forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #1540 from WenmuZhou/tree_doc 

update py inference to 2.0 and delete fluid
This commit is contained in:
zhoujun 2020-12-21 17:55:33 +08:00 committed by GitHub
parent 2a789770cd 3a0090dc00
commit 0ec11a29c6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 47 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
ppocr/losses/det_sast_loss.py
View File

@ -19,7 +19,6 @@ from __future__ import print_function
import paddle
from paddle import nn
from .det_basic_loss import DiceLoss
import paddle.fluid as fluid
import numpy as np
@ -27,9 +26,7 @@ class SASTLoss(nn.Layer):
"""
"""
def __init__(self,
eps=1e-6,
**kwargs):
def __init__(self, eps=1e-6, **kwargs):
super(SASTLoss, self).__init__()
self.dice_loss = DiceLoss(eps=eps)
@ -39,7 +36,7 @@ class SASTLoss(nn.Layer):
tcl_mask: N x 128 x 1
tcl_label: N x X list or LoDTensor
"""
f_score = predicts['f_score']
f_border = predicts['f_border']
f_tvo = predicts['f_tvo']
@ -53,15 +50,17 @@ class SASTLoss(nn.Layer):
score_loss = 1.0 - 2 * intersection / (union + 1e-5)
#border loss
l_border_split, l_border_norm = paddle.split(l_border, num_or_sections=[4, 1], axis=1)
l_border_split, l_border_norm = paddle.split(
l_border, num_or_sections=[4, 1], axis=1)
f_border_split = f_border
border_ex_shape = l_border_norm.shape * np.array([1, 4, 1, 1])
l_border_norm_split = paddle.expand(x=l_border_norm, shape=border_ex_shape)
l_border_score = paddle.expand(x=l_score, shape=border_ex_shape)
l_border_mask = paddle.expand(x=l_mask, shape=border_ex_shape)
l_border_norm_split = paddle.expand(
x=l_border_norm, shape=border_ex_shape)
l_border_score = paddle.expand(x=l_score, shape=border_ex_shape)
l_border_mask = paddle.expand(x=l_mask, shape=border_ex_shape)
border_diff = l_border_split - f_border_split
abs_border_diff = paddle.abs(border_diff)
abs_border_diff = paddle.abs(border_diff)
border_sign = abs_border_diff < 1.0
border_sign = paddle.cast(border_sign, dtype='float32')
border_sign.stop_gradient = True
@ -72,15 +71,16 @@ class SASTLoss(nn.Layer):
(paddle.sum(l_border_score * l_border_mask) + 1e-5)
#tvo_loss
l_tvo_split, l_tvo_norm = paddle.split(l_tvo, num_or_sections=[8, 1], axis=1)
l_tvo_split, l_tvo_norm = paddle.split(
l_tvo, num_or_sections=[8, 1], axis=1)
f_tvo_split = f_tvo
tvo_ex_shape = l_tvo_norm.shape * np.array([1, 8, 1, 1])
l_tvo_norm_split = paddle.expand(x=l_tvo_norm, shape=tvo_ex_shape)
l_tvo_score = paddle.expand(x=l_score, shape=tvo_ex_shape)
l_tvo_mask = paddle.expand(x=l_mask, shape=tvo_ex_shape)
l_tvo_score = paddle.expand(x=l_score, shape=tvo_ex_shape)
l_tvo_mask = paddle.expand(x=l_mask, shape=tvo_ex_shape)
#
tvo_geo_diff = l_tvo_split - f_tvo_split
abs_tvo_geo_diff = paddle.abs(tvo_geo_diff)
abs_tvo_geo_diff = paddle.abs(tvo_geo_diff)
tvo_sign = abs_tvo_geo_diff < 1.0
tvo_sign = paddle.cast(tvo_sign, dtype='float32')
tvo_sign.stop_gradient = True
@ -91,15 +91,16 @@ class SASTLoss(nn.Layer):
(paddle.sum(l_tvo_score * l_tvo_mask) + 1e-5)
#tco_loss
l_tco_split, l_tco_norm = paddle.split(l_tco, num_or_sections=[2, 1], axis=1)
l_tco_split, l_tco_norm = paddle.split(
l_tco, num_or_sections=[2, 1], axis=1)
f_tco_split = f_tco
tco_ex_shape = l_tco_norm.shape * np.array([1, 2, 1, 1])
l_tco_norm_split = paddle.expand(x=l_tco_norm, shape=tco_ex_shape)
l_tco_score = paddle.expand(x=l_score, shape=tco_ex_shape)
l_tco_mask = paddle.expand(x=l_mask, shape=tco_ex_shape)
l_tco_score = paddle.expand(x=l_score, shape=tco_ex_shape)
l_tco_mask = paddle.expand(x=l_mask, shape=tco_ex_shape)
tco_geo_diff = l_tco_split - f_tco_split
abs_tco_geo_diff = paddle.abs(tco_geo_diff)
abs_tco_geo_diff = paddle.abs(tco_geo_diff)
tco_sign = abs_tco_geo_diff < 1.0
tco_sign = paddle.cast(tco_sign, dtype='float32')
tco_sign.stop_gradient = True
@ -109,13 +110,12 @@ class SASTLoss(nn.Layer):
tco_loss = paddle.sum(tco_out_loss * l_tco_score * l_tco_mask) / \
(paddle.sum(l_tco_score * l_tco_mask) + 1e-5)
# total loss
tvo_lw, tco_lw = 1.5, 1.5
score_lw, border_lw = 1.0, 1.0
total_loss = score_loss * score_lw + border_loss * border_lw + \
tvo_loss * tvo_lw + tco_loss * tco_lw
losses = {'loss':total_loss, "score_loss":score_loss,\
"border_loss":border_loss, 'tvo_loss':tvo_loss, 'tco_loss':tco_loss}
return losses
return losses

