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

modified infer single

This commit is contained in:
tink2123 2020-06-02 19:03:27 +08:00
parent dab609b18e
commit 24757ba6bc
17 changed files with 43 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
configs/rec/rec_benchmark_reader.yml
View File

@ -10,4 +10,3 @@ EvalReader:
TestReader:
reader_function: ppocr.data.rec.dataset_traversal,LMDBReader
lmdb_sets_dir: ./train_data/data_lmdb_release/evaluation/
infer_img: ./infer_img

2
configs/rec/rec_chinese_lite_train.yml
View File

@ -18,6 +18,8 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

1
configs/rec/rec_chinese_reader.yml
View File

@ -11,4 +11,3 @@ EvalReader:
TestReader:
reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
infer_img: ./infer_img

1
configs/rec/rec_icdar15_reader.yml
View File

@ -11,4 +11,3 @@ EvalReader:
TestReader:
reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
infer_img: ./infer_img

2
configs/rec/rec_icdar15_train.yml
View File

@ -17,6 +17,8 @@ Global:
pretrain_weights: ./pretrain_models/rec_mv3_none_bilstm_ctc/best_accuracy
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

4
configs/rec/rec_mv3_none_bilstm_ctc.yml
View File

@ -1,6 +1,6 @@
Global:
algorithm: CRNN
use_gpu: true
use_gpu: false
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
@ -14,7 +14,7 @@ Global:
character_type: en
loss_type: ctc
reader_yml: ./configs/rec/rec_benchmark_reader.yml
pretrain_weights:
pretrain_weights: ./output/rec_CRNN/rec_mv3_none_bilstm_ctc/best_accuracy
checkpoints:
save_inference_dir:

1
configs/rec/rec_mv3_none_none_ctc.yml
View File

@ -17,6 +17,7 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

4
configs/rec/rec_mv3_tps_bilstm_attn.yml
View File

@ -17,7 +17,9 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

1
configs/rec/rec_mv3_tps_bilstm_ctc.yml
View File

@ -17,6 +17,7 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:

4
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
View File

@ -17,7 +17,9 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

1
configs/rec/rec_r34_vd_none_none_ctc.yml
View File

@ -17,6 +17,7 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

2
configs/rec/rec_r34_vd_tps_bilstm_attn.yml
View File

@ -17,6 +17,8 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

2
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
View File

@ -17,6 +17,8 @@ Global:
pretrain_weights:
checkpoints:
save_inference_dir:
infer_img:
Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel

2
doc/recognition.md
View File

@ -184,7 +184,7 @@ python3 tools/eval.py -c configs/rec/rec_chinese_lite_train.yml -o Global.checkp
```
# 预测英文结果
python3 tools/infer_rec.py -c configs/rec/rec_chinese_lite_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy TestReader.infer_img=doc/imgs_words/en/word_1.jpg
python3 tools/infer_rec.py -c configs/rec/rec_chinese_lite_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
```
预测图片：

30
ppocr/data/rec/dataset_traversal.py
View File

@ -43,11 +43,10 @@ class LMDBReader(object):
self.mode = params['mode']
if params['mode'] == 'train':
self.batch_size = params['train_batch_size_per_card']
elif params['mode'] == "eval":
else:
self.batch_size = params['test_batch_size_per_card']
elif params['mode'] == "test":
self.batch_size = 1
self.infer_img = params["infer_img"]
self.infer_img = params['infer_img']
def load_hierarchical_lmdb_dataset(self):
lmdb_sets = {}
dataset_idx = 0
@ -100,11 +99,11 @@ class LMDBReader(object):
process_id = 0
def sample_iter_reader():
if self.mode == 'test':
if self.infer_img is not None:
image_file_list = get_image_file_list(self.infer_img)
for single_img in image_file_list:
img = cv2.imread(single_img)
if img.shape[-1]==1 or len(list(img.shape))==2:
if img.shape[-1] == 1 or len(list(img.shape)) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
norm_img = process_image(img, self.image_shape)
yield norm_img
@ -136,6 +135,7 @@ class LMDBReader(object):
if finish_read_num == len(lmdb_sets):
break
self.close_lmdb_dataset(lmdb_sets)
def batch_iter_reader():
batch_outs = []
for outs in sample_iter_reader():
@ -146,7 +146,7 @@ class LMDBReader(object):
if len(batch_outs) != 0:
yield batch_outs
if self.mode != 'test':
if self.infer_img is None:
return batch_iter_reader
return sample_iter_reader
@ -165,24 +165,22 @@ class SimpleReader(object):
self.loss_type = params['loss_type']
self.max_text_length = params['max_text_length']
self.mode = params['mode']
self.infer_img = params['infer_img']
if params['mode'] == 'train':
self.batch_size = params['train_batch_size_per_card']
elif params['mode'] == 'eval':
self.batch_size = params['test_batch_size_per_card']
else:
self.batch_size = 1
self.infer_img = params['infer_img']
self.batch_size = params['test_batch_size_per_card']
def __call__(self, process_id):
if self.mode != 'train':
process_id = 0
def sample_iter_reader():
if self.mode == 'test':
if self.infer_img is not None:
image_file_list = get_image_file_list(self.infer_img)
for single_img in image_file_list:
img = cv2.imread(single_img)
if img.shape[-1]==1 or len(list(img.shape))==2:
if img.shape[-1] == 1 or len(list(img.shape)) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
norm_img = process_image(img, self.image_shape)
yield norm_img
@ -192,7 +190,7 @@ class SimpleReader(object):
img_num = len(label_infor_list)
img_id_list = list(range(img_num))
random.shuffle(img_id_list)
if sys.platform=="win32":
if sys.platform == "win32":
print("multiprocess is not fully compatible with Windows."
"num_workers will be 1.")
self.num_workers = 1
@ -204,7 +202,7 @@ class SimpleReader(object):
if img is None:
logger.info("{} does not exist!".format(img_path))
continue
if img.shape[-1]==1 or len(list(img.shape))==2:
if img.shape[-1] == 1 or len(list(img.shape)) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
label = substr[1]
@ -225,6 +223,6 @@ class SimpleReader(object):
if len(batch_outs) != 0:
yield batch_outs
if self.mode != 'test':
if self.infer_img is None:
return batch_iter_reader
return sample_iter_reader

8
tools/eval_utils/eval_rec_utils.py
View File

@ -48,7 +48,7 @@ def eval_rec_run(exe, config, eval_info_dict, mode):
total_sample_num = 0
total_acc_num = 0
total_batch_num = 0
if mode == "test":
if mode == "eval":
is_remove_duplicate = False
else:
is_remove_duplicate = True
@ -91,11 +91,11 @@ def test_rec_benchmark(exe, config, eval_info_dict):
total_correct_number = 0
eval_data_acc_info = {}
for eval_data in eval_data_list:
config['EvalReader']['lmdb_sets_dir'] = \
config['TestReader']['lmdb_sets_dir'] = \
eval_data_dir + "/" + eval_data
eval_reader = reader_main(config=config, mode="eval")
eval_reader = reader_main(config=config, mode="test")
eval_info_dict['reader'] = eval_reader
metrics = eval_rec_run(exe, config, eval_info_dict, "eval")
metrics = eval_rec_run(exe, config, eval_info_dict, "test")
total_evaluation_data_number += metrics['total_sample_num']
total_correct_number += metrics['total_acc_num']
eval_data_acc_info[eval_data] = metrics

9
tools/infer_rec.py
View File

@ -21,6 +21,7 @@ import time
import multiprocessing
import numpy as np
def set_paddle_flags(**kwargs):
for key, value in kwargs.items():
if os.environ.get(key, None) is None:
@ -78,13 +79,13 @@ def main():
init_model(config, eval_prog, exe)
blobs = reader_main(config, 'test')()
infer_img = config['TestReader']['infer_img']
infer_img = config['Global']['infer_img']
infer_list = get_image_file_list(infer_img)
max_img_num = len(infer_list)
if len(infer_list) == 0:
logger.info("Can not find img in infer_img dir.")
for i in range(max_img_num):
print("infer_img:",infer_list[i])
print("infer_img:", infer_list[i])
img = next(blobs)
predict = exe.run(program=eval_prog,
feed={"image": img},
@ -105,8 +106,8 @@ def main():
preds_text = preds_text.reshape(-1)
preds_text = char_ops.decode(preds_text)
print("\t index:",preds)
print("\t word :",preds_text)
print("\t index:", preds)
print("\t word :", preds_text)
# save for inference model
target_var = []