def copy_subImages_labels_directly(subImage_dir, subLabel_dir, area_ini):
input_image_dir = parameters.get_directory_None_if_absence(
area_ini, 'input_image_dir')
# it is ok consider a file name as pattern and pass it the following functions to get file list
input_image_or_pattern = parameters.get_string_parameters(
area_ini, 'input_image_or_pattern')
# label raster folder
label_raster_dir = parameters.get_directory_None_if_absence(
area_ini, 'label_raster_dir')
sub_images_list = []
label_path_list = []
if os.path.isdir(subImage_dir) is False:
io_function.mkdir(subImage_dir)
if os.path.isdir(subLabel_dir) is False:
io_function.mkdir(subLabel_dir)
sub_images = io_function.get_file_list_by_pattern(input_image_dir,
input_image_or_pattern)
for sub_img in sub_images:
# find the corresponding label raster
label_name = io_function.get_name_by_adding_tail(
os.path.basename(sub_img), 'label')
label_path = os.path.join(label_raster_dir, label_name)
if os.path.isfile(label_path):
sub_images_list.append(sub_img)
label_path_list.append(label_path)
else:
print('Warning, cannot find label for %s in %s' %
(sub_img, label_raster_dir))
# copy sub-images, adding to txt files
with open('sub_images_labels_list.txt', 'a') as f_obj:
for tif_path, label_file in zip(sub_images_list, label_path_list):
if label_file is None:
continue
dst_subImg = os.path.join(subImage_dir, os.path.basename(tif_path))
# copy sub-images
io_function.copy_file_to_dst(tif_path, dst_subImg, overwrite=True)
dst_label_file = os.path.join(subLabel_dir,
os.path.basename(label_file))
io_function.copy_file_to_dst(label_file,
dst_label_file,
overwrite=True)
sub_image_label_str = dst_subImg + ":" + dst_label_file + '\n'
f_obj.writelines(sub_image_label_str)
def run_evaluation_main(para_file,
b_new_validation_data=False,
train_dir=None):
print("run evaluation")
SECONDS = time.time()
gpu_num = 1
if os.path.isfile(para_file) is False:
raise IOError('File %s not exists in current folder: %s' %
(para_file, os.getcwd()))
network_setting_ini = parameters.get_string_parameters(
para_file, 'network_setting_ini')
tf_research_dir = parameters.get_directory_None_if_absence(
network_setting_ini, 'tf_research_dir')
print(tf_research_dir)
if tf_research_dir is None:
raise ValueError('tf_research_dir is not in %s' % para_file)
if os.path.isdir(tf_research_dir) is False:
raise ValueError('%s does not exist' % tf_research_dir)
# sys.path.insert(0, tf_research_dir)
# sys.path.insert(0, os.path.join(tf_research_dir,'slim'))
# print(sys.path)
# need to change PYTHONPATH, otherwise, deeplab cannot be found
if os.getenv('PYTHONPATH'):
os.environ['PYTHONPATH'] = os.getenv(
'PYTHONPATH') + ':' + tf_research_dir + ':' + os.path.join(
tf_research_dir, 'slim')
else:
os.environ['PYTHONPATH'] = tf_research_dir + ':' + os.path.join(
tf_research_dir, 'slim')
# os.system('echo $PYTHONPATH ')
tf1x_python = parameters.get_file_path_parameters(network_setting_ini,
'tf1x_python')
deeplab_train.tf1x_python = tf1x_python
deeplab_dir = os.path.join(tf_research_dir, 'deeplab')
WORK_DIR = os.getcwd()
expr_name = parameters.get_string_parameters(para_file, 'expr_name')
# prepare data for validation
if b_new_validation_data:
prepare_data_for_evaluation(para_file)
run_evaluation(WORK_DIR,
deeplab_dir,
expr_name,
para_file,
network_setting_ini,
gpu_num,
train_dir=train_dir)
duration = time.time() - SECONDS
os.system(
'echo "$(date): time cost of running evaluation: %.2f seconds">>time_cost.txt'
% duration)
def get_file_path_parameter(parafile, data_dir, data_name_or_pattern):
data_dir = parameters.get_directory_None_if_absence(parafile, data_dir)
data_name_or_pattern = parameters.get_string_parameters_None_if_absence(parafile, data_name_or_pattern)
if data_dir is None or data_name_or_pattern is None:
return None
file_list = io_function.get_file_list_by_pattern(data_dir,data_name_or_pattern)
if len(file_list) < 1:
raise IOError('NO file in %s with name or pattern: %s'%(data_dir, data_name_or_pattern))
if len(file_list) == 1:
return file_list[0]
else:
# return multiple files
return file_list
def train_evaluation_deeplab_separate(WORK_DIR, deeplab_dir, expr_name,
para_file, network_setting_ini, gpu_num):
'''
in "train_evaluation_deeplab", run training, stop, then evaluation, then traininng, make learning rate strange, and the results worse.
so in this function, we start two process, one for training, another for evaluation (run on CPU)
'''
# prepare training folder
EXP_FOLDER = expr_name
INIT_FOLDER = os.path.join(WORK_DIR, EXP_FOLDER, 'init_models')
TRAIN_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'train')
EVAL_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'eval')
VIS_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'vis')
EXPORT_DIR = os.path.join(WORK_DIR, EXP_FOLDER, 'export')
io_function.mkdir(INIT_FOLDER)
io_function.mkdir(TRAIN_LOGDIR)
io_function.mkdir(EVAL_LOGDIR)
io_function.mkdir(VIS_LOGDIR)
io_function.mkdir(EXPORT_DIR)
# prepare the tensorflow check point (pretrained model) for training
pre_trained_dir = parameters.get_directory_None_if_absence(
network_setting_ini, 'pre_trained_model_folder')
pre_trained_tar = parameters.get_string_parameters(network_setting_ini,
'TF_INIT_CKPT')
pre_trained_path = os.path.join(pre_trained_dir, pre_trained_tar)
if os.path.isfile(pre_trained_path) is False:
print('pre-trained model: %s not exist, try to download' %
pre_trained_path)
# try to download the file
pre_trained_url = parameters.get_string_parameters_None_if_absence(
network_setting_ini, 'pre_trained_model_url')
res = os.system('wget %s ' % pre_trained_url)
if res != 0:
sys.exit(1)
io_function.movefiletodir(pre_trained_tar, pre_trained_dir)
# unpack pre-trained model to INIT_FOLDER
os.chdir(INIT_FOLDER)
res = os.system('tar -xf %s' % pre_trained_path)
if res != 0:
raise IOError('failed to unpack %s' % pre_trained_path)
os.chdir(WORK_DIR)
dataset_dir = os.path.join(WORK_DIR, 'tfrecord')
batch_size = parameters.get_digit_parameters(network_setting_ini,
'batch_size', 'int')
# maximum iteration number
iteration_num = parameters.get_digit_parameters(network_setting_ini,
'iteration_num', 'int')
base_learning_rate = parameters.get_digit_parameters(
network_setting_ini, 'base_learning_rate', 'float')
train_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_output_stride', 'int')
train_atrous_rates1 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_atrous_rates1', 'int')
train_atrous_rates2 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_atrous_rates2', 'int')
train_atrous_rates3 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_atrous_rates3', 'int')
inf_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_output_stride', 'int')
inf_atrous_rates1 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates1', 'int')
inf_atrous_rates2 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates2', 'int')
inf_atrous_rates3 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates3', 'int')
# depth_multiplier default is 1.0.
depth_multiplier = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'depth_multiplier', 'float')
decoder_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'decoder_output_stride', 'int')
aspp_convs_filters = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'aspp_convs_filters', 'int')
train_script = os.path.join(deeplab_dir, 'train.py')
train_split = os.path.splitext(
parameters.get_string_parameters(para_file,
'training_sample_list_txt'))[0]
model_variant = parameters.get_string_parameters(network_setting_ini,
'model_variant')
checkpoint = parameters.get_string_parameters(network_setting_ini,
'tf_initial_checkpoint')
init_checkpoint_files = io_function.get_file_list_by_pattern(
INIT_FOLDER, checkpoint + '*')
if len(init_checkpoint_files) < 1:
raise IOError('No initial checkpoint in %s with pattern: %s' %
(INIT_FOLDER, checkpoint))
init_checkpoint = os.path.join(INIT_FOLDER, checkpoint)
b_early_stopping = parameters.get_bool_parameters(para_file,
'b_early_stopping')
b_initialize_last_layer = parameters.get_bool_parameters(
para_file, 'b_initialize_last_layer')
dataset = parameters.get_string_parameters(para_file, 'dataset_name')
num_classes_noBG = parameters.get_digit_parameters_None_if_absence(
para_file, 'NUM_CLASSES_noBG', 'int')
assert num_classes_noBG != None
if b_initialize_last_layer is True:
if pre_trained_tar in pre_trained_tar_21_classes:
print(
'warning, pretrained model %s is trained with 21 classes, set num_of_classes to 21'
% pre_trained_tar)
num_classes_noBG = 20
if pre_trained_tar in pre_trained_tar_19_classes:
print(
'warning, pretrained model %s is trained with 19 classes, set num_of_classes to 19'
% pre_trained_tar)
num_classes_noBG = 18
num_of_classes = num_classes_noBG + 1
image_crop_size = parameters.get_string_list_parameters(
para_file, 'image_crop_size')
if len(image_crop_size) != 2 and image_crop_size[0].isdigit(
) and image_crop_size[1].isdigit():
raise ValueError('image_crop_size should be height,width')
crop_size_str = ','.join(image_crop_size)
# validation interval (epoch), do
# validation_interval = parameters.get_digit_parameters_None_if_absence(para_file,'validation_interval','int')
train_count, val_count = get_train_val_sample_count(WORK_DIR, para_file)
iter_per_epoch = math.ceil(train_count / batch_size)
total_epoches = math.ceil(iteration_num / iter_per_epoch)
already_trained_iteration = get_trained_iteration(TRAIN_LOGDIR)
if already_trained_iteration >= iteration_num:
basic.outputlogMessage('Training already run %d iterations, skip' %
already_trained_iteration)
return True
save_interval_secs = 1200 # default is 1200 second for saving model
save_summaries_secs = 600 # default is 600 second for saving summaries
eval_interval_secs = save_interval_secs # default is 300 second for running evaluation, if no new saved model, no need to run evaluation?
train_process = Process(
target=train_deeplab,
args=(train_script, dataset, train_split, num_of_classes,
base_learning_rate, model_variant, init_checkpoint, TRAIN_LOGDIR,
dataset_dir, gpu_num, train_atrous_rates1, train_atrous_rates2,
train_atrous_rates3, train_output_stride, crop_size_str,
batch_size, iteration_num, depth_multiplier,
decoder_output_stride, aspp_convs_filters,
b_initialize_last_layer))
train_process.start()
time.sleep(60) # wait
if train_process.exitcode is not None and train_process.exitcode != 0:
sys.exit(1)
# eval_process.start()
# time.sleep(10) # wait
# if eval_process.exitcode is not None and eval_process.exitcode != 0:
# sys.exit(1)
while True:
# only run evaluation when there is new trained model
already_trained_iteration = get_trained_iteration(TRAIN_LOGDIR)
miou_dict = get_miou_list_class_all(EVAL_LOGDIR, num_of_classes)
basic.outputlogMessage(
'Already trained iteration: %d, latest evaluation at %d step' %
(already_trained_iteration, miou_dict['step'][-1]))
if already_trained_iteration > miou_dict['step'][-1]:
# run evaluation and wait until it finished
gpuid = "" # set gpuid to empty string, making evaluation run on CPU
evl_script = os.path.join(deeplab_dir, 'eval.py')
evl_split = os.path.splitext(
parameters.get_string_parameters(
para_file, 'validation_sample_list_txt'))[0]
# max_eva_number = -1 # run as many evaluation as possible, --eval_interval_secs (default is 300 seconds)
max_eva_number = 1 # only run once inside the while loop, use while loop to control multiple evaluation
eval_process = Process(
target=evaluation_deeplab,
args=(evl_script, dataset, evl_split, num_of_classes,
model_variant, inf_atrous_rates1, inf_atrous_rates2,
inf_atrous_rates3, inf_output_stride, TRAIN_LOGDIR,
EVAL_LOGDIR, dataset_dir, crop_size_str, max_eva_number,
depth_multiplier, decoder_output_stride,
aspp_convs_filters, gpuid, eval_interval_secs))
eval_process.start(
) # put Process inside while loop to avoid error: AssertionError: cannot start a process twice
while eval_process.is_alive():
time.sleep(5)
# check if need early stopping
if b_early_stopping:
print(datetime.now(), 'check early stopping')
miou_dict = get_miou_list_class_all(EVAL_LOGDIR, num_of_classes)
if 'overall' in miou_dict.keys() and len(
miou_dict['overall']) >= 5:
# if the last five miou did not improve, then stop training
if np.all(np.diff(miou_dict['overall'][-5:]) < 0.005
): # 0.0001 (%0.01) # 0.5 %
basic.outputlogMessage(
'early stopping: stop training because overall miou did not improved in the last five evaluation'
)
output_early_stopping_message(TRAIN_LOGDIR)
# train_process.kill() # this one seems not working
# subprocess pid different from ps output
# https://stackoverflow.com/questions/4444141/subprocess-pid-different-from-ps-output
# os.system('kill ' + str(train_process.pid)) # still not working. train_process.pid is not the one output by ps -aux
# train_process.terminate() # Note that descendant processes of the process will not be terminated
# train_process.join() # Wait until child process terminates
with open('train_py_pid.txt', 'r') as f_obj:
lines = f_obj.readlines()
train_pid = int(lines[0].strip())
os.system('kill ' + str(train_pid))
basic.outputlogMessage(
'kill training processing with id: %d' % train_pid)
break # this breaks the while loop, making that it may not evaluate on some new saved model.
# if the evaluation step is less than saved model iteration, run another iteration again immediately
already_trained_iteration = get_trained_iteration(TRAIN_LOGDIR)
miou_dict = get_miou_list_class_all(EVAL_LOGDIR, num_of_classes)
if already_trained_iteration > miou_dict['step'][-1]:
continue
# if finished training
if train_process.is_alive() is False:
break
# # if eval_process exit, then quit training as well
# if eval_process.is_alive() is False and train_process.is_alive():
# train_process.kill()
# break
time.sleep(eval_interval_secs) # wait for next evaluation
# save loss value to disk
get_loss_learning_rate_list(TRAIN_LOGDIR)
# get miou again
miou_dict = get_miou_list_class_all(EVAL_LOGDIR, num_of_classes)
# eval_process did not exit as expected, kill it again.
# os.system('kill ' + str(eval_process.pid))
# get iou and backup
iou_path = os.path.join(EVAL_LOGDIR, 'miou.txt')
loss_path = os.path.join(TRAIN_LOGDIR, 'loss_learning_rate.txt')
patch_info = os.path.join(WORK_DIR, 'sub_images_patches_info.txt')
# backup miou and training_loss & learning rate
test_id = os.path.basename(WORK_DIR) + '_' + expr_name
backup_dir = os.path.join(WORK_DIR, 'result_backup')
if os.path.isdir(backup_dir) is False:
io_function.mkdir(backup_dir)
new_iou_name = os.path.join(backup_dir,
test_id + '_' + os.path.basename(iou_path))
io_function.copy_file_to_dst(iou_path, new_iou_name, overwrite=True)
loss_new_name = os.path.join(backup_dir,
test_id + '_' + os.path.basename(loss_path))
io_function.copy_file_to_dst(loss_path, loss_new_name, overwrite=True)
new_patch_info = os.path.join(backup_dir,
test_id + '_' + os.path.basename(patch_info))
io_function.copy_file_to_dst(patch_info, new_patch_info, overwrite=True)
# plot mIOU, loss, and learnint rate curves, and backup
miou_curve_path = plot_miou_loss_curve.plot_miou_loss_main(
iou_path,
train_count=train_count,
val_count=val_count,
batch_size=batch_size)
loss_curve_path = plot_miou_loss_curve.plot_miou_loss_main(
loss_path,
train_count=train_count,
val_count=val_count,
batch_size=batch_size)
miou_curve_bakname = os.path.join(
backup_dir, test_id + '_' + os.path.basename(miou_curve_path))
io_function.copy_file_to_dst(miou_curve_path,
miou_curve_bakname,
overwrite=True)
loss_curve_bakname = os.path.join(
backup_dir, test_id + '_' + os.path.basename(loss_curve_path))
io_function.copy_file_to_dst(loss_curve_path,
loss_curve_bakname,
overwrite=True)
def train_evaluation_deeplab(WORK_DIR, deeplab_dir, expr_name, para_file,
network_setting_ini, gpu_num):
# prepare training folder
EXP_FOLDER = expr_name
INIT_FOLDER = os.path.join(WORK_DIR, EXP_FOLDER, 'init_models')
TRAIN_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'train')
EVAL_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'eval')
VIS_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'vis')
EXPORT_DIR = os.path.join(WORK_DIR, EXP_FOLDER, 'export')
io_function.mkdir(INIT_FOLDER)
io_function.mkdir(TRAIN_LOGDIR)
io_function.mkdir(EVAL_LOGDIR)
io_function.mkdir(VIS_LOGDIR)
io_function.mkdir(EXPORT_DIR)
# prepare the tensorflow check point (pretrained model) for training
pre_trained_dir = parameters.get_directory_None_if_absence(
network_setting_ini, 'pre_trained_model_folder')
pre_trained_tar = parameters.get_string_parameters(network_setting_ini,
'TF_INIT_CKPT')
pre_trained_path = os.path.join(pre_trained_dir, pre_trained_tar)
if os.path.isfile(pre_trained_path) is False:
print('pre-trained model: %s not exist, try to download' %
pre_trained_path)
# try to download the file
pre_trained_url = parameters.get_string_parameters_None_if_absence(
network_setting_ini, 'pre_trained_model_url')
res = os.system('wget %s ' % pre_trained_url)
if res != 0:
sys.exit(1)
io_function.movefiletodir(pre_trained_tar, pre_trained_dir)
# unpack pre-trained model to INIT_FOLDER
os.chdir(INIT_FOLDER)
res = os.system('tar -xf %s' % pre_trained_path)
if res != 0:
raise IOError('failed to unpack %s' % pre_trained_path)
os.chdir(WORK_DIR)
dataset_dir = os.path.join(WORK_DIR, 'tfrecord')
batch_size = parameters.get_digit_parameters(network_setting_ini,
'batch_size', 'int')
# maximum iteration number
iteration_num = parameters.get_digit_parameters(network_setting_ini,
'iteration_num', 'int')
base_learning_rate = parameters.get_digit_parameters(
network_setting_ini, 'base_learning_rate', 'float')
train_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_output_stride', 'int')
train_atrous_rates1 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_atrous_rates1', 'int')
train_atrous_rates2 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_atrous_rates2', 'int')
train_atrous_rates3 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'train_atrous_rates3', 'int')
inf_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_output_stride', 'int')
inf_atrous_rates1 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates1', 'int')
inf_atrous_rates2 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates2', 'int')
inf_atrous_rates3 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates3', 'int')
# depth_multiplier default is 1.0.
depth_multiplier = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'depth_multiplier', 'float')
decoder_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'decoder_output_stride', 'int')
aspp_convs_filters = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'aspp_convs_filters', 'int')
train_script = os.path.join(deeplab_dir, 'train.py')
train_split = os.path.splitext(
parameters.get_string_parameters(para_file,
'training_sample_list_txt'))[0]
model_variant = parameters.get_string_parameters(network_setting_ini,
'model_variant')
checkpoint = parameters.get_string_parameters(network_setting_ini,
'tf_initial_checkpoint')
init_checkpoint_files = io_function.get_file_list_by_pattern(
INIT_FOLDER, checkpoint + '*')
if len(init_checkpoint_files) < 1:
raise IOError('No initial checkpoint in %s with pattern: %s' %
(INIT_FOLDER, checkpoint))
init_checkpoint = os.path.join(INIT_FOLDER, checkpoint)
b_early_stopping = parameters.get_bool_parameters(para_file,
'b_early_stopping')
b_initialize_last_layer = parameters.get_bool_parameters(
para_file, 'b_initialize_last_layer')
dataset = parameters.get_string_parameters(para_file, 'dataset_name')
num_classes_noBG = parameters.get_digit_parameters_None_if_absence(
para_file, 'NUM_CLASSES_noBG', 'int')
assert num_classes_noBG != None
if b_initialize_last_layer is True:
if pre_trained_tar in pre_trained_tar_21_classes:
print(
'warning, pretrained model %s is trained with 21 classes, set num_of_classes to 21'
% pre_trained_tar)
num_classes_noBG = 20
if pre_trained_tar in pre_trained_tar_19_classes:
print(
'warning, pretrained model %s is trained with 19 classes, set num_of_classes to 19'
% pre_trained_tar)
num_classes_noBG = 18
num_of_classes = num_classes_noBG + 1
image_crop_size = parameters.get_string_list_parameters(
para_file, 'image_crop_size')
if len(image_crop_size) != 2 and image_crop_size[0].isdigit(
) and image_crop_size[1].isdigit():
raise ValueError('image_crop_size should be height,width')
crop_size_str = ','.join(image_crop_size)
evl_script = os.path.join(deeplab_dir, 'eval.py')
evl_split = os.path.splitext(
parameters.get_string_parameters(para_file,
'validation_sample_list_txt'))[0]
max_eva_number = 1
# validation interval (epoch)
validation_interval = parameters.get_digit_parameters_None_if_absence(
para_file, 'validation_interval', 'int')
train_count, val_count = get_train_val_sample_count(WORK_DIR, para_file)
iter_per_epoch = math.ceil(train_count / batch_size)
total_epoches = math.ceil(iteration_num / iter_per_epoch)
already_trained_iteration = get_trained_iteration(TRAIN_LOGDIR)
if already_trained_iteration >= iteration_num:
basic.outputlogMessage('Training already run %d iterations, skip' %
already_trained_iteration)
return True
if validation_interval is None:
basic.outputlogMessage(
'No input validation_interval, so training to %d, then evaluating in the end'
% iteration_num)
# run training
train_deeplab(train_script, dataset, train_split, num_of_classes,
base_learning_rate, model_variant, init_checkpoint,
TRAIN_LOGDIR, dataset_dir, gpu_num, train_atrous_rates1,
train_atrous_rates2, train_atrous_rates3,
train_output_stride, crop_size_str, batch_size,
iteration_num, depth_multiplier, decoder_output_stride,
aspp_convs_filters, b_initialize_last_layer)
# run evaluation
evaluation_deeplab(evl_script, dataset, evl_split, num_of_classes,
model_variant, inf_atrous_rates1, inf_atrous_rates2,
inf_atrous_rates3, inf_output_stride, TRAIN_LOGDIR,
EVAL_LOGDIR, dataset_dir, crop_size_str,
max_eva_number, depth_multiplier,
decoder_output_stride, aspp_convs_filters)
miou_dict = get_miou_list_class_all(EVAL_LOGDIR, num_of_classes)
get_loss_learning_rate_list(TRAIN_LOGDIR)
else:
basic.outputlogMessage(
'training to the maximum iteration of %d, and evaluating very %d epoch(es)'
% (iteration_num, validation_interval))
for epoch in range(validation_interval,
total_epoches + validation_interval,
validation_interval):
to_iter_num = min(epoch * iter_per_epoch, iteration_num)
if to_iter_num <= already_trained_iteration:
continue
basic.outputlogMessage(
'training and evaluating to %d epoches (to iteration: %d)' %
(epoch, to_iter_num))
# run training
train_deeplab(train_script, dataset, train_split, num_of_classes,
base_learning_rate, model_variant, init_checkpoint,
TRAIN_LOGDIR, dataset_dir, gpu_num,
train_atrous_rates1, train_atrous_rates2,
train_atrous_rates3, train_output_stride,
crop_size_str, batch_size, to_iter_num,
depth_multiplier, decoder_output_stride,
aspp_convs_filters, b_initialize_last_layer)
# run evaluation
evaluation_deeplab(evl_script, dataset, evl_split, num_of_classes,
model_variant, inf_atrous_rates1,
inf_atrous_rates2, inf_atrous_rates3,
inf_output_stride, TRAIN_LOGDIR, EVAL_LOGDIR,
dataset_dir, crop_size_str, max_eva_number,
depth_multiplier, decoder_output_stride,
aspp_convs_filters)
# get miou
miou_dict = get_miou_list_class_all(EVAL_LOGDIR, num_of_classes)
# save loss value to disk
get_loss_learning_rate_list(TRAIN_LOGDIR)
# check if need to early stopping
if b_early_stopping:
if len(miou_dict['overall']) >= 5:
# if the last five miou did not improve, then stop training
if np.all(np.diff(miou_dict['overall'][-5:]) < 0.005
): # 0.0001 (%0.01) # 0.5 %
basic.outputlogMessage(
'early stopping: stop training because overall miou did not improved in the last five evaluation'
)
output_early_stopping_message(TRAIN_LOGDIR)
break
# plot mIOU, loss, and learnint rate curves
iou_path = os.path.join(EVAL_LOGDIR, 'miou.txt')
loss_path = os.path.join(TRAIN_LOGDIR, 'loss_learning_rate.txt')
miou_curve_path = plot_miou_loss_curve.plot_miou_loss_main(
iou_path,
train_count=train_count,
val_count=val_count,
batch_size=batch_size)
loss_curve_path = plot_miou_loss_curve.plot_miou_loss_main(
loss_path,
train_count=train_count,
val_count=val_count,
batch_size=batch_size)
# backup miou and training_loss & learning rate
test_id = os.path.basename(WORK_DIR) + '_' + expr_name
backup_dir = os.path.join(WORK_DIR, 'result_backup')
if os.path.isdir(backup_dir) is False:
io_function.mkdir(backup_dir)
new_iou_name = os.path.join(backup_dir,
test_id + '_' + os.path.basename(iou_path))
io_function.copy_file_to_dst(iou_path, new_iou_name, overwrite=True)
miou_curve_bakname = os.path.join(
backup_dir, test_id + '_' + os.path.basename(miou_curve_path))
io_function.copy_file_to_dst(miou_curve_path,
miou_curve_bakname,
overwrite=True)
loss_new_name = os.path.join(backup_dir,
test_id + '_' + os.path.basename(loss_path))
io_function.copy_file_to_dst(loss_path, loss_new_name, overwrite=True)
loss_curve_bakname = os.path.join(
backup_dir, test_id + '_' + os.path.basename(loss_curve_path))
io_function.copy_file_to_dst(loss_curve_path,
loss_curve_bakname,
overwrite=True)
def get_sub_images_multi_regions(para_file):
print(
"extract sub-images and sub-labels for a given shape file (training polygons)"
)
if os.path.isfile(para_file) is False:
raise IOError('File %s not exists in current folder: %s' %
(para_file, os.getcwd()))
get_subImage_script = os.path.join(code_dir, 'datasets',
'get_subImages.py')
SECONDS = time.time()
# get name of training areas
multi_training_regions = parameters.get_string_list_parameters_None_if_absence(
para_file, 'training_regions')
if multi_training_regions is None or len(multi_training_regions) < 1:
raise ValueError('No training area is set in %s' % para_file)
# multi_training_files = parameters.get_string_parameters_None_if_absence(para_file, 'multi_training_files')
dstnodata = parameters.get_string_parameters(para_file, 'dst_nodata')
buffersize = parameters.get_string_parameters(para_file, 'buffer_size')
rectangle_ext = parameters.get_string_parameters(para_file,
'b_use_rectangle')
process_num = parameters.get_digit_parameters(para_file, 'process_num',
'int')
b_no_label_image = parameters.get_bool_parameters_None_if_absence(
para_file, 'b_no_label_image')
if os.path.isfile('sub_images_labels_list.txt'):
io_function.delete_file_or_dir('sub_images_labels_list.txt')
subImage_dir = parameters.get_string_parameters_None_if_absence(
para_file, 'input_train_dir')
subLabel_dir = parameters.get_string_parameters_None_if_absence(
para_file, 'input_label_dir')
# loop each training regions
for idx, area_ini in enumerate(multi_training_regions):
input_image_dir = parameters.get_directory_None_if_absence(
area_ini, 'input_image_dir')
# it is ok consider a file name as pattern and pass it the following functions to get file list
input_image_or_pattern = parameters.get_string_parameters(
area_ini, 'input_image_or_pattern')
b_sub_images_json = parameters.get_bool_parameters(
area_ini, 'b_sub_images_json')
if b_sub_images_json is True:
# copy sub-images, then covert json files to label images.
object_names = parameters.get_string_list_parameters(
para_file, 'object_names')
get_subImages_json.get_subimages_label_josn(
input_image_dir,
input_image_or_pattern,
subImage_dir,
subLabel_dir,
object_names,
b_no_label_image=b_no_label_image,
process_num=process_num)
pass
else:
all_train_shp = parameters.get_file_path_parameters_None_if_absence(
area_ini, 'training_polygons')
train_shp = parameters.get_string_parameters(
area_ini, 'training_polygons_sub')
# get subImage and subLabel for one training polygons
print(
'extract training data from image folder (%s) and polgyons (%s)'
% (input_image_dir, train_shp))
if b_no_label_image is True:
get_subImage_one_shp(get_subImage_script,
all_train_shp,
buffersize,
dstnodata,
rectangle_ext,
train_shp,
input_image_dir,
file_pattern=input_image_or_pattern,
process_num=process_num)
else:
get_subImage_subLabel_one_shp(
get_subImage_script,
all_train_shp,
buffersize,
dstnodata,
rectangle_ext,
train_shp,
input_image_dir,
file_pattern=input_image_or_pattern,
process_num=process_num)
# check black sub-images or most part of the sub-images is black (nodata)
new_sub_image_label_list = []
delete_sub_image_label_list = []
subImage_dir_delete = subImage_dir + '_delete'
subLabel_dir_delete = subLabel_dir + '_delete'
io_function.mkdir(subImage_dir_delete)
if b_no_label_image is None or b_no_label_image is False:
io_function.mkdir(subLabel_dir_delete)
get_valid_percent_entropy.plot_valid_entropy(subImage_dir)
with open('sub_images_labels_list.txt', 'r') as f_obj:
lines = f_obj.readlines()
for line in lines:
image_path, label_path = line.strip().split(':')
# valid_per = raster_io.get_valid_pixel_percentage(image_path)
valid_per, entropy = raster_io.get_valid_percent_shannon_entropy(
image_path) # base=10
if valid_per > 60 and entropy >= 0.5:
new_sub_image_label_list.append(line)
else:
delete_sub_image_label_list.append(line)
io_function.movefiletodir(image_path, subImage_dir_delete)
if os.path.isfile(label_path):
io_function.movefiletodir(label_path, subLabel_dir_delete)
if len(delete_sub_image_label_list) > 0:
with open('sub_images_labels_list.txt', 'w') as f_obj:
for line in new_sub_image_label_list:
f_obj.writelines(line)
# check weather they have the same subImage and subLabel
if b_no_label_image is None or b_no_label_image is False:
sub_image_list = io_function.get_file_list_by_pattern(
subImage_dir, '*.tif')
sub_label_list = io_function.get_file_list_by_pattern(
subLabel_dir, '*.tif')
if len(sub_image_list) != len(sub_label_list):
raise ValueError(
'the count of subImage (%d) and subLabel (%d) is different' %
(len(sub_image_list), len(sub_label_list)))
# save brief information of sub-images
height_list = []
width_list = []
band_count = 0
dtype = 'unknown'
for line in new_sub_image_label_list:
image_path, label_path = line.strip().split(':')
height, width, band_count, dtype = raster_io.get_height_width_bandnum_dtype(
image_path)
height_list.append(height)
width_list.append(width)
# save info to file, if it exists, it will be overwritten
img_count = len(new_sub_image_label_list)
with open('sub_images_patches_info.txt', 'w') as f_obj:
f_obj.writelines('information of sub-images: \n')
f_obj.writelines('number of sub-images : %d \n' % img_count)
f_obj.writelines('band count : %d \n' % band_count)
f_obj.writelines('data type : %s \n' % dtype)
f_obj.writelines('maximum width and height: %d, %d \n' %
(max(width_list), max(height_list)))
f_obj.writelines('minimum width and height: %d, %d \n' %
(min(width_list), min(height_list)))
f_obj.writelines(
'mean width and height: %.2f, %.2f \n\n' %
(sum(width_list) / img_count, sum(height_list) / img_count))
duration = time.time() - SECONDS
os.system(
'echo "$(date): time cost of getting sub images and labels: %.2f seconds">>time_cost.txt'
% duration)
def main(options, args):
print("%s : export the frozen inference graph" %
os.path.basename(sys.argv[0]))
para_file = args[0]
if os.path.isfile(para_file) is False:
raise IOError('File %s not exists in current folder: %s' %
(para_file, os.getcwd()))
network_setting_ini = parameters.get_string_parameters(
para_file, 'network_setting_ini')
tf_research_dir = parameters.get_directory_None_if_absence(
network_setting_ini, 'tf_research_dir')
print(tf_research_dir)
if tf_research_dir is None:
raise ValueError('tf_research_dir is not in %s' % para_file)
if os.path.isdir(tf_research_dir) is False:
raise ValueError('%s does not exist' % tf_research_dir)
if os.getenv('PYTHONPATH'):
os.environ['PYTHONPATH'] = os.getenv(
'PYTHONPATH') + ':' + tf_research_dir + ':' + os.path.join(
tf_research_dir, 'slim')
else:
os.environ['PYTHONPATH'] = tf_research_dir + ':' + os.path.join(
tf_research_dir, 'slim')
global tf1x_python
tf1x_python = parameters.get_file_path_parameters(network_setting_ini,
'tf1x_python')
deeplab_dir = os.path.join(tf_research_dir, 'deeplab')
WORK_DIR = os.getcwd()
expr_name = parameters.get_string_parameters(para_file, 'expr_name')
EXP_FOLDER = expr_name
TRAIN_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'train')
EXPORT_DIR = os.path.join(WORK_DIR, EXP_FOLDER, 'export')
inf_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_output_stride', 'int')
inf_atrous_rates1 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates1', 'int')
inf_atrous_rates2 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates2', 'int')
inf_atrous_rates3 = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'inf_atrous_rates3', 'int')
# depth_multiplier default is 1.0.
depth_multiplier = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'depth_multiplier', 'float')
decoder_output_stride = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'decoder_output_stride', 'int')
aspp_convs_filters = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'aspp_convs_filters', 'int')
model_variant = parameters.get_string_parameters(network_setting_ini,
'model_variant')
num_classes_noBG = parameters.get_digit_parameters_None_if_absence(
para_file, 'NUM_CLASSES_noBG', 'int')
assert num_classes_noBG != None
b_initialize_last_layer = parameters.get_bool_parameters(
para_file, 'b_initialize_last_layer')
if b_initialize_last_layer is False:
pre_trained_tar = parameters.get_string_parameters(
network_setting_ini, 'TF_INIT_CKPT')
if pre_trained_tar in pre_trained_tar_21_classes:
print(
'warning, pretrained model %s is trained with 21 classes, set num_of_classes to 21'
% pre_trained_tar)
num_classes_noBG = 20
if pre_trained_tar in pre_trained_tar_19_classes:
print(
'warning, pretrained model %s is trained with 19 classes, set num_of_classes to 19'
% pre_trained_tar)
num_classes_noBG = 18
num_of_classes = num_classes_noBG + 1
image_crop_size = parameters.get_string_list_parameters(
para_file, 'image_crop_size')
if len(image_crop_size) != 2 and image_crop_size[0].isdigit(
) and image_crop_size[1].isdigit():
raise ValueError('image_crop_size should be height,width')
iteration_num = get_trained_iteration(TRAIN_LOGDIR)
multi_scale = parameters.get_digit_parameters_None_if_absence(
network_setting_ini, 'export_multi_scale', 'int')
export_script = os.path.join(deeplab_dir, 'export_model.py')
CKPT_PATH = os.path.join(TRAIN_LOGDIR, 'model.ckpt-%s' % iteration_num)
EXPORT_PATH = os.path.join(EXPORT_DIR,
'frozen_inference_graph_%s.pb' % iteration_num)
if os.path.isfile(EXPORT_PATH):
basic.outputlogMessage('%s exists, skipping exporting models' %
EXPORT_PATH)
return
export_graph(export_script, CKPT_PATH, EXPORT_PATH, model_variant,
num_of_classes, inf_atrous_rates1, inf_atrous_rates2,
inf_atrous_rates3, inf_output_stride, image_crop_size[0],
image_crop_size[1], multi_scale, depth_multiplier,
decoder_output_stride, aspp_convs_filters)