15
tools/infer/predict_cls.py
View File

@ -24,7 +24,6 @@ import numpy as np
import math
import time
import traceback
import paddle.fluid as fluid
import tools.infer.utility as utility
from ppocr.postprocess import build_post_process
@ -39,7 +38,6 @@ class TextClassifier(object):
self.cls_image_shape = [int(v) for v in args.cls_image_shape.split(",")]
self.cls_batch_num = args.cls_batch_num
self.cls_thresh = args.cls_thresh
self.use_zero_copy_run = args.use_zero_copy_run
postprocess_params = {
'name': 'ClsPostProcess',
"label_list": args.label_list,
@ -99,12 +97,8 @@ class TextClassifier(object):
norm_img_batch = norm_img_batch.copy()
starttime = time.time()
if self.use_zero_copy_run:
self.input_tensor.copy_from_cpu(norm_img_batch)
self.predictor.zero_copy_run()
else:
norm_img_batch = fluid.core.PaddleTensor(norm_img_batch)
self.predictor.run([norm_img_batch])
self.input_tensor.copy_from_cpu(norm_img_batch)
self.predictor.run()
prob_out = self.output_tensors[0].copy_to_cpu()
cls_result = self.postprocess_op(prob_out)
elapse += time.time() - starttime
@ -143,10 +137,11 @@ def main(args):
"Please set --rec_image_shape='3,32,100' and --rec_char_type='en' ")
exit()
for ino in range(len(img_list)):
logger.info("Predicts of {}:{}".format(valid_image_file_list[ino], cls_res[
ino]))
logger.info("Predicts of {}:{}".format(valid_image_file_list[ino],
cls_res[ino]))
logger.info("Total predict time for {} images, cost: {:.3f}".format(
len(img_list), predict_time))
if __name__ == "__main__":
main(utility.parse_args())

14
tools/infer/predict_det.py
View File

@ -22,7 +22,6 @@ import cv2
import numpy as np
import time
import sys
import paddle
import tools.infer.utility as utility
from ppocr.utils.logging import get_logger
@ -37,7 +36,6 @@ class TextDetector(object):
def __init__(self, args):
self.args = args
self.det_algorithm = args.det_algorithm
self.use_zero_copy_run = args.use_zero_copy_run
pre_process_list = [{
'DetResizeForTest': {
'limit_side_len': args.det_limit_side_len,
@ -72,7 +70,9 @@ class TextDetector(object):
postprocess_params["nms_thresh"] = args.det_east_nms_thresh
elif self.det_algorithm == "SAST":
pre_process_list[0] = {
'DetResizeForTest': {'resize_long': args.det_limit_side_len}
'DetResizeForTest': {
'resize_long': args.det_limit_side_len
}
}
postprocess_params['name'] = 'SASTPostProcess'
postprocess_params["score_thresh"] = args.det_sast_score_thresh
@ -161,12 +161,8 @@ class TextDetector(object):
img = img.copy()
starttime = time.time()
if self.use_zero_copy_run:
self.input_tensor.copy_from_cpu(img)
self.predictor.zero_copy_run()
else:
im = paddle.fluid.core.PaddleTensor(img)
self.predictor.run([im])
self.input_tensor.copy_from_cpu(img)
self.predictor.run()
outputs = []
for output_tensor in self.output_tensors:
output = output_tensor.copy_to_cpu()

