
for i in range(n):
|
||||
scale_coords(shape1, y[i][:, :4], shape0[i])
|
||||
|
||||
t.append(time_sync())
|
||||
return Detections(imgs, y, files, t, self.names, x.shape)
|
||||
|
||||
|
||||
class Detections:
|
||||
# YOLOv5 detections class for inference results
|
||||
def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
|
||||
super().__init__()
|
||||
d = pred[0].device # device
|
||||
gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs] # normalizations
|
||||
self.imgs = imgs # list of images as numpy arrays
|
||||
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
|
||||
self.names = names # class names
|
||||
self.files = files # image filenames
|
||||
self.xyxy = pred # xyxy pixels
|
||||
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
|
||||
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
|
||||
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
|
||||
self.n = len(self.pred) # number of images (batch size)
|
||||
self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
|
||||
self.s = shape # inference BCHW shape
|
||||
|
||||
def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
|
||||
crops = []
|
||||
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
|
||||
s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
|
||||
if pred.shape[0]:
|
||||
for c in pred[:, -1].unique():
|
||||
n = (pred[:, -1] == c).sum() # detections per class
|
||||
s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
if show or save or render or crop:
|
||||
annotator = Annotator(im, example=str(self.names))
|
||||
for *box, conf, cls in reversed(pred): # xyxy, confidence, class
|
||||
label = f'{self.names[int(cls)]} {conf:.2f}'
|
||||
if crop:
|
||||
file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
|
||||
crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
|
||||
'im': save_one_box(box, im, file=file, save=save)})
|
||||
else: # all others
|
||||
annotator.box_label(box, label, color=colors(cls))
|
||||
im = annotator.im
|
||||
else:
|
||||
s += '(no detections)'
|
||||
|
||||
im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
|
||||
if pprint:
|
||||
LOGGER.info(s.rstrip(', '))
|
||||
if show:
|
||||
im.show(self.files[i]) # show
|
||||
if save:
|
||||
f = self.files[i]
|
||||
im.save(save_dir / f) # save
|
||||
if i == self.n - 1:
|
||||
LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
|
||||
if render:
|
||||
self.imgs[i] = np.asarray(im)
|
||||
if crop:
|
||||
if save:
|
||||
LOGGER.info(f'Saved results to {save_dir}\n')
|
||||
return crops
|
||||
|
||||
def print(self):
|
||||
self.display(pprint=True) # print results
|
||||
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
|
||||
self.t)
|
||||
|
||||
def show(self):
|
||||
self.display(show=True) # show results
|
||||
|
||||
def save(self, save_dir='runs/detect/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir
|
||||
self.display(save=True, save_dir=save_dir) # save results
|
||||
|
||||
def crop(self, save=True, save_dir='runs/detect/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
|
||||
return self.display(crop=True, save=save, save_dir=save_dir) # crop results
|
||||
|
||||
def render(self):
|
||||
self.display(render=True) # render results
|
||||
return self.imgs
|
||||
|
||||
def pandas(self):
|
||||
# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
|
||||
new = copy(self) # return copy
|
||||
ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
|
||||
cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
|
||||
for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
|
||||
a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
|
||||
setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
|
||||
return new
|
||||
|
||||
def tolist(self):
|
||||
# return a list of Detections objects, i.e. 'for result in results.tolist():'
|
||||
x = [Detections([self.imgs[i]], [self.pred[i]], self.names, self.s) for i in range(self.n)]
|
||||
for d in x:
|
||||
for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
|
||||
setattr(d, k, getattr(d, k)[0]) # pop out of list
|
||||
return x
|
||||
|
||||
def __len__(self):
|
||||
return self.n
|
||||
|
||||
|
||||
class Classify(nn.Module):
|
||||
# Classification head, i.e. x(b,c1,20,20) to x(b,c2)
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.aap = nn.AdaptiveAvgPool2d(1) # to x(b,c1,1,1)
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g) # to x(b,c2,1,1)
|
||||
self.flat = nn.Flatten()
|
||||
|
||||
def forward(self, x):
|
||||
z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1) # cat if list
|
||||
return self.flat(self.conv(z)) # flatten to x(b,c2)
|
||||
|
|
@ -0,0 +1,119 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Experimental modules
|
||||
"""
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from models.common import Conv
|
||||
from utils.downloads import attempt_download
|
||||
|
||||
|
||||
class CrossConv(nn.Module):
|
||||
# Cross Convolution Downsample
|
||||
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
|
||||
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, (1, k), (1, s))
|
||||
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class Sum(nn.Module):
|
||||
# Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
|
||||
def __init__(self, n, weight=False): # n: number of inputs
|
||||
super().__init__()
|
||||
self.weight = weight # apply weights boolean
|
||||
self.iter = range(n - 1) # iter object
|
||||
if weight:
|
||||
self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True) # layer weights
|
||||
|
||||
def forward(self, x):
|
||||
y = x[0] # no weight
|
||||
if self.weight:
|
||||
w = torch.sigmoid(self.w) * 2
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1] * w[i]
|
||||
else:
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1]
|
||||
return y
|
||||
|
||||
|
||||
class MixConv2d(nn.Module):
|
||||
# Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
|
||||
def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
|
||||
super().__init__()
|
||||
groups = len(k)
|
||||
if equal_ch: # equal c_ per group
|
||||
i = torch.linspace(0, groups - 1E-6, c2).floor() # c2 indices
|
||||
c_ = [(i == g).sum() for g in range(groups)] # intermediate channels
|
||||
else: # equal weight.numel() per group
|
||||
b = [c2] + [0] * groups
|
||||
a = np.eye(groups + 1, groups, k=-1)
|
||||
a -= np.roll(a, 1, axis=1)
|
||||
a *= np.array(k) ** 2
|
||||
a[0] = 1
|
||||
c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
|
||||
|
||||
self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.LeakyReLU(0.1, inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
|
||||
|
||||
|
||||
class Ensemble(nn.ModuleList):
|
||||
# Ensemble of models
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
|
||||
def forward(self, x, augment=False, profile=False, visualize=False):
|
||||
y = []
|
||||
for module in self:
|
||||
y.append(module(x, augment, profile, visualize)[0])
|
||||
# y = torch.stack(y).max(0)[0] # max ensemble
|
||||
# y = torch.stack(y).mean(0) # mean ensemble
|
||||
y = torch.cat(y, 1) # nms ensemble
|
||||
return y, None # inference, train output
|
||||
|
||||
|
||||
def attempt_load(weights, map_location=None, inplace=True, fuse=True):
|
||||
from models.yolo import Detect, Model
|
||||
|
||||
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
|
||||
model = Ensemble()
|
||||
for w in weights if isinstance(weights, list) else [weights]:
|
||||
ckpt = torch.load(attempt_download(w), map_location=map_location) # load
|
||||
if fuse:
|
||||
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
|
||||
else:
|
||||
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval()) # without layer fuse
|
||||
|
||||
|
||||
# Compatibility updates
|
||||
for m in model.modules():
|
||||
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
|
||||
m.inplace = inplace # pytorch 1.7.0 compatibility
|
||||
if type(m) is Detect:
|
||||
if not isinstance(m.anchor_grid, list): # new Detect Layer compatibility
|
||||
delattr(m, 'anchor_grid')
|
||||
setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
|
||||
elif type(m) is Conv:
|
||||
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
|
||||
|
||||
if len(model) == 1:
|
||||
return model[-1] # return model
|
||||
else:
|
||||
print(f'Ensemble created with {weights}\n')
|
||||
for k in ['names']:
|
||||
setattr(model, k, getattr(model[-1], k))
|
||||
model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride
|
||||
return model # return ensemble
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Default anchors for COCO data
|
||||
|
||||
|
||||
# P5 -------------------------------------------------------------------------------------------------------------------
|
||||
# P5-640:
|
||||
anchors_p5_640:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
|
||||
# P6 -------------------------------------------------------------------------------------------------------------------
|
||||
# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
|
||||
anchors_p6_640:
|
||||
- [9,11, 21,19, 17,41] # P3/8
|
||||
- [43,32, 39,70, 86,64] # P4/16
|
||||
- [65,131, 134,130, 120,265] # P5/32
|
||||
- [282,180, 247,354, 512,387] # P6/64
|
||||
|
||||
# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792
|
||||
anchors_p6_1280:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187
|
||||
anchors_p6_1920:
|
||||
- [28,41, 67,59, 57,141] # P3/8
|
||||
- [144,103, 129,227, 270,205] # P4/16
|
||||
- [209,452, 455,396, 358,812] # P5/32
|
||||
- [653,922, 1109,570, 1387,1187] # P6/64
|
||||
|
||||
|
||||
# P7 -------------------------------------------------------------------------------------------------------------------
|
||||
# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372
|
||||
anchors_p7_640:
|
||||
- [11,11, 13,30, 29,20] # P3/8
|
||||
- [30,46, 61,38, 39,92] # P4/16
|
||||
- [78,80, 146,66, 79,163] # P5/32
|
||||
- [149,150, 321,143, 157,303] # P6/64
|
||||
- [257,402, 359,290, 524,372] # P7/128
|
||||
|
||||
# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818
|
||||
anchors_p7_1280:
|
||||
- [19,22, 54,36, 32,77] # P3/8
|
||||
- [70,83, 138,71, 75,173] # P4/16
|
||||
- [165,159, 148,334, 375,151] # P5/32
|
||||
- [334,317, 251,626, 499,474] # P6/64
|
||||
- [750,326, 534,814, 1079,818] # P7/128
|
||||
|
||||
# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227
|
||||
anchors_p7_1920:
|
||||
- [29,34, 81,55, 47,115] # P3/8
|
||||
- [105,124, 207,107, 113,259] # P4/16
|
||||
- [247,238, 222,500, 563,227] # P5/32
|
||||
- [501,476, 376,939, 749,711] # P6/64
|
||||
- [1126,489, 801,1222, 1618,1227] # P7/128
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3-SPP head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, SPP, [512, [5, 9, 13]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,14, 23,27, 37,58] # P4/16
|
||||
- [81,82, 135,169, 344,319] # P5/32
|
||||
|
||||
# YOLOv3-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [16, 3, 1]], # 0
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11
|
||||
[-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12
|
||||
]
|
||||
|
||||
# YOLOv3-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium)
|
||||
|
||||
[[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3 head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, Conv, [512, [1, 1]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]]
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 BiFPN head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14, 6], 1, Concat, [1]], # cat P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 6, BottleneckCSP, [1024]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 FPN head
|
||||
head:
|
||||
[[-1, 3, BottleneckCSP, [1024, False]], # 10 (P5/32-large)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 14 (P4/16-medium)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 3, BottleneckCSP, [256, False]], # 18 (P3/8-small)
|
||||
|
||||
[[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,54 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 2], 1, Concat, [1]], # cat backbone P2
|
||||
[-1, 1, C3, [128, False]], # 21 (P2/4-xsmall)
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, 18], 1, Concat, [1]], # cat head P3
|
||||
[-1, 3, C3, [256, False]], # 24 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 27 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 30 (P5/32-large)
|
||||
|
||||
[[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P2, P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 1, SPP, [1024, [3, 5, 7]]],
|
||||
[-1, 3, C3, [1024, False]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P5/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,67 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, Conv, [1280, 3, 2]], # 11-P7/128
|
||||
[-1, 1, SPP, [1280, [3, 5]]],
|
||||
[-1, 3, C3, [1280, False]], # 13
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 10], 1, Concat, [1]], # cat backbone P6
|
||||
[-1, 3, C3, [1024, False]], # 17
|
||||
|
||||
[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 21
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 25
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 29 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 26], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 32 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 22], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 35 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 18], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 38 (P6/64-xlarge)
|
||||
|
||||
[-1, 1, Conv, [1024, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P7
|
||||
[-1, 3, C3, [1280, False]], # 41 (P7/128-xxlarge)
|
||||
|
||||
[[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6, P7)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, BottleneckCSP, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 PANet head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, BottleneckCSP, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.25 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, GhostConv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3Ghost, [128]],
|
||||
[-1, 1, GhostConv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3Ghost, [256]],
|
||||
[-1, 1, GhostConv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3Ghost, [512]],
|
||||
[-1, 1, GhostConv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3Ghost, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, GhostConv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3Ghost, [512, False]], # 13
|
||||
|
||||
[-1, 1, GhostConv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3Ghost, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, GhostConv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3Ghost, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, GhostConv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3Ghost, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3TR, [1024, False]], # 9 <-------- C3TR() Transformer module
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
|
|
@ -0,0 +1,466 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
TensorFlow, Keras and TFLite versions of YOLOv5
|
||||
Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
|
||||
|
||||
Usage:
|
||||
$ python models/tf.py --weights yolov5s.pt
|
||||
|
||||
Export:
|
||||
$ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
# ROOT = ROOT.relative_to(Path.cwd()) # relative
|
||||
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from tensorflow import keras
|
||||
|
||||
from models.common import Bottleneck, BottleneckCSP, Concat, Conv, C3, DWConv, Focus, SPP, SPPF, autopad
|
||||
from models.experimental import CrossConv, MixConv2d, attempt_load
|
||||
from models.yolo import Detect
|
||||
from utils.general import make_divisible, print_args, set_logging
|
||||
from utils.activations import SiLU
|
||||
|
||||
LOGGER = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class TFBN(keras.layers.Layer):
|
||||
# TensorFlow BatchNormalization wrapper
|
||||
def __init__(self, w=None):
|
||||
super(TFBN, self).__init__()
|
||||
self.bn = keras.layers.BatchNormalization(
|
||||
beta_initializer=keras.initializers.Constant(w.bias.numpy()),
|
||||
gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
|
||||
moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
|
||||
moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
|
||||
epsilon=w.eps)
|
||||
|
||||
def call(self, inputs):
|
||||
return self.bn(inputs)
|
||||
|
||||
|
||||
class TFPad(keras.layers.Layer):
|
||||
def __init__(self, pad):
|
||||
super(TFPad, self).__init__()
|
||||
self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
|
||||
|
||||
def call(self, inputs):
|
||||
return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
|
||||
|
||||
|
||||
class TFConv(keras.layers.Layer):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
|
||||
# ch_in, ch_out, weights, kernel, stride, padding, groups
|
||||
super(TFConv, self).__init__()
|
||||
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
|
||||
assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
|
||||
# TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
|
||||
# see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
|
||||
|
||||
conv = keras.layers.Conv2D(
|
||||
c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True,
|
||||
kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
|
||||
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
|
||||
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
|
||||
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
|
||||
|
||||
# YOLOv5 activations
|
||||
if isinstance(w.act, nn.LeakyReLU):
|
||||
self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity
|
||||
elif isinstance(w.act, nn.Hardswish):
|
||||
self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity
|
||||
elif isinstance(w.act, (nn.SiLU, SiLU)):
|
||||
self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity
|
||||
else:
|
||||
raise Exception(f'no matching TensorFlow activation found for {w.act}')
|
||||
|
||||
def call(self, inputs):
|
||||
return self.act(self.bn(self.conv(inputs)))
|
||||
|
||||
|
||||
class TFFocus(keras.layers.Layer):
|
||||
# Focus wh information into c-space
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
|
||||
# ch_in, ch_out, kernel, stride, padding, groups
|
||||
super(TFFocus, self).__init__()
|
||||
self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
|
||||
|
||||
def call(self, inputs): # x(b,w,h,c) -> y(b,w/2,h/2,4c)
|
||||
# inputs = inputs / 255. # normalize 0-255 to 0-1
|
||||
return self.conv(tf.concat([inputs[:, ::2, ::2, :],
|
||||
inputs[:, 1::2, ::2, :],
|
||||
inputs[:, ::2, 1::2, :],
|
||||
inputs[:, 1::2, 1::2, :]], 3))
|
||||
|
||||
|
||||
class TFBottleneck(keras.layers.Layer):
|
||||
# Standard bottleneck
|
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None): # ch_in, ch_out, shortcut, groups, expansion
|
||||
super(TFBottleneck, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def call(self, inputs):
|
||||
return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
|
||||
|
||||
|
||||
class TFConv2d(keras.layers.Layer):
|
||||
# Substitution for PyTorch nn.Conv2D
|
||||
def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
|
||||
super(TFConv2d, self).__init__()
|
||||
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
|
||||
self.conv = keras.layers.Conv2D(
|
||||
c2, k, s, 'VALID', use_bias=bias,
|
||||
kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
|
||||
bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, )
|
||||
|
||||
def call(self, inputs):
|
||||
return self.conv(inputs)
|
||||
|
||||
|
||||
class TFBottleneckCSP(keras.layers.Layer):
|
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
|
||||
# ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super(TFBottleneckCSP, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
|
||||
self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
|
||||
self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
|
||||
self.bn = TFBN(w.bn)
|
||||
self.act = lambda x: keras.activations.relu(x, alpha=0.1)
|
||||
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
|
||||
|
||||
def call(self, inputs):
|
||||
y1 = self.cv3(self.m(self.cv1(inputs)))
|
||||
y2 = self.cv2(inputs)
|
||||
return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
|
||||
|
||||
|
||||
class TFC3(keras.layers.Layer):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
|
||||
# ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super(TFC3, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
|
||||
self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
|
||||
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
|
||||
|
||||
def call(self, inputs):
|
||||
return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
|
||||
|
||||
|
||||
class TFSPP(keras.layers.Layer):
|
||||
# Spatial pyramid pooling layer used in YOLOv3-SPP
|
||||
def __init__(self, c1, c2, k=(5, 9, 13), w=None):
|
||||
super(TFSPP, self).__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
|
||||
self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
|
||||
|
||||
def call(self, inputs):
|
||||
x = self.cv1(inputs)
|
||||
return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
|
||||
|
||||
|
||||
class TFSPPF(keras.layers.Layer):
|
||||
# Spatial pyramid pooling-Fast layer
|
||||
def __init__(self, c1, c2, k=5, w=None):
|
||||
super(TFSPPF, self).__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
|
||||
self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
|
||||
|
||||
def call(self, inputs):
|
||||
x = self.cv1(inputs)
|
||||
y1 = self.m(x)
|
||||
y2 = self.m(y1)
|
||||
return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
|
||||
|
||||
|
||||
class TFDetect(keras.layers.Layer):
|
||||
def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None): # detection layer
|
||||
super(TFDetect, self).__init__()
|
||||
self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [tf.zeros(1)] * self.nl # init grid
|
||||
self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
|
||||
self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]),
|
||||
[self.nl, 1, -1, 1, 2])
|
||||
self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
|
||||
self.training = False # set to False after building model
|
||||
self.imgsz = imgsz
|
||||
for i in range(self.nl):
|
||||
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
|
||||
self.grid[i] = self._make_grid(nx, ny)
|
||||
|
||||
def call(self, inputs):
|
||||
z = [] # inference output
|
||||
x = []
|
||||
for i in range(self.nl):
|
||||
x.append(self.m[i](inputs[i]))
|
||||
# x(bs,20,20,255) to x(bs,3,20,20,85)
|
||||
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
|
||||
x[i] = tf.transpose(tf.reshape(x[i], [-1, ny * nx, self.na, self.no]), [0, 2, 1, 3])
|
||||
|
||||
if not self.training: # inference
|
||||
y = tf.sigmoid(x[i])
|
||||
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
|
||||
# Normalize xywh to 0-1 to reduce calibration error
|
||||
xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
|
||||
wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
|
||||
y = tf.concat([xy, wh, y[..., 4:]], -1)
|
||||
z.append(tf.reshape(y, [-1, 3 * ny * nx, self.no]))
|
||||
|
||||
return x if self.training else (tf.concat(z, 1), x)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
# yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
# return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
|
||||
return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
|
||||
|
||||
|
||||
class TFUpsample(keras.layers.Layer):
|
||||
def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w'
|
||||
super(TFUpsample, self).__init__()
|
||||
assert scale_factor == 2, "scale_factor must be 2"
|
||||
self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
|
||||
# self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
|
||||
# with default arguments: align_corners=False, half_pixel_centers=False
|
||||
# self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
|
||||
# size=(x.shape[1] * 2, x.shape[2] * 2))
|
||||
|
||||
def call(self, inputs):
|
||||
return self.upsample(inputs)
|
||||
|
||||
|
||||
class TFConcat(keras.layers.Layer):
|
||||
def __init__(self, dimension=1, w=None):
|
||||
super(TFConcat, self).__init__()
|
||||
assert dimension == 1, "convert only NCHW to NHWC concat"
|
||||
self.d = 3
|
||||
|
||||
def call(self, inputs):
|
||||
return tf.concat(inputs, self.d)
|
||||
|
||||
|
||||
def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
|
||||
LOGGER.info('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m_str = m
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
try:
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
except NameError:
|
||||
pass
|
||||
|
||||
n = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
|
||||
c1, c2 = ch[f], args[0]
|
||||
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [BottleneckCSP, C3]:
|
||||
args.insert(2, n)
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum([ch[-1 if x == -1 else x + 1] for x in f])
|
||||
elif m is Detect:
|
||||
args.append([ch[x + 1] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
args.append(imgsz)
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
tf_m = eval('TF' + m_str.replace('nn.', ''))
|
||||
m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
|
||||
else tf_m(*args, w=model.model[i]) # module
|
||||
|
||||
torch_m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum([x.numel() for x in torch_m_.parameters()]) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
LOGGER.info('%3s%18s%3s%10.0f %-40s%-30s' % (i, f, n, np, t, args)) # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
ch.append(c2)
|
||||
return keras.Sequential(layers), sorted(save)
|
||||
|
||||
|
||||
class TFModel:
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
|
||||
super(TFModel, self).__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg) as f:
|
||||
self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict
|
||||
|
||||
# Define model
|
||||
if nc and nc != self.yaml['nc']:
|
||||
print('Overriding %s nc=%g with nc=%g' % (cfg, self.yaml['nc'], nc))
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
|
||||
|
||||
def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
|
||||
conf_thres=0.25):
|
||||
y = [] # outputs
|
||||
x = inputs
|
||||
for i, m in enumerate(self.model.layers):
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.savelist else None) # save output
|
||||
|
||||
# Add TensorFlow NMS
|
||||
if tf_nms:
|
||||
boxes = self._xywh2xyxy(x[0][..., :4])
|
||||
probs = x[0][:, :, 4:5]
|
||||
classes = x[0][:, :, 5:]
|
||||
scores = probs * classes
|
||||
if agnostic_nms:
|
||||
nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
|
||||
return nms, x[1]
|
||||
else:
|
||||
boxes = tf.expand_dims(boxes, 2)
|
||||
nms = tf.image.combined_non_max_suppression(
|
||||
boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False)
|
||||
return nms, x[1]
|
||||
|
||||
return x[0] # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
|
||||
# x = x[0][0] # [x(1,6300,85), ...] to x(6300,85)
|
||||
# xywh = x[..., :4] # x(6300,4) boxes
|
||||
# conf = x[..., 4:5] # x(6300,1) confidences
|
||||
# cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1)) # x(6300,1) classes
|
||||
# return tf.concat([conf, cls, xywh], 1)
|
||||
|
||||
@staticmethod
|
||||
def _xywh2xyxy(xywh):
|
||||
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
|
||||
return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
|
||||
|
||||
|
||||
class AgnosticNMS(keras.layers.Layer):
|
||||
# TF Agnostic NMS
|
||||
def call(self, input, topk_all, iou_thres, conf_thres):
|
||||
# wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
|
||||
return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input,
|
||||
fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
|
||||
name='agnostic_nms')
|
||||
|
||||
@staticmethod
|
||||
def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25): # agnostic NMS
|
||||
boxes, classes, scores = x
|
||||
class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
|
||||
scores_inp = tf.reduce_max(scores, -1)
|
||||
selected_inds = tf.image.non_max_suppression(
|
||||
boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres)
|
||||
selected_boxes = tf.gather(boxes, selected_inds)
|
||||
padded_boxes = tf.pad(selected_boxes,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
|
||||
mode="CONSTANT", constant_values=0.0)
|
||||
selected_scores = tf.gather(scores_inp, selected_inds)
|
||||
padded_scores = tf.pad(selected_scores,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
|
||||
mode="CONSTANT", constant_values=-1.0)
|
||||
selected_classes = tf.gather(class_inds, selected_inds)
|
||||
padded_classes = tf.pad(selected_classes,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
|
||||
mode="CONSTANT", constant_values=-1.0)
|
||||
valid_detections = tf.shape(selected_inds)[0]
|
||||
return padded_boxes, padded_scores, padded_classes, valid_detections
|
||||
|
||||
|
||||
def representative_dataset_gen(dataset, ncalib=100):
|
||||
# Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
|
||||
for n, (path, img, im0s, vid_cap) in enumerate(dataset):
|
||||
input = np.transpose(img, [1, 2, 0])
|
||||
input = np.expand_dims(input, axis=0).astype(np.float32)
|
||||
input /= 255.0
|
||||
yield [input]
|
||||
if n >= ncalib:
|
||||
break
|
||||
|
||||
|
||||
def run(weights=ROOT / 'yolov5s.pt', # weights path
|
||||
imgsz=(640, 640), # inference size h,w
|
||||
batch_size=1, # batch size
|
||||
dynamic=False, # dynamic batch size
|
||||
):
|
||||
# PyTorch model
|
||||
im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image
|
||||
model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
|
||||
y = model(im) # inference
|
||||
model.info()
|
||||
|
||||
# TensorFlow model
|
||||
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC image
|
||||
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
|
||||
y = tf_model.predict(im) # inference
|
||||
|
||||
# Keras model
|
||||
im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
|
||||
keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
|
||||
keras_model.summary()
|
||||
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
||||
parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
|
||||
opt = parser.parse_args()
|
||||
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
||||
print_args(FILE.stem, opt)
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
set_logging()
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
|
|
@ -0,0 +1,327 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
YOLO-specific modules
|
||||
|
||||
Usage:
|
||||
$ python path/to/models/yolo.py --cfg yolov5s.yaml
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
# ROOT = ROOT.relative_to(Path.cwd()) # relative
|
||||
|
||||
from models.common import *
|
||||
from models.experimental import *
|
||||
from utils.autoanchor import check_anchor_order
|
||||
from utils.general import check_yaml, make_divisible, print_args, set_logging
|
||||
from utils.plots import feature_visualization
|
||||
from utils.torch_utils import copy_attr, fuse_conv_and_bn, initialize_weights, model_info, scale_img, \
|
||||
select_device, time_sync
|
||||
|
||||
try:
|
||||
import thop # for FLOPs computation
|
||||
except ImportError:
|
||||
thop = None
|
||||
|
||||
LOGGER = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class Detect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
onnx_dynamic = False # ONNX export parameter
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
|
||||
super().__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid
|
||||
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
|
||||
self.inplace = inplace # use in-place ops (e.g. slice assignment)
|
||||
|
||||
def forward(self, x):
|
||||
z = [] # inference output
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](x[i]) # conv
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
|
||||
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
if self.inplace:
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
|
||||
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
y = torch.cat((xy, wh, y[..., 4:]), -1)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
return x if self.training else (torch.cat(z, 1), x)
|
||||
|
||||
def _make_grid(self, nx=20, ny=20, i=0):
|
||||
d = self.anchors[i].device
|
||||
yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
|
||||
grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
|
||||
anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
|
||||
.view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
|
||||
return grid, anchor_grid
|
||||
|
||||
|
||||
class Model(nn.Module):
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
|
||||
super().__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg, errors='ignore') as f:
|
||||
self.yaml = yaml.safe_load(f) # model dict
|
||||
|
||||
# Define model
|
||||
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
|
||||
if nc and nc != self.yaml['nc']:
|
||||
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
if anchors:
|
||||
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
|
||||
self.yaml['anchors'] = round(anchors) # override yaml value
|
||||
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
|
||||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
|
||||
self.inplace = self.yaml.get('inplace', True)
|
||||
|
||||
# Build strides, anchors
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
s = 256 # 2x min stride
|
||||
m.inplace = self.inplace
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
check_anchor_order(m)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases() # only run once
|
||||
|
||||
# Init weights, biases
|
||||
initialize_weights(self)
|
||||
self.info()
|
||||
LOGGER.info('')
|
||||
|
||||
def forward(self, x, augment=False, profile=False, visualize=False):
|
||||
if augment:
|
||||
return self._forward_augment(x) # augmented inference, None
|
||||
return self._forward_once(x, profile, visualize) # single-scale inference, train
|
||||
|
||||
def _forward_augment(self, x):
|
||||
img_size = x.shape[-2:] # height, width
|
||||
s = [1, 0.83, 0.67] # scales
|
||||
f = [None, 3, None] # flips (2-ud, 3-lr)
|
||||
y = [] # outputs
|
||||
for si, fi in zip(s, f):
|
||||
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
|
||||
yi = self._forward_once(xi)[0] # forward
|
||||
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
|
||||
yi = self._descale_pred(yi, fi, si, img_size)
|
||||
y.append(yi)
|
||||
y = self._clip_augmented(y) # clip augmented tails
|
||||
return torch.cat(y, 1), None # augmented inference, train
|
||||
|
||||
def _forward_once(self, x, profile=False, visualize=False):
|
||||
y, dt = [], [] # outputs
|
||||
for m in self.model:
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
if profile:
|
||||
self._profile_one_layer(m, x, dt)
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.save else None) # save output
|
||||
if visualize:
|
||||
feature_visualization(x, m.type, m.i, save_dir=visualize)
|
||||
return x
|
||||
|
||||
def _descale_pred(self, p, flips, scale, img_size):
|
||||
# de-scale predictions following augmented inference (inverse operation)
|
||||
if self.inplace:
|
||||
p[..., :4] /= scale # de-scale
|
||||
if flips == 2:
|
||||
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
|
||||
elif flips == 3:
|
||||
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
|
||||
else:
|
||||
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
|
||||
if flips == 2:
|
||||
y = img_size[0] - y # de-flip ud
|
||||
elif flips == 3:
|
||||
x = img_size[1] - x # de-flip lr
|
||||
p = torch.cat((x, y, wh, p[..., 4:]), -1)
|
||||
return p
|
||||
|
||||
def _clip_augmented(self, y):
|
||||
# Clip YOLOv5 augmented inference tails
|
||||
nl = self.model[-1].nl # number of detection layers (P3-P5)
|
||||
g = sum(4 ** x for x in range(nl)) # grid points
|
||||
e = 1 # exclude layer count
|
||||
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices
|
||||
y[0] = y[0][:, :-i] # large
|
||||
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices
|
||||
y[-1] = y[-1][:, i:] # small
|
||||
return y
|
||||
|
||||
def _profile_one_layer(self, m, x, dt):
|
||||
c = isinstance(m, Detect) # is final layer, copy input as inplace fix
|
||||
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
|
||||
t = time_sync()
|
||||
for _ in range(10):
|
||||
m(x.copy() if c else x)
|
||||
dt.append((time_sync() - t) * 100)
|
||||
if m == self.model[0]:
|
||||
LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} {'module'}")
|
||||
LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
|
||||
if c:
|
||||
LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")
|
||||
|
||||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi, s in zip(m.m, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
|
||||
def _print_biases(self):
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi in m.m: # from
|
||||
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
|
||||
LOGGER.info(
|
||||
('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
|
||||
|
||||
# def _print_weights(self):
|
||||
# for m in self.model.modules():
|
||||
# if type(m) is Bottleneck:
|
||||
# LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||||
|
||||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||||
LOGGER.info('Fusing layers... ')
|
||||
for m in self.model.modules():
|
||||
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
|
||||
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
|
||||
delattr(m, 'bn') # remove batchnorm
|
||||
m.forward = m.forward_fuse # update forward
|
||||
self.info()
|
||||
return self
|
||||
|
||||
def autoshape(self): # add AutoShape module
|
||||
LOGGER.info('Adding AutoShape... ')
|
||||
m = AutoShape(self) # wrap model
|
||||
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
|
||||
return m
|
||||
|
||||
def info(self, verbose=False, img_size=640): # print model information
|
||||
model_info(self, verbose, img_size)
|
||||
|
||||
def _apply(self, fn):
|
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
|
||||
self = super()._apply(fn)
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
m.stride = fn(m.stride)
|
||||
m.grid = list(map(fn, m.grid))
|
||||
if isinstance(m.anchor_grid, list):
|
||||
m.anchor_grid = list(map(fn, m.anchor_grid))
|
||||
return self
|
||||
|
||||
|
||||
def parse_model(d, ch): # model_dict, input_channels(3)
|
||||
LOGGER.info('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
try:
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
except NameError:
|
||||
pass
|
||||
|
||||
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
|
||||
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
|
||||
c1, c2 = ch[f], args[0]
|
||||
if c2 != no: # if not output
|
||||
c2 = make_divisible(c2 * gw, 8)
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
|
||||
args.insert(2, n) # number of repeats
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum([ch[x] for x in f])
|
||||
elif m is Detect:
|
||||
args.append([ch[x] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
elif m is Contract:
|
||||
c2 = ch[f] * args[0] ** 2
|
||||
elif m is Expand:
|
||||
c2 = ch[f] // args[0] ** 2
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum([x.numel() for x in m_.parameters()]) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
LOGGER.info('%3s%18s%3s%10.0f %-40s%-30s' % (i, f, n_, np, t, args)) # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
if i == 0:
|
||||
ch = []
|
||||
ch.append(c2)
|
||||
return nn.Sequential(*layers), sorted(save)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--profile', action='store_true', help='profile model speed')
|
||||
opt = parser.parse_args()
|
||||
opt.cfg = check_yaml(opt.cfg) # check YAML
|
||||
print_args(FILE.stem, opt)
|
||||
set_logging()
|
||||
device = select_device(opt.device)
|
||||
|
||||
# Create model
|
||||
model = Model(opt.cfg).to(device)
|
||||
model.train()
|
||||
|
||||
# Profile
|
||||
if opt.profile:
|
||||
img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
|
||||
y = model(img, profile=True)
|
||||
|
||||
# Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
|
||||
# from torch.utils.tensorboard import SummaryWriter
|
||||
# tb_writer = SummaryWriter('.')
|
||||
# LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
|
||||
# tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.25 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 917 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.3 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.0 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1002 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 870 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.0 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 915 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 909 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.3 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.0 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.3 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1020 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 972 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.0 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 973 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 985 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.3 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.0 KiB |
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue