def __init__(self, args):
pre_process_list = [{
'ResizeTableImage': {
'max_len': args.table_max_len
}
}, {
'NormalizeImage': {
'std': [0.229, 0.224, 0.225],
'mean': [0.485, 0.456, 0.406],
'scale': '1./255.',
'order': 'hwc'
}
}, {
'PaddingTableImage': None
}, {
'ToCHWImage': None
}, {
'KeepKeys': {
'keep_keys': ['image']
}
}]
postprocess_params = {
'name': 'TableLabelDecode',
"character_type": args.table_char_type,
"character_dict_path": args.table_char_dict_path,
}
self.preprocess_op = create_operators(pre_process_list)
self.postprocess_op = build_post_process(postprocess_params)
self.predictor, self.input_tensor, self.output_tensors, self.config = \
utility.create_predictor(args, 'table', logger)
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,
'limit_type': args.det_limit_type
}
}, {
'NormalizeImage': {
'std': [0.229, 0.224, 0.225],
'mean': [0.485, 0.456, 0.406],
'scale': '1./255.',
'order': 'hwc'
}
}, {
'ToCHWImage': None
}, {
'KeepKeys': {
'keep_keys': ['image', 'shape']
}
}]
postprocess_params = {}
if self.det_algorithm == "DB":
postprocess_params['name'] = 'DBPostProcess'
postprocess_params["thresh"] = args.det_db_thresh
postprocess_params["box_thresh"] = args.det_db_box_thresh
postprocess_params["max_candidates"] = 1000
postprocess_params["unclip_ratio"] = args.det_db_unclip_ratio
postprocess_params["use_dilation"] = True
elif self.det_algorithm == "EAST":
postprocess_params['name'] = 'EASTPostProcess'
postprocess_params["score_thresh"] = args.det_east_score_thresh
postprocess_params["cover_thresh"] = args.det_east_cover_thresh
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}
}
postprocess_params['name'] = 'SASTPostProcess'
postprocess_params["score_thresh"] = args.det_sast_score_thresh
postprocess_params["nms_thresh"] = args.det_sast_nms_thresh
self.det_sast_polygon = args.det_sast_polygon
if self.det_sast_polygon:
postprocess_params["sample_pts_num"] = 6
postprocess_params["expand_scale"] = 1.2
postprocess_params["shrink_ratio_of_width"] = 0.2
else:
postprocess_params["sample_pts_num"] = 2
postprocess_params["expand_scale"] = 1.0
postprocess_params["shrink_ratio_of_width"] = 0.3
else:
logger.info("unknown det_algorithm:{}".format(self.det_algorithm))
sys.exit(0)
self.preprocess_op = create_operators(pre_process_list)
self.postprocess_op = build_post_process(postprocess_params)
self.predictor, self.input_tensor, self.output_tensors = utility.create_predictor(
args, 'det', logger) # paddle.jit.load(args.det_model_dir)
def main(config, device, logger, vdl_writer):
global_config = config['Global']
# build post process
post_process_class = build_post_process(config['PostProcess'],
global_config)
# build model
if hasattr(post_process_class, 'character'):
config['Architecture']["Head"]['out_channels'] = len(
getattr(post_process_class, 'character'))
model = build_model(config['Architecture'])
init_model(config, model, logger)
# create data ops
transforms = []
use_padding = False
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
if op_name == 'KeepKeys':
op[op_name]['keep_keys'] = ['image']
if op_name == "ResizeTableImage":
use_padding = True
padding_max_len = op['ResizeTableImage']['max_len']
transforms.append(op)
global_config['infer_mode'] = True
ops = create_operators(transforms, global_config)
model.eval()
for file in get_image_file_list(config['Global']['infer_img']):
logger.info("infer_img: {}".format(file))
with open(file, 'rb') as f:
img = f.read()
data = {'image': img}
batch = transform(data, ops)
images = np.expand_dims(batch[0], axis=0)
images = paddle.to_tensor(images)
preds = model(images)
post_result = post_process_class(preds)
res_html_code = post_result['res_html_code']
res_loc = post_result['res_loc']
img = cv2.imread(file)
imgh, imgw = img.shape[0:2]
res_loc_final = []
for rno in range(len(res_loc[0])):
x0, y0, x1, y1 = res_loc[0][rno]
left = max(int(imgw * x0), 0)
top = max(int(imgh * y0), 0)
right = min(int(imgw * x1), imgw - 1)
bottom = min(int(imgh * y1), imgh - 1)
cv2.rectangle(img, (left, top), (right, bottom), (0, 0, 255), 2)
res_loc_final.append([left, top, right, bottom])
res_loc_str = json.dumps(res_loc_final)
logger.info("result: {}, {}".format(res_html_code, res_loc_final))
logger.info("success!")
def main():
global_config = config['Global']
# build model
model = build_model(config['Architecture'])
load_model(config, model)
# create data ops
transforms = []
for op in config['Eval']['dataset']['transforms']:
transforms.append(op)
data_dir = config['Eval']['dataset']['data_dir']
ops = create_operators(transforms, global_config)
save_res_path = config['Global']['save_res_path']
class_path = config['Global']['class_path']
idx_to_cls = read_class_list(class_path)
if not os.path.exists(os.path.dirname(save_res_path)):
os.makedirs(os.path.dirname(save_res_path))
model.eval()
warmup_times = 0
count_t = []
with open(save_res_path, "wb") as fout:
with open(config['Global']['infer_img'], "rb") as f:
lines = f.readlines()
for index, data_line in enumerate(lines):
if index == 10:
warmup_t = time.time()
data_line = data_line.decode('utf-8')
substr = data_line.strip("\n").split("\t")
img_path, label = data_dir + "/" + substr[0], substr[1]
data = {'img_path': img_path, 'label': label}
with open(data['img_path'], 'rb') as f:
img = f.read()
data['image'] = img
st = time.time()
batch = transform(data, ops)
batch_pred = [0] * len(batch)
for i in range(len(batch)):
batch_pred[i] = paddle.to_tensor(
np.expand_dims(batch[i], axis=0))
st = time.time()
node, edge = model(batch_pred)
node = F.softmax(node, -1)
count_t.append(time.time() - st)
draw_kie_result(batch, node, idx_to_cls, index)
logger.info("success!")
logger.info("It took {} s for predict {} images.".format(
np.sum(count_t), len(count_t)))
ips = len(count_t[warmup_times:]) / np.sum(count_t[warmup_times:])
logger.info("The ips is {} images/s".format(ips))
def main():
global_config = config['Global']
# build model
model = build_model(config['Architecture'])
init_model(config, model, logger)
# build post process
post_process_class = build_post_process(config['PostProcess'],
global_config)
# create data ops
transforms = []
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
elif op_name == 'KeepKeys':
op[op_name]['keep_keys'] = ['image', 'shape']
transforms.append(op)
ops = create_operators(transforms, global_config)
save_res_path = config['Global']['save_res_path']
if not os.path.exists(os.path.dirname(save_res_path)):
os.makedirs(os.path.dirname(save_res_path))
model.eval()
with open(save_res_path, "wb") as fout:
for file in get_image_file_list(config['Global']['infer_img']):
logger.info("infer_img: {}".format(file))
with open(file, 'rb') as f:
img = f.read()
data = {'image': img}
batch = transform(data, ops)
images = np.expand_dims(batch[0], axis=0)
shape_list = np.expand_dims(batch[1], axis=0)
images = paddle.to_tensor(images)
preds = model(images)
post_result = post_process_class(preds, shape_list)
points, strs = post_result['points'], post_result['texts']
# write resule
dt_boxes_json = []
for poly, str in zip(points, strs):
tmp_json = {"transcription": str}
tmp_json['points'] = poly.tolist()
dt_boxes_json.append(tmp_json)
otstr = file + "\t" + json.dumps(dt_boxes_json) + "\n"
fout.write(otstr.encode())
src_img = cv2.imread(file)
draw_e2e_res(points, strs, config, src_img, file)
logger.info("success!")
def main():
global_config = config['Global']
# build post process
post_process_class = build_post_process(config['PostProcess'],
global_config)
# build model
if hasattr(post_process_class, 'character'):
config['Architecture']["Head"]['out_channels'] = len(
getattr(post_process_class, 'character'))
model = build_model(config['Architecture'])
init_model(config, model, logger)
# create data ops
transforms = []
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
elif op_name in ['RecResizeImg']:
op[op_name]['infer_mode'] = True
elif op_name == 'KeepKeys':
op[op_name]['keep_keys'] = ['image']
transforms.append(op)
global_config['infer_mode'] = True
ops = create_operators(transforms, global_config)
model.eval()
for file in get_image_file_list(config['Global']['infer_img']):
logger.info("infer_img: {}".format(file))
with open(file, 'rb') as f:
img = f.read()
data = {'image': img}
batch = transform(data, ops)
images = np.expand_dims(batch[0], axis=0)
images = paddle.to_tensor(images)
preds = model(images)
post_result = post_process_class(preds)
for rec_reuslt in post_result:
logger.info('\t result: {}'.format(rec_reuslt))
logger.info("success!")
def __init__(self, args):
self.args = args
self.e2e_algorithm = args.e2e_algorithm
pre_process_list = [{
'E2EResizeForTest': {}
}, {
'NormalizeImage': {
'std': [0.229, 0.224, 0.225],
'mean': [0.485, 0.456, 0.406],
'scale': '1./255.',
'order': 'hwc'
}
}, {
'ToCHWImage': None
}, {
'KeepKeys': {
'keep_keys': ['image', 'shape']
}
}]
postprocess_params = {}
if self.e2e_algorithm == "PGNet":
pre_process_list[0] = {
'E2EResizeForTest': {
'max_side_len': args.e2e_limit_side_len,
'valid_set': 'totaltext'
}
}
postprocess_params['name'] = 'PGPostProcess'
postprocess_params["score_thresh"] = args.e2e_pgnet_score_thresh
postprocess_params["character_dict_path"] = args.e2e_char_dict_path
postprocess_params["valid_set"] = args.e2e_pgnet_valid_set
postprocess_params["mode"] = args.e2e_pgnet_mode
self.e2e_pgnet_polygon = args.e2e_pgnet_polygon
else:
logger.info("unknown e2e_algorithm:{}".format(self.e2e_algorithm))
sys.exit(0)
self.preprocess_op = create_operators(pre_process_list)
self.postprocess_op = build_post_process(postprocess_params)
self.predictor, self.input_tensor, self.output_tensors = utility.create_predictor(
args, 'e2e', logger) # paddle.jit.load(args.det_model_dir)
def __init__(self, args):
self.args = args
self.det_algorithm = args.det_algorithm
pre_process_list = [{
'DetResizeForTest': {
'limit_side_len': args.det_limit_side_len,
'limit_type': args.det_limit_type,
}
}, {
'NormalizeImage': {
'std': [0.229, 0.224, 0.225],
'mean': [0.485, 0.456, 0.406],
'scale': '1./255.',
'order': 'hwc'
}
}, {
'ToCHWImage': None
}, {
'KeepKeys': {
'keep_keys': ['image', 'shape']
}
}]
postprocess_params = {}
if self.det_algorithm == "DB":
postprocess_params['name'] = 'DBPostProcess'
postprocess_params["thresh"] = args.det_db_thresh
postprocess_params["box_thresh"] = args.det_db_box_thresh
postprocess_params["max_candidates"] = 1000
postprocess_params["unclip_ratio"] = args.det_db_unclip_ratio
postprocess_params["use_dilation"] = args.use_dilation
postprocess_params["score_mode"] = args.det_db_score_mode
elif self.det_algorithm == "EAST":
postprocess_params['name'] = 'EASTPostProcess'
postprocess_params["score_thresh"] = args.det_east_score_thresh
postprocess_params["cover_thresh"] = args.det_east_cover_thresh
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
}
}
postprocess_params['name'] = 'SASTPostProcess'
postprocess_params["score_thresh"] = args.det_sast_score_thresh
postprocess_params["nms_thresh"] = args.det_sast_nms_thresh
self.det_sast_polygon = args.det_sast_polygon
if self.det_sast_polygon:
postprocess_params["sample_pts_num"] = 6
postprocess_params["expand_scale"] = 1.2
postprocess_params["shrink_ratio_of_width"] = 0.2
else:
postprocess_params["sample_pts_num"] = 2
postprocess_params["expand_scale"] = 1.0
postprocess_params["shrink_ratio_of_width"] = 0.3
else:
logger.info("unknown det_algorithm:{}".format(self.det_algorithm))
sys.exit(0)
self.preprocess_op = create_operators(pre_process_list)
self.postprocess_op = build_post_process(postprocess_params)
self.predictor, self.input_tensor, self.output_tensors, self.config = utility.create_predictor(
args, 'det', logger)
if args.benchmark:
import auto_log
pid = os.getpid()
self.autolog = auto_log.AutoLogger(model_name="det",
model_precision=args.precision,
batch_size=1,
data_shape="dynamic",
save_path=args.save_log_path,
inference_config=self.config,
pids=pid,
process_name=None,
gpu_ids=0,
time_keys=[
'preprocess_time',
'inference_time',
'postprocess_time'
],
warmup=10)
def main():
global_config = config['Global']
# build post process
post_process_class = build_post_process(config['PostProcess'],
global_config)
# build model
if hasattr(post_process_class, 'character'):
config['Architecture']["Head"]['out_channels'] = len(
getattr(post_process_class, 'character'))
model = build_model(config['Architecture'])
init_model(config, model, logger)
# create data ops
transforms = []
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
elif op_name in ['RecResizeImg']:
op[op_name]['infer_mode'] = True
elif op_name == 'KeepKeys':
if config['Architecture']['algorithm'] == "SRN":
op[op_name]['keep_keys'] = [
'image', 'encoder_word_pos', 'gsrm_word_pos',
'gsrm_slf_attn_bias1', 'gsrm_slf_attn_bias2'
]
else:
op[op_name]['keep_keys'] = ['image']
transforms.append(op)
global_config['infer_mode'] = True
ops = create_operators(transforms, global_config)
save_res_path = config['Global'].get('save_res_path',
"./output/rec/predicts_rec.txt")
if not os.path.exists(os.path.dirname(save_res_path)):
os.makedirs(os.path.dirname(save_res_path))
model.eval()
with open(save_res_path, "w") as fout:
for file in get_image_file_list(config['Global']['infer_img']):
logger.info("infer_img: {}".format(file))
with open(file, 'rb') as f:
img = f.read()
data = {'image': img}
batch = transform(data, ops)
if config['Architecture']['algorithm'] == "SRN":
encoder_word_pos_list = np.expand_dims(batch[1], axis=0)
gsrm_word_pos_list = np.expand_dims(batch[2], axis=0)
gsrm_slf_attn_bias1_list = np.expand_dims(batch[3], axis=0)
gsrm_slf_attn_bias2_list = np.expand_dims(batch[4], axis=0)
others = [
paddle.to_tensor(encoder_word_pos_list),
paddle.to_tensor(gsrm_word_pos_list),
paddle.to_tensor(gsrm_slf_attn_bias1_list),
paddle.to_tensor(gsrm_slf_attn_bias2_list)
]
images = np.expand_dims(batch[0], axis=0)
images = paddle.to_tensor(images)
if config['Architecture']['algorithm'] == "SRN":
preds = model(images, others)
else:
preds = model(images)
post_result = post_process_class(preds)
for rec_result in post_result:
logger.info('\t result: {}'.format(rec_result))
if len(rec_result) >= 2:
fout.write(file + "\t" + rec_result[0] + "\t" +
str(rec_result[1]) + "\n")
logger.info("success!")
def main():
global_config = config['Global']
# build post process
post_process_class = build_post_process(config['PostProcess'],
global_config)
# build model
if hasattr(post_process_class, 'character'):
char_num = len(getattr(post_process_class, 'character'))
if config['Architecture']["algorithm"] in [
"Distillation",
]: # distillation model
for key in config['Architecture']["Models"]:
config['Architecture']["Models"][key]["Head"][
'out_channels'] = char_num
else: # base rec model
config['Architecture']["Head"]['out_channels'] = char_num
model = build_model(config['Architecture'])
init_model(config, model)
# create data ops
transforms = []
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
elif op_name in ['RecResizeImg']:
op[op_name]['infer_mode'] = True
elif op_name == 'KeepKeys':
if config['Architecture']['algorithm'] == "SRN":
op[op_name]['keep_keys'] = [
'image', 'encoder_word_pos', 'gsrm_word_pos',
'gsrm_slf_attn_bias1', 'gsrm_slf_attn_bias2'
]
else:
op[op_name]['keep_keys'] = ['image']
transforms.append(op)
global_config['infer_mode'] = True
ops = create_operators(transforms, global_config)
save_res_path = config['Global'].get('save_res_path',
"./output/rec/predicts_rec.txt")
if not os.path.exists(os.path.dirname(save_res_path)):
os.makedirs(os.path.dirname(save_res_path))
model.eval()
with open(save_res_path, "w") as fout:
for file in get_image_file_list(config['Global']['infer_img']):
logger.info("infer_img: {}".format(file))
with open(file, 'rb') as f:
img = f.read()
data = {'image': img}
batch = transform(data, ops)
if config['Architecture']['algorithm'] == "SRN":
encoder_word_pos_list = np.expand_dims(batch[1], axis=0)
gsrm_word_pos_list = np.expand_dims(batch[2], axis=0)
gsrm_slf_attn_bias1_list = np.expand_dims(batch[3], axis=0)
gsrm_slf_attn_bias2_list = np.expand_dims(batch[4], axis=0)
others = [
paddle.to_tensor(encoder_word_pos_list),
paddle.to_tensor(gsrm_word_pos_list),
paddle.to_tensor(gsrm_slf_attn_bias1_list),
paddle.to_tensor(gsrm_slf_attn_bias2_list)
]
images = np.expand_dims(batch[0], axis=0)
images = paddle.to_tensor(images)
if config['Architecture']['algorithm'] == "SRN":
preds = model(images, others)
else:
preds = model(images)
post_result = post_process_class(preds)
info = None
if isinstance(post_result, dict):
rec_info = dict()
for key in post_result:
if len(post_result[key][0]) >= 2:
rec_info[key] = {
"label": post_result[key][0][0],
"score": float(post_result[key][0][1]),
}
info = json.dumps(rec_info)
else:
if len(post_result[0]) >= 2:
info = post_result[0][0] + "\t" + str(post_result[0][1])
if info is not None:
logger.info("\t result: {}".format(info))
fout.write(file + "\t" + info)
logger.info("success!")
def main():
global_config = config['Global']
# build model
model = build_model(config['Architecture'])
load_model(config, model)
# build post process
post_process_class = build_post_process(config['PostProcess'])
# create data ops
transforms = []
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
elif op_name == 'KeepKeys':
op[op_name]['keep_keys'] = ['image', 'shape']
transforms.append(op)
ops = create_operators(transforms, global_config)
save_res_path = config['Global']['save_res_path']
if not os.path.exists(os.path.dirname(save_res_path)):
os.makedirs(os.path.dirname(save_res_path))
model.eval()
with open(save_res_path, "wb") as fout:
for file in get_image_file_list(config['Global']['infer_img']):
logger.info("infer_img: {}".format(file))
with open(file, 'rb') as f:
img = f.read()
data = {'image': img}
batch = transform(data, ops)
images = np.expand_dims(batch[0], axis=0)
shape_list = np.expand_dims(batch[1], axis=0)
images = paddle.to_tensor(images)
preds = model(images)
post_result = post_process_class(preds, shape_list)
src_img = cv2.imread(file)
dt_boxes_json = []
# parser boxes if post_result is dict
if isinstance(post_result, dict):
det_box_json = {}
for k in post_result.keys():
boxes = post_result[k][0]['points']
dt_boxes_list = []
for box in boxes:
tmp_json = {"transcription": ""}
tmp_json['points'] = box.tolist()
dt_boxes_list.append(tmp_json)
det_box_json[k] = dt_boxes_list
save_det_path = os.path.dirname(
config['Global']
['save_res_path']) + "/det_results_{}/".format(k)
draw_det_res(boxes, config, src_img, file, save_det_path)
else:
boxes = post_result[0]['points']
dt_boxes_json = []
# write result
for box in boxes:
tmp_json = {"transcription": ""}
tmp_json['points'] = box.tolist()
dt_boxes_json.append(tmp_json)
save_det_path = os.path.dirname(
config['Global']['save_res_path']) + "/det_results/"
draw_det_res(boxes, config, src_img, file, save_det_path)
otstr = file + "\t" + json.dumps(dt_boxes_json) + "\n"
fout.write(otstr.encode())
logger.info("success!")