14
tools/infer/predict_rec.py
View File

@ -23,7 +23,6 @@ import numpy as np
import math
import time
import traceback
import paddle.fluid as fluid
import tools.infer.utility as utility
from ppocr.postprocess import build_post_process
@ -39,7 +38,6 @@ class TextRecognizer(object):
self.character_type = args.rec_char_type
self.rec_batch_num = args.rec_batch_num
self.rec_algorithm = args.rec_algorithm
self.use_zero_copy_run = args.use_zero_copy_run
postprocess_params = {
'name': 'CTCLabelDecode',
"character_type": args.rec_char_type,
@ -101,12 +99,8 @@ class TextRecognizer(object):
norm_img_batch = np.concatenate(norm_img_batch)
norm_img_batch = norm_img_batch.copy()
starttime = time.time()
if self.use_zero_copy_run:
self.input_tensor.copy_from_cpu(norm_img_batch)
self.predictor.zero_copy_run()
else:
norm_img_batch = fluid.core.PaddleTensor(norm_img_batch)
self.predictor.run([norm_img_batch])
self.input_tensor.copy_from_cpu(norm_img_batch)
self.predictor.run()
outputs = []
for output_tensor in self.output_tensors:
output = output_tensor.copy_to_cpu()
@ -145,8 +139,8 @@ def main(args):
"Please set --rec_image_shape='3,32,100' and --rec_char_type='en' ")
exit()
for ino in range(len(img_list)):
logger.info("Predicts of {}:{}".format(valid_image_file_list[ino], rec_res[
ino]))
logger.info("Predicts of {}:{}".format(valid_image_file_list[ino],
rec_res[ino]))
logger.info("Total predict time for {} images, cost: {:.3f}".format(
len(img_list), predict_time))

25
tools/infer/utility.py
View File

@ -20,8 +20,7 @@ import numpy as np
import json
from PIL import Image, ImageDraw, ImageFont
import math
from paddle.fluid.core import AnalysisConfig
from paddle.fluid.core import create_paddle_predictor
from paddle import inference
def parse_args():
@ -83,8 +82,6 @@ def parse_args():
parser.add_argument("--cls_thresh", type=float, default=0.9)
parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
parser.add_argument("--use_zero_copy_run", type=str2bool, default=False)
parser.add_argument("--use_pdserving", type=str2bool, default=False)
return parser.parse_args()
@ -110,14 +107,14 @@ def create_predictor(args, mode, logger):
logger.info("not find params file path {}".format(params_file_path))
sys.exit(0)
config = AnalysisConfig(model_file_path, params_file_path)
config = inference.Config(model_file_path, params_file_path)
if args.use_gpu:
config.enable_use_gpu(args.gpu_mem, 0)
if args.use_tensorrt:
config.enable_tensorrt_engine(
precision_mode=AnalysisConfig.Precision.Half
if args.use_fp16 else AnalysisConfig.Precision.Float32,
precision_mode=inference.PrecisionType.Half
if args.use_fp16 else inference.PrecisionType.Float32,
max_batch_size=args.max_batch_size)
else:
config.disable_gpu()
@ -130,20 +127,18 @@ def create_predictor(args, mode, logger):
# config.enable_memory_optim()
config.disable_glog_info()
if args.use_zero_copy_run:
config.delete_pass("conv_transpose_eltwiseadd_bn_fuse_pass")
config.switch_use_feed_fetch_ops(False)
else:
config.switch_use_feed_fetch_ops(True)
config.delete_pass("conv_transpose_eltwiseadd_bn_fuse_pass")
config.switch_use_feed_fetch_ops(False)
predictor = create_paddle_predictor(config)
# create predictor
predictor = inference.create_predictor(config)
input_names = predictor.get_input_names()
for name in input_names:
input_tensor = predictor.get_input_tensor(name)
input_tensor = predictor.get_input_handle(name)
output_names = predictor.get_output_names()
output_tensors = []
for output_name in output_names:
output_tensor = predictor.get_output_tensor(output_name)
output_tensor = predictor.get_output_handle(output_name)
output_tensors.append(output_tensor)
return predictor, input_tensor, output_tensors

2
tools/program.py
View File

@ -131,7 +131,7 @@ def check_gpu(use_gpu):
"model on CPU"
try:
if use_gpu and not paddle.fluid.is_compiled_with_cuda():
if use_gpu and not paddle.is_compiled_with_cuda():
print(err)
sys.exit(1)
except Exception as e: