测试完成yolov5

.idea/code.iml

@@ -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>

.idea/misc.xml

@@ -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>

detect.py

@@ -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

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):
+    def __init__(self, value, array):
-        self.v = v
+        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.mp_drawing.draw_landmarks(
+                        #     self.image, self.identify_results.multi_hand_landmarks[i], self.mp_hands.HAND_CONNECTIONS)
-                            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.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.mp_drawing.draw_landmarks(
-                            self.image, self.identify_results.multi_hand_landmarks[i], self.mp_hands.HAND_CONNECTIONS)
+                        #     self.image, self.identify_results.multi_hand_landmarks[i], self.mp_hands.HAND_CONNECTIONS)
-                        self.right_hand_flag = True
+                        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):
+        if self.step_up == 0 and self.judge_step_three():
-            self.step = 1
+            self.step_up = 4
-        elif self.step == 1 and self.judge_step_two(False):
+        if self.step_up == 4 and self.judge_step_one(False):
-            self.step = 3
+            self.step_up = 1
-        elif self.step == 2 and self.judge_zero():
+        elif self.step_up == 1 and self.judge_step_two(False):
-            self.step = 3
+            self.step_up = 3
-        elif self.step == 3:
+        elif self.step_up == 2 and self.judge_zero():
-            self.step = 0
+            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):
+        if self.step_down == 0 and self.judge_step_three():
-            self.step = 1
+            self.step_down = 4
-        elif self.step == 1 and self.judge_step_two(True):
+            print("step = 1")
-            self.step = 3
+        if self.step_down == 4 and self.judge_step_one(True):
-        elif self.step == 2 and self.judge_zero():
+            self.step_down = 1
-            self.step = 3
+            print("step = 2")
-        elif self.step == 3:
+        elif self.step_down == 1 and self.judge_step_two(True):
-            self.step = 0
+            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:

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)
-
+        # print("***********array************")
-        control_flag = v.value
+        # 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):
+def identify_thread(value, array):
-    identify = Identify(v)
+    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)
+    value = multiprocessing.Value('i', 0)
-    p1 = multiprocessing.Process(target=identify_thread, args=(v, 0))
+    array = multiprocessing.Array('i', 4)
-    p2 = multiprocessing.Process(target=control_thread, args=(v, 0))
+    # 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__':

models/common.py

@@ -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)

models/experimental.py

@@ -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

models/hub/anchors.yaml

@@ -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

models/hub/yolov3-spp.yaml

@@ -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)
+  ]

models/hub/yolov3-tiny.yaml

@@ -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)
+  ]

models/hub/yolov3.yaml

@@ -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)
+  ]

models/hub/yolov5-bifpn.yaml

@@ -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)
+  ]

models/hub/yolov5-fpn.yaml

@@ -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)
+  ]

models/hub/yolov5-p2.yaml

@@ -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)
+  ]

models/hub/yolov5-p6.yaml

@@ -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)
+  ]

models/hub/yolov5-p7.yaml

@@ -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)
+  ]

models/hub/yolov5-panet.yaml

@@ -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)
+  ]

models/hub/yolov5l6.yaml

@@ -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)
+  ]

models/hub/yolov5m6.yaml

@@ -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)
+  ]

models/hub/yolov5n6.yaml

@@ -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)
+  ]

models/hub/yolov5s-ghost.yaml

@@ -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)
+  ]

models/hub/yolov5s-transformer.yaml

@@ -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)
+  ]

models/hub/yolov5s6.yaml

@@ -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)
+  ]

models/hub/yolov5x6.yaml

@@ -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)
+  ]

models/tf.py

@@ -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)

models/yolo.py

@@ -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

models/yolov5l.yaml

@@ -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)
+  ]

models/yolov5m.yaml

@@ -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)
+  ]

models/yolov5n.yaml

@@ -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)
+  ]

models/yolov5s.yaml

@@ -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)
+  ]

models/yolov5x.yaml

@@ -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)
+  ]