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

Merge pull request #2 from tink2123/develop 

del tmp
This commit is contained in:
Double_V 2020-05-10 20:48:38 +08:00 committed by GitHub
parent 476c51a73c 1a84472df9
commit e3388a2440
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 0 additions and 977 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tools/infer/det_program.txt
View File

@ -1 +0,0 @@
<paddle.fluid.core_avx.ProgramDesc object at 0x10d15fab0>

134
tools/tmp/eval_det.py
View File

@ -1,134 +0,0 @@
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import sys
import time
import numpy as np
from copy import deepcopy
import json
# from paddle.fluid.contrib.model_stat import summary
def set_paddle_flags(**kwargs):
for key, value in kwargs.items():
if os.environ.get(key, None) is None:
os.environ[key] = str(value)
# NOTE(paddle-dev): All of these flags should be
# set before `import paddle`. Otherwise, it would
# not take any effect.
set_paddle_flags(
FLAGS_eager_delete_tensor_gb=0, # enable GC to save memory
)
from paddle import fluid
from ppocr.utils.utility import create_module
from ppocr.utils.utility import load_config, merge_config
import ppocr.data.det.reader_main as reader
from ppocr.utils.utility import ArgsParser
from ppocr.utils.check import check_gpu
from ppocr.utils.checkpoint import load_pretrain, load_checkpoint, save, save_model
from ppocr.utils.utility import initial_logger
logger = initial_logger()
from ppocr.utils.eval_utils import eval_det_run
def draw_det_res(dt_boxes, config, img_name, ino):
if len(dt_boxes) > 0:
img_set_path = config['TestReader']['img_set_dir']
img_path = img_set_path + img_name
import cv2
src_im = cv2.imread(img_path)
for box in dt_boxes:
box = box.astype(np.int32).reshape((-1, 1, 2))
cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
cv2.imwrite("tmp%d.jpg" % ino, src_im)
def main():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
print(config)
# check if set use_gpu=True in paddlepaddle cpu version
use_gpu = config['Global']['use_gpu']
check_gpu(use_gpu)
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
det_model = create_module(config['Architecture']['function'])(params=config)
startup_prog = fluid.Program()
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
eval_loader, eval_outputs = det_model(mode="test")
eval_fetch_list = [v.name for v in eval_outputs]
eval_prog = eval_prog.clone(for_test=True)
exe.run(startup_prog)
pretrain_weights = config['Global']['pretrain_weights']
if pretrain_weights is not None:
load_pretrain(exe, eval_prog, pretrain_weights)
# fluid.load(eval_prog, pretrain_weights)
# def if_exist(var):
# return os.path.exists(os.path.join(pretrain_weights, var.name))
# fluid.io.load_vars(exe, pretrain_weights, predicate=if_exist, main_program=eval_prog)
else:
logger.info("Not find pretrain_weights:%s" % pretrain_weights)
sys.exit(0)
# fluid.io.save_inference_model("./output/", feeded_var_names=['image'],
# target_vars=eval_outputs, executor=exe, main_program=eval_prog,
# model_filename="model", params_filename="params")
# sys.exit(-1)
metrics = eval_det_run(exe, eval_prog, eval_fetch_list, config, "test")
logger.info("metrics:{}".format(metrics))
logger.info("success!")
def test_reader():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
print(config)
tmp_reader = reader.test_reader(config=config)
count = 0
print_count = 0
import time
starttime = time.time()
for data in tmp_reader():
count += len(data)
print_count += 1
if print_count % 10 == 0:
batch_time = (time.time() - starttime) / print_count
print("reader:", count, len(data), batch_time)
print("finish reader:", count)
print("success")
if __name__ == '__main__':
parser = ArgsParser()
FLAGS = parser.parse_args()
main()
# test_reader()

160
tools/tmp/infer_det.py
View File

@ -1,160 +0,0 @@
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import sys
import time
import numpy as np
from copy import deepcopy
import json
# from paddle.fluid.contrib.model_stat import summary
def set_paddle_flags(**kwargs):
for key, value in kwargs.items():
if os.environ.get(key, None) is None:
os.environ[key] = str(value)
# NOTE(paddle-dev): All of these flags should be
# set before `import paddle`. Otherwise, it would
# not take any effect.
set_paddle_flags(
FLAGS_eager_delete_tensor_gb=0, # enable GC to save memory
)
from paddle import fluid
from ppocr.utils.utility import create_module
from ppocr.utils.utility import load_config, merge_config
import ppocr.data.det.reader_main as reader
from ppocr.utils.utility import ArgsParser
from ppocr.utils.check import check_gpu
from ppocr.utils.checkpoint import load_pretrain, load_checkpoint, save, save_model
from ppocr.utils.utility import initial_logger
logger = initial_logger()
from ppocr.utils.eval_utils import eval_det_run
def draw_det_res(dt_boxes, config, img_name, ino):
if len(dt_boxes) > 0:
img_set_path = config['TestReader']['img_set_dir']
img_path = img_set_path + img_name
import cv2
src_im = cv2.imread(img_path)
for box in dt_boxes:
box = box.astype(np.int32).reshape((-1, 1, 2))
cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
cv2.imwrite("tmp%d.jpg" % ino, src_im)
def main():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
print(config)
# check if set use_gpu=True in paddlepaddle cpu version
use_gpu = config['Global']['use_gpu']
check_gpu(use_gpu)
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
det_model = create_module(config['Architecture']['function'])(params=config)
startup_prog = fluid.Program()
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
eval_outputs = det_model(mode="test")
eval_fetch_list = [v.name for v in eval_outputs]
eval_prog = eval_prog.clone(for_test=True)
exe.run(startup_prog)
pretrain_weights = config['Global']['pretrain_weights']
if pretrain_weights is not None:
fluid.load(eval_prog, pretrain_weights)
else:
logger.info("Not find pretrain_weights:%s" % pretrain_weights)
sys.exit(0)
save_res_path = config['Global']['save_res_path']
with open(save_res_path, "wb") as fout:
test_reader = reader.test_reader(config=config)
tackling_num = 0
for data in test_reader():
img_num = len(data)
tackling_num = tackling_num + img_num
logger.info("tackling_num:%d", tackling_num)
img_list = []
ratio_list = []
img_name_list = []
for ino in range(img_num):
img_list.append(data[ino][0])
ratio_list.append(data[ino][1])
img_name_list.append(data[ino][2])
img_list = np.concatenate(img_list, axis=0)
outs = exe.run(eval_prog,\
feed={'image': img_list},\
fetch_list=eval_fetch_list)
global_params = config['Global']
postprocess_params = deepcopy(config["PostProcess"])
postprocess_params.update(global_params)
postprocess = create_module(postprocess_params['function'])\
(params=postprocess_params)
dt_boxes_list = postprocess(outs, ratio_list)
for ino in range(img_num):
dt_boxes = dt_boxes_list[ino]
img_name = img_name_list[ino]
dt_boxes_json = []
for box in dt_boxes:
tmp_json = {"transcription": ""}
tmp_json['points'] = box.tolist()
dt_boxes_json.append(tmp_json)
otstr = img_name + "\t" + json.dumps(dt_boxes_json) + "\n"
fout.write(otstr.encode())
#draw_det_res(dt_boxes, config, img_name, ino)
logger.info("success!")
def test_reader():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
print(config)
tmp_reader = reader.test_reader(config=config)
count = 0
print_count = 0
import time
starttime = time.time()
for data in tmp_reader():
count += len(data)
print_count += 1
if print_count % 10 == 0:
batch_time = (time.time() - starttime) / print_count
print("reader:", count, len(data), batch_time)
print("finish reader:", count)
print("success")
if __name__ == '__main__':
parser = ArgsParser()
FLAGS = parser.parse_args()
main()
# test_reader()

116
tools/tmp/infer_rec.py
View File

@ -1,116 +0,0 @@
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
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:
os.environ[key] = str(value)
# NOTE(paddle-dev): All of these flags should be
# set before `import paddle`. Otherwise, it would
# not take any effect.
set_paddle_flags(
FLAGS_eager_delete_tensor_gb=0, # enable GC to save memory
)
from paddle import fluid
from ppocr.utils.utility import load_config, merge_config
from ppocr.data.rec.reader_main import test_reader
from ppocr.utils.utility import ArgsParser
from ppocr.utils.character import CharacterOps, cal_predicts_accuracy
from ppocr.utils.check import check_gpu
from ppocr.utils.utility import create_module
from ppocr.utils.utility import initial_logger
logger = initial_logger()
def main():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
char_ops = CharacterOps(config['Global'])
config['Global']['char_num'] = char_ops.get_char_num()
# check if set use_gpu=True in paddlepaddle cpu version
use_gpu = config['Global']['use_gpu']
check_gpu(use_gpu)
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
rec_model = create_module(config['Architecture']['function'])(params=config)
startup_prog = fluid.Program()
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
eval_outputs = rec_model(mode="test")
eval_fetch_list = [v.name for v in eval_outputs]
eval_prog = eval_prog.clone(for_test=True)
exe.run(startup_prog)
pretrain_weights = config['Global']['pretrain_weights']
if pretrain_weights is not None:
fluid.load(eval_prog, pretrain_weights)
test_img_path = config['test_img_path']
image_shape = config['Global']['image_shape']
blobs = test_reader(image_shape, test_img_path)
predict = exe.run(program=eval_prog,
feed={"image": blobs},
fetch_list=eval_fetch_list,
return_numpy=False)
preds = np.array(predict[0])
if preds.shape[1] == 1:
preds = preds.reshape(-1)
preds_lod = predict[0].lod()[0]
preds_text = char_ops.decode(preds)
else:
end_pos = np.where(preds[0, :] == 1)[0]
if len(end_pos) <= 1:
preds_text = preds[0, 1:]
else:
preds_text = preds[0, 1:end_pos[1]]
preds_text = preds_text.reshape(-1)
preds_text = char_ops.decode(preds_text)
fluid.io.save_inference_model(
"./output/",
feeded_var_names=['image'],
target_vars=eval_outputs,
executor=exe,
main_program=eval_prog,
model_filename="model",
params_filename="params")
print(preds)
print(preds_text)
if __name__ == '__main__':
parser = ArgsParser()
FLAGS = parser.parse_args()
main()

128
tools/tmp/test_rec_benchmark.py
View File

@ -1,128 +0,0 @@
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
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:
os.environ[key] = str(value)
# NOTE(paddle-dev): All of these flags should be
# set before `import paddle`. Otherwise, it would
# not take any effect.
set_paddle_flags(
FLAGS_eager_delete_tensor_gb=0, # enable GC to save memory
)
from paddle import fluid
from ppocr.utils.utility import load_config, merge_config
import ppocr.data.rec.reader_main as reader
from ppocr.utils.utility import ArgsParser
from ppocr.utils.character import CharacterOps, cal_predicts_accuracy
from ppocr.utils.check import check_gpu
from ppocr.utils.utility import create_module
from ppocr.utils.eval_utils import eval_run
from ppocr.utils.utility import initial_logger
logger = initial_logger()
def main():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
char_ops = CharacterOps(config['Global'])
config['Global']['char_num'] = char_ops.get_char_num()
# check if set use_gpu=True in paddlepaddle cpu version
use_gpu = config['Global']['use_gpu']
check_gpu(use_gpu)
if use_gpu:
devices_num = fluid.core.get_cuda_device_count()
else:
devices_num = int(
os.environ.get('CPU_NUM', multiprocessing.cpu_count()))
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
rec_model = create_module(config['Architecture']['function'])(params=config)
startup_prog = fluid.Program()
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
eval_loader, eval_outputs = rec_model(mode="eval")
eval_fetch_list = [v.name for v in eval_outputs]
eval_prog = eval_prog.clone(for_test=True)
exe.run(startup_prog)
pretrain_weights = config['Global']['pretrain_weights']
if pretrain_weights is not None:
fluid.load(eval_prog, pretrain_weights)
eval_data_list = ['IIIT5k_3000', 'SVT', 'IC03_860', 'IC03_867',\
'IC13_857', 'IC13_1015', 'IC15_1811', 'IC15_2077', 'SVTP', 'CUTE80']
eval_data_dir = config['TestReader']['lmdb_sets_dir']
total_forward_time = 0
total_evaluation_data_number = 0
total_correct_number = 0
eval_data_acc_info = {}
for eval_data in eval_data_list:
config['TestReader']['lmdb_sets_dir'] = \
eval_data_dir + "/" + eval_data
eval_reader = reader.train_eval_reader(
config=config, char_ops=char_ops, mode="test")
eval_loader.set_sample_list_generator(eval_reader, places=place)
start_time = time.time()
outs = eval_run(exe, eval_prog, eval_loader, eval_fetch_list, char_ops,
"best", "test")
infer_time = time.time() - start_time
eval_acc, acc_num, sample_num = outs
total_forward_time += infer_time
total_evaluation_data_number += sample_num
total_correct_number += acc_num
eval_data_acc_info[eval_data] = outs
avg_forward_time = total_forward_time / total_evaluation_data_number
avg_acc = total_correct_number * 1.0 / total_evaluation_data_number
logger.info('-' * 50)
strs = ""
for eval_data in eval_data_list:
eval_acc, acc_num, sample_num = eval_data_acc_info[eval_data]
strs += "\n {}, accuracy:{:.6f}".format(eval_data, eval_acc)
strs += "\n average, accuracy:{:.6f}, time:{:.6f}".format(avg_acc,
avg_forward_time)
logger.info(strs)
logger.info('-' * 50)
if __name__ == '__main__':
parser = ArgsParser()
FLAGS = parser.parse_args()
main()

216
tools/tmp/train_det.py
View File

@ -1,216 +0,0 @@
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import sys
import time
import multiprocessing
import numpy as np
# from paddle.fluid.contrib.model_stat import summary
def set_paddle_flags(**kwargs):
for key, value in kwargs.items():
if os.environ.get(key, None) is None:
os.environ[key] = str(value)
# NOTE(paddle-dev): All of these flags should be
# set before `import paddle`. Otherwise, it would
# not take any effect.
set_paddle_flags(
FLAGS_eager_delete_tensor_gb=0, # enable GC to save memory
)
from paddle import fluid
from ppocr.utils.utility import create_module
from ppocr.utils.utility import load_config, merge_config
import ppocr.data.det.reader_main as reader
from ppocr.utils.utility import ArgsParser
from ppocr.utils.character import CharacterOps, cal_predicts_accuracy
from ppocr.utils.check import check_gpu
from ppocr.utils.stats import TrainingStats
from ppocr.utils.checkpoint import load_pretrain, load_checkpoint, save, save_model
from ppocr.utils.eval_utils import eval_run
from ppocr.utils.eval_utils import eval_det_run
from ppocr.utils.utility import initial_logger
logger = initial_logger()
from ppocr.utils.utility import create_multi_devices_program
def main():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
print(config)
alg = config['Global']['algorithm']
assert alg in ['EAST', 'DB']
# check if set use_gpu=True in paddlepaddle cpu version
use_gpu = config['Global']['use_gpu']
check_gpu(use_gpu)
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
det_model = create_module(config['Architecture']['function'])(params=config)
startup_prog = fluid.Program()
train_prog = fluid.Program()
with fluid.program_guard(train_prog, startup_prog):
with fluid.unique_name.guard():
train_loader, train_outputs = det_model(mode="train")
train_fetch_list = [v.name for v in train_outputs]
train_loss = train_outputs[0]
opt_params = config['Optimizer']
optimizer = create_module(opt_params['function'])(opt_params)
optimizer.minimize(train_loss)
global_lr = optimizer._global_learning_rate()
global_lr.persistable = True
train_fetch_list.append(global_lr.name)
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
eval_loader, eval_outputs = det_model(mode="eval")
eval_fetch_list = [v.name for v in eval_outputs]
eval_prog = eval_prog.clone(for_test=True)
train_reader = reader.train_reader(config=config)
train_loader.set_sample_list_generator(train_reader, places=place)
exe.run(startup_prog)
# compile program for multi-devices
train_compile_program = create_multi_devices_program(train_prog,
train_loss.name)
pretrain_weights = config['Global']['pretrain_weights']
if pretrain_weights is not None:
load_pretrain(exe, train_prog, pretrain_weights)
print("pretrain weights loaded!")
train_batch_id = 0
if alg == 'EAST':
train_log_keys = ['loss_total', 'loss_cls', 'loss_offset']
elif alg == 'DB':
train_log_keys = [
'loss_total', 'loss_shrink', 'loss_threshold', 'loss_binary'
]
log_smooth_window = config['Global']['log_smooth_window']
epoch_num = config['Global']['epoch_num']
print_step = config['Global']['print_step']
eval_step = config['Global']['eval_step']
save_epoch_step = config['Global']['save_epoch_step']
save_dir = config['Global']['save_dir']
train_stats = TrainingStats(log_smooth_window, train_log_keys)
best_eval_hmean = -1
best_batch_id = 0
best_epoch = 0
for epoch in range(epoch_num):
train_loader.start()
try:
while True:
t1 = time.time()
train_outs = exe.run(program=train_compile_program,
fetch_list=train_fetch_list,
return_numpy=False)
loss_total = np.mean(np.array(train_outs[0]))
if alg == 'EAST':
loss_cls = np.mean(np.array(train_outs[1]))
loss_offset = np.mean(np.array(train_outs[2]))
stats = {'loss_total':loss_total, 'loss_cls':loss_cls,\
'loss_offset':loss_offset}
elif alg == 'DB':
loss_shrink_maps = np.mean(np.array(train_outs[1]))
loss_threshold_maps = np.mean(np.array(train_outs[2]))
loss_binary_maps = np.mean(np.array(train_outs[3]))
stats = {'loss_total':loss_total, 'loss_shrink':loss_shrink_maps, \
'loss_threshold':loss_threshold_maps, 'loss_binary':loss_binary_maps}
lr = np.mean(np.array(train_outs[-1]))
t2 = time.time()
train_batch_elapse = t2 - t1
# stats = {'loss_total':loss_total, 'loss_cls':loss_cls,\
# 'loss_offset':loss_offset}
train_stats.update(stats)
if train_batch_id > 0 and train_batch_id % print_step == 0:
logs = train_stats.log()
strs = 'epoch: {}, iter: {}, lr: {:.6f}, {}, time: {:.3f}'.format(
epoch, train_batch_id, lr, logs, train_batch_elapse)
logger.info(strs)
if train_batch_id > 0 and\
train_batch_id % eval_step == 0:
metrics = eval_det_run(exe, eval_prog, eval_fetch_list,
config, "eval")
hmean = metrics['hmean']
if hmean >= best_eval_hmean:
best_eval_hmean = hmean
best_batch_id = train_batch_id
best_epoch = epoch
save_path = save_dir + "/best_accuracy"
save_model(train_prog, save_path)
strs = 'Test iter: {}, metrics:{}, best_hmean:{:.6f}, best_epoch:{}, best_batch_id:{}'.format(
train_batch_id, metrics, best_eval_hmean, best_epoch,
best_batch_id)
logger.info(strs)
train_batch_id += 1
except fluid.core.EOFException:
train_loader.reset()
if epoch > 0 and epoch % save_epoch_step == 0:
save_path = save_dir + "/iter_epoch_%d" % (epoch)
save_model(train_prog, save_path)
def test_reader():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
print(config)
tmp_reader = reader.train_reader(config=config)
count = 0
print_count = 0
import time
while True:
starttime = time.time()
count = 0
for data in tmp_reader():
count += 1
if print_count % 1 == 0:
batch_time = time.time() - starttime
starttime = time.time()
print("reader:", count, len(data), batch_time)
print("finish reader:", count)
print("success")
if __name__ == '__main__':
parser = ArgsParser()
parser.add_argument(
"-r",
"--resume_checkpoint",
default=None,
type=str,
help="Checkpoint path for resuming training.")
FLAGS = parser.parse_args()
main()
# test_reader()

222
tools/tmp/train_rec.py
View File

@ -1,222 +0,0 @@
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import sys
import time
import multiprocessing
import numpy as np
# from paddle.fluid.contrib.model_stat import summary
def set_paddle_flags(**kwargs):
for key, value in kwargs.items():
if os.environ.get(key, None) is None:
os.environ[key] = str(value)
# NOTE(paddle-dev): All of these flags should be
# set before `import paddle`. Otherwise, it would
# not take any effect.
set_paddle_flags(
FLAGS_eager_delete_tensor_gb=0, # enable GC to save memory
)
from paddle import fluid
from ppocr.utils.utility import create_module
from ppocr.utils.utility import load_config, merge_config
import ppocr.data.rec.reader_main as reader
from ppocr.utils.utility import ArgsParser
from ppocr.utils.character import CharacterOps, cal_predicts_accuracy
from ppocr.utils.check import check_gpu
from ppocr.utils.stats import TrainingStats
from ppocr.utils.checkpoint import load_pretrain, load_checkpoint, save, save_model
from ppocr.utils.eval_utils import eval_run
from ppocr.utils.utility import initial_logger
logger = initial_logger()
from ppocr.utils.utility import create_multi_devices_program
def main():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
char_ops = CharacterOps(config['Global'])
config['Global']['char_num'] = char_ops.get_char_num()
print(config)
# check if set use_gpu=True in paddlepaddle cpu version
use_gpu = config['Global']['use_gpu']
check_gpu(use_gpu)
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
rec_model = create_module(config['Architecture']['function'])(params=config)
startup_prog = fluid.Program()
train_prog = fluid.Program()
with fluid.program_guard(train_prog, startup_prog):
with fluid.unique_name.guard():
train_loader, train_outputs = rec_model(mode="train")
save_var = train_outputs[1]
if "gradient_clip" in config['Global']:
gradient_clip = config['Global']['gradient_clip']
clip = fluid.clip.GradientClipByGlobalNorm(gradient_clip)
fluid.clip.set_gradient_clip(clip, program=train_prog)
train_fetch_list = [v.name for v in train_outputs]
train_loss = train_outputs[0]
opt_params = config['Optimizer']
optimizer = create_module(opt_params['function'])(opt_params)
optimizer.minimize(train_loss)
global_lr = optimizer._global_learning_rate()
global_lr.persistable = True
train_fetch_list.append(global_lr.name)
train_reader = reader.train_eval_reader(
config=config, char_ops=char_ops, mode="train")
train_loader.set_sample_list_generator(train_reader, places=place)
eval_prog = fluid.Program()
with fluid.program_guard(eval_prog, startup_prog):
with fluid.unique_name.guard():
eval_loader, eval_outputs = rec_model(mode="eval")
eval_fetch_list = [v.name for v in eval_outputs]
eval_prog = eval_prog.clone(for_test=True)
exe.run(startup_prog)
eval_reader = reader.train_eval_reader(
config=config, char_ops=char_ops, mode="eval")
eval_loader.set_sample_list_generator(eval_reader, places=place)
# compile program for multi-devices
train_compile_program = create_multi_devices_program(train_prog,
train_loss.name)
pretrain_weights = config['Global']['pretrain_weights']
if pretrain_weights is not None:
load_pretrain(exe, train_prog, pretrain_weights)
train_batch_id = 0
train_log_keys = ['loss', 'acc']
log_smooth_window = config['Global']['log_smooth_window']
epoch_num = config['Global']['epoch_num']
loss_type = config['Global']['loss_type']
print_step = config['Global']['print_step']
eval_step = config['Global']['eval_step']
save_epoch_step = config['Global']['save_epoch_step']
save_dir = config['Global']['save_dir']
train_stats = TrainingStats(log_smooth_window, train_log_keys)
best_eval_acc = -1
best_batch_id = 0
best_epoch = 0
for epoch in range(epoch_num):
train_loader.start()
try:
while True:
t1 = time.time()
train_outs = exe.run(program=train_compile_program,
fetch_list=train_fetch_list,
return_numpy=False)
loss = np.mean(np.array(train_outs[0]))
lr = np.mean(np.array(train_outs[-1]))
preds = np.array(train_outs[1])
preds_lod = train_outs[1].lod()[0]
labels = np.array(train_outs[2])
labels_lod = train_outs[2].lod()[0]
acc, acc_num, img_num = cal_predicts_accuracy(
char_ops, preds, preds_lod, labels, labels_lod)
t2 = time.time()
train_batch_elapse = t2 - t1
stats = {'loss': loss, 'acc': acc}
train_stats.update(stats)
if train_batch_id > 0 and train_batch_id % print_step == 0:
logs = train_stats.log()
strs = 'epoch: {}, iter: {}, lr: {:.6f}, {}, time: {:.3f}'.format(
epoch, train_batch_id, lr, logs, train_batch_elapse)
logger.info(strs)
if train_batch_id > 0 and train_batch_id % eval_step == 0:
outs = eval_run(exe, eval_prog, eval_loader,
eval_fetch_list, char_ops, train_batch_id,
"eval")
eval_acc, acc_num, sample_num = outs
if eval_acc > best_eval_acc:
best_eval_acc = eval_acc
best_batch_id = train_batch_id
best_epoch = epoch
save_path = save_dir + "/best_accuracy"
save_model(train_prog, save_path)
strs = 'Test iter: {}, acc:{:.6f}, best_acc:{:.6f}, best_epoch:{}, best_batch_id:{}, sample_num:{}'.format(
train_batch_id, eval_acc, best_eval_acc, best_epoch,
best_batch_id, sample_num)
logger.info(strs)
train_batch_id += 1
except fluid.core.EOFException:
train_loader.reset()
if epoch > 0 and epoch % save_epoch_step == 0:
save_path = save_dir + "/iter_epoch_%d" % (epoch)
save_model(train_prog, save_path)
def test_reader():
config = load_config(FLAGS.config)
merge_config(FLAGS.opt)
char_ops = CharacterOps(config['Global'])
config['Global']['char_num'] = char_ops.get_char_num()
print(config)
# tmp_reader = reader.train_eval_reader(
# config=cfg, char_ops=char_ops, mode="train")
tmp_reader = reader.train_eval_reader(
config=config, char_ops=char_ops, mode="eval")
count = 0
print_count = 0
import time
starttime = time.time()
for data in tmp_reader():
count += len(data)
print_count += 1
if print_count % 10 == 0:
batch_time = (time.time() - starttime) / print_count
print("reader:", count, len(data), batch_time)
print("finish reader:", count)
print("success")
if __name__ == '__main__':
parser = ArgsParser()
parser.add_argument(
"-r",
"--resume_checkpoint",
default=None,
type=str,
help="Checkpoint path for resuming training.")
FLAGS = parser.parse_args()
main()
# test_reader()