def get_sub_images_from_prediction_results(para_file, polygons_shp, image_folder_or_path, image_pattern, saved_dir): class_names = parameters.get_string_list_parameters( para_file, 'object_names') dstnodata = parameters.get_digit_parameters(para_file, 'dst_nodata', 'int') bufferSize = parameters.get_digit_parameters(para_file, 'buffer_size', 'int') rectangle_ext = parameters.get_string_parameters_None_if_absence( para_file, 'b_use_rectangle') if rectangle_ext is not None: b_rectangle = True else: b_rectangle = False process_num = parameters.get_digit_parameters(para_file, 'process_num', 'int') get_sub_images_pixel_json_files(polygons_shp, image_folder_or_path, image_pattern, class_names, bufferSize, dstnodata, saved_dir, b_rectangle, process_num) pass
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 postProcess(para_file, inf_post_note, b_skip_getshp=False, test_id=None): # test_id is the related to training if os.path.isfile(para_file) is False: raise IOError('File %s not exists in current folder: %s' % (para_file, os.getcwd())) # the test string in 'exe.sh' test_note = inf_post_note WORK_DIR = os.getcwd() SECONDS = time.time() expr_name = parameters.get_string_parameters(para_file, 'expr_name') network_setting_ini = parameters.get_string_parameters( para_file, 'network_setting_ini') inf_dir = parameters.get_directory(para_file, 'inf_output_dir') if test_id is None: test_id = os.path.basename(WORK_DIR) + '_' + expr_name # get name of inference areas multi_inf_regions = parameters.get_string_list_parameters( para_file, 'inference_regions') # run post-processing parallel # max_parallel_postProc_task = 8 backup_dir = os.path.join(WORK_DIR, 'result_backup') io_function.mkdir(backup_dir) # loop each inference regions sub_tasks = [] same_area_time_inis = group_same_area_time_observations(multi_inf_regions) region_eva_reports = {} for key in same_area_time_inis.keys(): multi_observations = same_area_time_inis[key] area_name = parameters.get_string_parameters( multi_observations[0], 'area_name') # they have the same name and time area_time = parameters.get_string_parameters(multi_observations[0], 'area_time') merged_shp_list = [] map_raster_list_2d = [None] * len(multi_observations) for area_idx, area_ini in enumerate(multi_observations): area_remark = parameters.get_string_parameters( area_ini, 'area_remark') area_save_dir, shp_pre, _ = get_observation_save_dir_shp_pre( inf_dir, area_name, area_time, area_remark, test_id) # get image list inf_image_dir = parameters.get_directory(area_ini, 'inf_image_dir') # it is ok consider a file name as pattern and pass it the following functions to get file list inf_image_or_pattern = parameters.get_string_parameters( area_ini, 'inf_image_or_pattern') inf_img_list = io_function.get_file_list_by_pattern( inf_image_dir, inf_image_or_pattern) img_count = len(inf_img_list) if img_count < 1: raise ValueError( 'No image for inference, please check inf_image_dir and inf_image_or_pattern in %s' % area_ini) merged_shp = os.path.join(WORK_DIR, area_save_dir, shp_pre + '.shp') if b_skip_getshp: pass else: # post image one by one result_shp_list = [] map_raster_list = [] for img_idx, img_path in enumerate(inf_img_list): out_shp, out_raster = inf_results_to_shapefile( WORK_DIR, img_idx, area_save_dir, test_id) if out_shp is None or out_raster is None: continue result_shp_list.append(os.path.join(WORK_DIR, out_shp)) map_raster_list.append(out_raster) # merge shapefiles if merge_shape_files(result_shp_list, merged_shp) is False: continue map_raster_list_2d[area_idx] = map_raster_list merged_shp_list.append(merged_shp) if b_skip_getshp is False: # add occurrence to each polygons get_occurence_for_multi_observation(merged_shp_list) for area_idx, area_ini in enumerate(multi_observations): area_remark = parameters.get_string_parameters( area_ini, 'area_remark') area_save_dir, shp_pre, area_remark_time = get_observation_save_dir_shp_pre( inf_dir, area_name, area_time, area_remark, test_id) merged_shp = os.path.join(WORK_DIR, area_save_dir, shp_pre + '.shp') if os.path.isfile(merged_shp) is False: print('Warning, %s not exist, skip' % merged_shp) continue # add attributes to shapefile # add_attributes_script = os.path.join(code_dir,'datasets', 'get_polygon_attributes.py') shp_attributes = os.path.join(WORK_DIR, area_save_dir, shp_pre + '_post_NOrm.shp') # add_polygon_attributes(add_attributes_script,merged_shp, shp_attributes, para_file, area_ini ) add_polygon_attributes(merged_shp, shp_attributes, para_file, area_ini) # remove polygons # rm_polygon_script = os.path.join(code_dir,'datasets', 'remove_mappedPolygons.py') shp_post = os.path.join(WORK_DIR, area_save_dir, shp_pre + '_post.shp') # remove_polygons(rm_polygon_script,shp_attributes, shp_post, para_file) remove_polygons_main(shp_attributes, shp_post, para_file) # evaluate the mapping results # eval_shp_script = os.path.join(code_dir,'datasets', 'evaluation_result.py') out_report = os.path.join(WORK_DIR, area_save_dir, shp_pre + '_evaluation_report.txt') # evaluation_polygons(eval_shp_script, shp_post, para_file, area_ini,out_report) evaluation_polygons(shp_post, para_file, area_ini, out_report) ##### copy and backup files ###### # copy files to result_backup if len(test_note) > 0: backup_dir_area = os.path.join( backup_dir, area_name + '_' + area_remark_time + '_' + test_id + '_' + test_note) else: backup_dir_area = os.path.join( backup_dir, area_name + '_' + area_remark_time + '_' + test_id) io_function.mkdir(backup_dir_area) if len(test_note) > 0: bak_merged_shp = os.path.join( backup_dir_area, '_'.join([shp_pre, test_note]) + '.shp') bak_post_shp = os.path.join( backup_dir_area, '_'.join([shp_pre, 'post', test_note]) + '.shp') bak_eva_report = os.path.join( backup_dir_area, '_'.join([shp_pre, 'eva_report', test_note]) + '.txt') bak_area_ini = os.path.join( backup_dir_area, '_'.join([shp_pre, 'region', test_note]) + '.ini') else: bak_merged_shp = os.path.join(backup_dir_area, '_'.join([shp_pre]) + '.shp') bak_post_shp = os.path.join( backup_dir_area, '_'.join([shp_pre, 'post']) + '.shp') bak_eva_report = os.path.join( backup_dir_area, '_'.join([shp_pre, 'eva_report']) + '.txt') bak_area_ini = os.path.join( backup_dir_area, '_'.join([shp_pre, 'region']) + '.ini') io_function.copy_shape_file(merged_shp, bak_merged_shp) io_function.copy_shape_file(shp_post, bak_post_shp) if os.path.isfile(out_report): io_function.copy_file_to_dst(out_report, bak_eva_report, overwrite=True) io_function.copy_file_to_dst(area_ini, bak_area_ini, overwrite=True) # copy map raster b_backup_map_raster = parameters.get_bool_parameters_None_if_absence( area_ini, 'b_backup_map_raster') if b_backup_map_raster is True: if map_raster_list_2d[area_idx] is not None: for map_tif in map_raster_list_2d[area_idx]: bak_map_tif = os.path.join(backup_dir_area, os.path.basename(map_tif)) io_function.copy_file_to_dst(map_tif, bak_map_tif, overwrite=True) region_eva_reports[shp_pre] = bak_eva_report if len(test_note) > 0: bak_para_ini = os.path.join( backup_dir, '_'.join([test_id, 'para', test_note]) + '.ini') bak_network_ini = os.path.join( backup_dir, '_'.join([test_id, 'network', test_note]) + '.ini') bak_time_cost = os.path.join( backup_dir, '_'.join([test_id, 'time_cost', test_note]) + '.txt') else: bak_para_ini = os.path.join(backup_dir, '_'.join([test_id, 'para']) + '.ini') bak_network_ini = os.path.join(backup_dir, '_'.join([test_id, 'network']) + '.ini') bak_time_cost = os.path.join(backup_dir, '_'.join([test_id, 'time_cost']) + '.txt') io_function.copy_file_to_dst(para_file, bak_para_ini) io_function.copy_file_to_dst(network_setting_ini, bak_network_ini) if os.path.isfile('time_cost.txt'): io_function.copy_file_to_dst('time_cost.txt', bak_time_cost) # output the evaluation report to screen for key in region_eva_reports.keys(): report = region_eva_reports[key] if os.path.isfile(report) is False: continue print('evaluation report for %s:' % key) os.system('head -n 7 %s' % report) # output evaluation report to table if len(test_note) > 0: out_table = os.path.join( backup_dir, '_'.join([test_id, 'accuracy_table', test_note]) + '.xlsx') else: out_table = os.path.join( backup_dir, '_'.join([test_id, 'accuracy_table']) + '.xlsx') eva_reports = [ region_eva_reports[key] for key in region_eva_reports if os.path.isfile(region_eva_reports[key]) ] eva_report_to_tables.eva_reports_to_table(eva_reports, out_table) duration = time.time() - SECONDS os.system( 'echo "$(date): time cost of post-procesing: %.2f seconds">>time_cost.txt' % duration)
def main(options, args): print( "%s : prediction using the trained model (run parallel if use multiple GPUs) " % os.path.basename(sys.argv[0])) machine_name = os.uname()[1] start_time = datetime.datetime.now() 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())) basic.setlogfile('parallel_predict_Log.txt') deeplab_inf_script = os.path.join(code_dir, 'deeplabBased', 'deeplab_inference.py') network_setting_ini = parameters.get_string_parameters( para_file, 'network_setting_ini') global tf1x_python tf1x_python = parameters.get_file_path_parameters(network_setting_ini, 'tf1x_python') trained_model = options.trained_model outdir = parameters.get_directory(para_file, 'inf_output_dir') # remove previous results (let user remove this folder manually or in exe.sh folder) io_function.mkdir(outdir) # get name of inference areas multi_inf_regions = parameters.get_string_list_parameters( para_file, 'inference_regions') # max_parallel_inf_task = parameters.get_digit_parameters(para_file,'max_parallel_inf_task','int') b_use_multiGPUs = parameters.get_bool_parameters(para_file, 'b_use_multiGPUs') # loop each inference regions sub_tasks = [] for area_idx, area_ini in enumerate(multi_inf_regions): area_name = parameters.get_string_parameters(area_ini, 'area_name') area_remark = parameters.get_string_parameters(area_ini, 'area_remark') area_time = parameters.get_string_parameters(area_ini, 'area_time') inf_image_dir = parameters.get_directory(area_ini, 'inf_image_dir') # it is ok consider a file name as pattern and pass it the following functions to get file list inf_image_or_pattern = parameters.get_string_parameters( area_ini, 'inf_image_or_pattern') inf_img_list = io_function.get_file_list_by_pattern( inf_image_dir, inf_image_or_pattern) img_count = len(inf_img_list) if img_count < 1: raise ValueError( 'No image for inference, please check inf_image_dir and inf_image_or_pattern in %s' % area_ini) area_save_dir = os.path.join( outdir, area_name + '_' + area_remark + '_' + area_time) io_function.mkdir(area_save_dir) # parallel inference images for this area CUDA_VISIBLE_DEVICES = [] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys(): CUDA_VISIBLE_DEVICES = [ int(item.strip()) for item in os.environ['CUDA_VISIBLE_DEVICES'].split(',') ] idx = 0 while idx < img_count: if b_use_multiGPUs: # get available GPUs # https://github.com/anderskm/gputil deviceIDs = GPUtil.getAvailable(order='first', limit=100, maxLoad=0.5, maxMemory=0.5, includeNan=False, excludeID=[], excludeUUID=[]) # only use the one in CUDA_VISIBLE_DEVICES if len(CUDA_VISIBLE_DEVICES) > 0: deviceIDs = [ item for item in deviceIDs if item in CUDA_VISIBLE_DEVICES ] basic.outputlogMessage('on ' + machine_name + ', available GPUs:' + str(deviceIDs) + ', among visible ones:' + str(CUDA_VISIBLE_DEVICES)) else: basic.outputlogMessage('on ' + machine_name + ', available GPUs:' + str(deviceIDs)) if len(deviceIDs) < 1: time.sleep( 60 ) # wait one minute, then check the available GPUs again continue # set only the first available visible gpuid = deviceIDs[0] basic.outputlogMessage( '%d: predict image %s on GPU %d of %s' % (idx, inf_img_list[idx], gpuid, machine_name)) else: gpuid = None basic.outputlogMessage('%d: predict image %s on %s' % (idx, inf_img_list[idx], machine_name)) # run inference img_save_dir = os.path.join(area_save_dir, 'I%d' % idx) inf_list_file = os.path.join(area_save_dir, '%d.txt' % idx) # if it already exist, then skip if os.path.isdir(img_save_dir) and is_file_exist_in_folder( img_save_dir): basic.outputlogMessage( 'folder of %dth image (%s) already exist, ' 'it has been predicted or is being predicted' % (idx, inf_img_list[idx])) idx += 1 continue with open(inf_list_file, 'w') as inf_obj: inf_obj.writelines(inf_img_list[idx] + '\n') sub_process = Process(target=predict_one_image_deeplab, args=(deeplab_inf_script, para_file, network_setting_ini, img_save_dir, inf_list_file, gpuid, trained_model)) sub_process.start() sub_tasks.append(sub_process) if b_use_multiGPUs is False: # wait until previous one finished while sub_process.is_alive(): time.sleep(5) idx += 1 # wait until predicted image patches exist or exceed 20 minutes time0 = time.time() elapsed_time = time.time() - time0 while elapsed_time < 20 * 60: elapsed_time = time.time() - time0 file_exist = is_file_exist_in_folder(img_save_dir) if file_exist is True or sub_process.is_alive() is False: break else: time.sleep(5) if sub_process.exitcode is not None and sub_process.exitcode != 0: sys.exit(1) # if 'chpc' in machine_name: # time.sleep(60) # wait 60 second on ITSC services # else: # time.sleep(10) # check all the tasks already finished while b_all_task_finish(sub_tasks) is False: basic.outputlogMessage('wait all tasks to finish') time.sleep(60) end_time = datetime.datetime.now() diff_time = end_time - start_time out_str = "%s: time cost of total parallel inference on %s: %d seconds" % ( str(end_time), machine_name, diff_time.seconds) basic.outputlogMessage(out_str) with open("time_cost.txt", 'a') as t_obj: t_obj.writelines(out_str + '\n')
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 calculate_polygon_topography(polygons_shp, para_file, dem_files, slope_files, aspect_files=None, dem_diffs=None): """ calculate the topography information such elevation and slope of each polygon Args: polygons_shp: input shapfe file dem_files: DEM raster file or tiles, should have the same projection of shapefile slope_files: slope raster file or tiles (can be drived from dem file by using QGIS or ArcGIS) aspect_files: aspect raster file or tiles (can be drived from dem file by using QGIS or ArcGIS) Returns: True if successful, False Otherwise """ if io_function.is_file_exist(polygons_shp) is False: return False operation_obj = shape_opeation() ## calculate the topography information from the buffer area # the para file was set in parameters.set_saved_parafile_path(options.para_file) b_use_buffer_area = parameters.get_bool_parameters( para_file, 'b_topo_use_buffer_area') if b_use_buffer_area is True: b_buffer_size = 5 # meters (the same as the shape file) basic.outputlogMessage( "info: calculate the topography information from the buffer area") buffer_polygon_shp = io_function.get_name_by_adding_tail( polygons_shp, 'buffer') # if os.path.isfile(buffer_polygon_shp) is False: if vector_features.get_buffer_polygons( polygons_shp, buffer_polygon_shp, b_buffer_size) is False: basic.outputlogMessage( "error, failed in producing the buffer_polygon_shp") return False # else: # basic.outputlogMessage("warning, buffer_polygon_shp already exist, skip producing it") # replace the polygon shape file polygons_shp_backup = polygons_shp polygons_shp = buffer_polygon_shp else: basic.outputlogMessage( "info: calculate the topography information from the inside of each polygon" ) # all_touched: bool, optional # Whether to include every raster cell touched by a geometry, or only # those having a center point within the polygon. # defaults to `False` # Since the dem usually is coarser, so we set all_touched = True all_touched = True process_num = 4 # #DEM if dem_files is not None: stats_list = ['min', 'max', 'mean', 'median', 'std'] #['min', 'max', 'mean', 'count','median','std'] # if operation_obj.add_fields_from_raster(polygons_shp, dem_file, "dem", band=1,stats_list=stats_list,all_touched=all_touched) is False: # return False if zonal_stats_multiRasters(polygons_shp, dem_files, stats=stats_list, prefix='dem', band=1, all_touched=all_touched, process_num=process_num) is False: return False else: basic.outputlogMessage( "warning, DEM file not exist, skip the calculation of DEM information" ) # #slope if slope_files is not None: stats_list = ['min', 'max', 'mean', 'median', 'std'] if zonal_stats_multiRasters(polygons_shp, slope_files, stats=stats_list, prefix='slo', band=1, all_touched=all_touched, process_num=process_num) is False: return False else: basic.outputlogMessage( "warning, slope file not exist, skip the calculation of slope information" ) # #aspect if aspect_files is not None: stats_list = ['min', 'max', 'mean', 'std'] if zonal_stats_multiRasters(polygons_shp, aspect_files, stats=stats_list, prefix='asp', band=1, all_touched=all_touched, process_num=process_num) is False: return False else: basic.outputlogMessage( 'warning, aspect file not exist, ignore adding aspect information') # elevation difference if dem_diffs is not None: stats_list = ['min', 'max', 'mean', 'median', 'std', 'area'] # only count the pixel within this range when do statistics dem_diff_range_str = parameters.get_string_list_parameters( para_file, 'dem_difference_range') range = [ None if item.upper() == 'NONE' else float(item) for item in dem_diff_range_str ] # expand the polygon when doing dem difference statistics buffer_size_dem_diff = parameters.get_digit_parameters( para_file, 'buffer_size_dem_diff', 'float') if zonal_stats_multiRasters(polygons_shp, dem_diffs, stats=stats_list, prefix='demD', band=1, all_touched=all_touched, process_num=process_num, range=range, buffer=buffer_size_dem_diff) is False: return False else: basic.outputlogMessage( 'warning, dem difference file not exist, ignore adding dem diff information' ) # # hillshape # copy the topography information if b_use_buffer_area is True: operation_obj.add_fields_shape(polygons_shp_backup, buffer_polygon_shp, polygons_shp_backup) return True
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)
def run_evaluation(WORK_DIR, deeplab_dir, expr_name, para_file, network_setting_ini, gpu_num, train_dir=None): EXP_FOLDER = expr_name if train_dir is None: TRAIN_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'train') else: TRAIN_LOGDIR = train_dir EVAL_LOGDIR = os.path.join(WORK_DIR, EXP_FOLDER, 'eval') dataset_dir = os.path.join(WORK_DIR, 'tfrecord') 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') b_initialize_last_layer = parameters.get_bool_parameters( para_file, 'b_initialize_last_layer') pre_trained_tar = parameters.get_string_parameters(network_setting_ini, 'TF_INIT_CKPT') # 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') 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 eval_interval_secs = 300 # gpuid = '' # do not use GPUs 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, eval_interval_secs=eval_interval_secs) # get miou again miou_dict = get_miou_list_class_all(EVAL_LOGDIR, num_of_classes)
def image_label_to_yolo_format(para_file): print("Image labels (semantic segmentation) to YOLO object detection") if os.path.isfile(para_file) is False: raise IOError('File %s not exists in current folder: %s' % (para_file, os.getcwd())) img_ext = parameters.get_string_parameters_None_if_absence( para_file, 'split_image_format') proc_num = parameters.get_digit_parameters(para_file, 'process_num', 'int') SECONDS = time.time() # get image and label path image_list = [] label_list = [] with open(os.path.join('list', 'trainval.txt'), 'r') as f_obj: lines = [item.strip() for item in f_obj.readlines()] for line in lines: image_list.append(os.path.join('split_images', line + img_ext)) label_list.append(os.path.join('split_labels', line + img_ext)) num_classes_noBG = parameters.get_digit_parameters_None_if_absence( para_file, 'NUM_CLASSES_noBG', 'int') b_ignore_edge_objects = parameters.get_bool_parameters_None_if_absence( para_file, 'b_ignore_edge_objects') if b_ignore_edge_objects is None: b_ignore_edge_objects = False # get boxes total_count = len(image_list) for idx, (img, label) in enumerate(zip(image_list, label_list)): get_yolo_boxes_one_img(idx, total_count, img, label, num_classes_noBG, rm_edge_obj=b_ignore_edge_objects) # write obj.data file train_sample_txt = parameters.get_string_parameters( para_file, 'training_sample_list_txt') val_sample_txt = parameters.get_string_parameters( para_file, 'validation_sample_list_txt') train_img_list = get_image_list('list', train_sample_txt, 'split_images', img_ext) val_img_list = get_image_list('list', val_sample_txt, 'split_images', img_ext) expr_name = parameters.get_string_parameters(para_file, 'expr_name') object_names = parameters.get_string_list_parameters( para_file, 'object_names') io_function.mkdir('data') io_function.mkdir(expr_name) with open(os.path.join('data', 'obj.data'), 'w') as f_obj: f_obj.writelines('classes = %d' % num_classes_noBG + '\n') train_txt = os.path.join('data', 'train.txt') io_function.save_list_to_txt(train_txt, train_img_list) f_obj.writelines('train = %s' % train_txt + '\n') val_txt = os.path.join('data', 'val.txt') io_function.save_list_to_txt(val_txt, val_img_list) f_obj.writelines('valid = %s' % val_txt + '\n') obj_name_txt = os.path.join('data', 'obj.names') io_function.save_list_to_txt(obj_name_txt, object_names) f_obj.writelines('names = %s' % obj_name_txt + '\n') f_obj.writelines('backup = %s' % expr_name + '\n') duration = time.time() - SECONDS os.system( 'echo "$(date): time cost of converting to yolo format: %.2f seconds">>time_cost.txt' % duration) pass
def mmseg_parallel_predict_main(para_file, trained_model): print( "MMSegmetation prediction using the trained model (run parallel if use multiple GPUs)" ) machine_name = os.uname()[1] start_time = datetime.now() if os.path.isfile(para_file) is False: raise IOError('File %s not exists in current folder: %s' % (para_file, os.getcwd())) expr_name = parameters.get_string_parameters(para_file, 'expr_name') # network_ini = parameters.get_string_parameters(para_file, 'network_setting_ini') # mmseg_repo_dir = parameters.get_directory(network_ini, 'mmseg_repo_dir') # mmseg_code_dir = osp.join(mmseg_repo_dir,'mmseg') # if os.path.isdir(mmseg_code_dir) is False: # raise ValueError('%s does not exist' % mmseg_code_dir) # # set PYTHONPATH to use my modified version of mmseg # if os.getenv('PYTHONPATH'): # os.environ['PYTHONPATH'] = os.getenv('PYTHONPATH') + ':' + mmseg_code_dir # else: # os.environ['PYTHONPATH'] = mmseg_code_dir # print('\nPYTHONPATH is: ',os.getenv('PYTHONPATH')) if trained_model is None: trained_model = os.path.join(expr_name, 'latest.pth') outdir = parameters.get_directory(para_file, 'inf_output_dir') # remove previous results (let user remove this folder manually or in exe.sh folder) io_function.mkdir(outdir) # get name of inference areas multi_inf_regions = parameters.get_string_list_parameters( para_file, 'inference_regions') b_use_multiGPUs = parameters.get_bool_parameters(para_file, 'b_use_multiGPUs') # loop each inference regions sub_tasks = [] for area_idx, area_ini in enumerate(multi_inf_regions): area_name = parameters.get_string_parameters(area_ini, 'area_name') area_remark = parameters.get_string_parameters(area_ini, 'area_remark') area_time = parameters.get_string_parameters(area_ini, 'area_time') inf_image_dir = parameters.get_directory(area_ini, 'inf_image_dir') # it is ok consider a file name as pattern and pass it the following functions to get file list inf_image_or_pattern = parameters.get_string_parameters( area_ini, 'inf_image_or_pattern') inf_img_list = io_function.get_file_list_by_pattern( inf_image_dir, inf_image_or_pattern) img_count = len(inf_img_list) if img_count < 1: raise ValueError( 'No image for inference, please check inf_image_dir and inf_image_or_pattern in %s' % area_ini) area_save_dir = os.path.join( outdir, area_name + '_' + area_remark + '_' + area_time) io_function.mkdir(area_save_dir) # parallel inference images for this area CUDA_VISIBLE_DEVICES = [] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys(): CUDA_VISIBLE_DEVICES = [ int(item.strip()) for item in os.environ['CUDA_VISIBLE_DEVICES'].split(',') ] idx = 0 while idx < img_count: if b_use_multiGPUs: # get available GPUs # https://github.com/anderskm/gputil # memory: orders the available GPU device ids by ascending memory usage deviceIDs = GPUtil.getAvailable(order='memory', limit=100, maxLoad=0.5, maxMemory=0.5, includeNan=False, excludeID=[], excludeUUID=[]) # only use the one in CUDA_VISIBLE_DEVICES if len(CUDA_VISIBLE_DEVICES) > 0: deviceIDs = [ item for item in deviceIDs if item in CUDA_VISIBLE_DEVICES ] basic.outputlogMessage('on ' + machine_name + ', available GPUs:' + str(deviceIDs) + ', among visible ones:' + str(CUDA_VISIBLE_DEVICES)) else: basic.outputlogMessage('on ' + machine_name + ', available GPUs:' + str(deviceIDs)) if len(deviceIDs) < 1: time.sleep( 60 ) # wait 60 seconds (mmseg need longer time to load models) , then check the available GPUs again continue # set only the first available visible gpuid = deviceIDs[0] basic.outputlogMessage( '%d: predict image %s on GPU %d of %s' % (idx, inf_img_list[idx], gpuid, machine_name)) else: gpuid = None basic.outputlogMessage('%d: predict image %s on %s' % (idx, inf_img_list[idx], machine_name)) # run inference img_save_dir = os.path.join(area_save_dir, 'I%d' % idx) inf_list_file = os.path.join(area_save_dir, '%d.txt' % idx) done_indicator = '%s_done' % inf_list_file if os.path.isfile(done_indicator): basic.outputlogMessage('warning, %s exist, skip prediction' % done_indicator) idx += 1 continue # if it already exist, then skip if os.path.isdir(img_save_dir) and is_file_exist_in_folder( img_save_dir): basic.outputlogMessage( 'folder of %dth image (%s) already exist, ' 'it has been predicted or is being predicted' % (idx, inf_img_list[idx])) idx += 1 continue with open(inf_list_file, 'w') as inf_obj: inf_obj.writelines(inf_img_list[idx] + '\n') sub_process = Process(target=predict_one_image_mmseg, args=(para_file, inf_img_list[idx], img_save_dir, inf_list_file, gpuid, trained_model)) sub_process.start() sub_tasks.append(sub_process) if b_use_multiGPUs is False: # wait until previous one finished while sub_process.is_alive(): time.sleep(1) idx += 1 # wait until predicted image patches exist or exceed 20 minutes time0 = time.time() elapsed_time = time.time() - time0 while elapsed_time < 20 * 60: elapsed_time = time.time() - time0 file_exist = os.path.isdir( img_save_dir) and is_file_exist_in_folder(img_save_dir) if file_exist is True or sub_process.is_alive() is False: break else: time.sleep(1) if sub_process.exitcode is not None and sub_process.exitcode != 0: sys.exit(1) basic.close_remove_completed_process(sub_tasks) # if 'chpc' in machine_name: # time.sleep(60) # wait 60 second on ITSC services # else: # time.sleep(10) # check all the tasks already finished wait_all_finish = 0 while basic.b_all_process_finish(sub_tasks) is False: if wait_all_finish % 100 == 0: basic.outputlogMessage('wait all tasks to finish') time.sleep(1) wait_all_finish += 1 basic.close_remove_completed_process(sub_tasks) end_time = datetime.now() diff_time = end_time - start_time out_str = "%s: time cost of total parallel inference on %s: %d seconds" % ( str(end_time), machine_name, diff_time.seconds) basic.outputlogMessage(out_str) with open("time_cost.txt", 'a') as t_obj: t_obj.writelines(out_str + '\n')
def image_translate_train_generate_main(para_file, gpu_num): ''' apply GAN to translate image from source domain to target domain existing sub-images (with sub-labels), these are image in source domain depend images for inference but no training data, each image for inference can be considered as on target domain ''' print(datetime.now(), "image translation (train and generate) using GAN") if os.path.isfile(para_file) is False: raise IOError('File %s not exists in current folder: %s' % (para_file, os.getcwd())) gan_para_file = parameters.get_string_parameters_None_if_absence( para_file, 'regions_n_setting_image_translation_ini') if gan_para_file is None: print( 'regions_n_setting_image_translation_ini is not set, skip image translation using GAN' ) return None gan_para_file = os.path.abspath( gan_para_file ) # change to absolute path, because later, we change folder training_regions = parameters.get_string_list_parameters( para_file, 'training_regions') machine_name = os.uname()[1] SECONDS = time.time() # get regions (equal to or subset of inference regions) need apply image translation multi_gan_regions = parameters.get_string_list_parameters( gan_para_file, 'regions_need_image_translation') multi_gan_source_regions = parameters.get_string_list_parameters( gan_para_file, 'source_domain_regions') # check target domain if len(multi_gan_source_regions) != len(multi_gan_regions): raise ValueError( 'the number of source domain and target domain is different') if set(multi_gan_source_regions).issubset(training_regions) is False: raise ValueError( 'the source domain regions are not the subset of training regions') for area_idx, (area_gan_ini, area_src_ini) in enumerate( zip(multi_gan_regions, multi_gan_source_regions)): basic.outputlogMessage('%d: source and target area: %s vs %s' % (area_idx, area_src_ini, area_gan_ini)) gan_working_dir = parameters.get_string_parameters(gan_para_file, 'working_root') # gan_dir_pre_name = parameters.get_string_parameters(gan_para_file, 'gan_dir_pre_name') # use GAN model name as the gan_dir_pre_name gan_model = parameters.get_string_parameters(gan_para_file, 'gan_model') gan_dir_pre_name = gan_model # '_' + # loop each regions need image translation sub_tasks = [] for area_idx, (area_gan_ini, area_src_ini) in enumerate( zip(multi_gan_regions, multi_gan_source_regions)): area_ini = os.path.abspath(area_gan_ini) area_src_ini = os.path.abspath(area_src_ini) area_name = parameters.get_string_parameters(area_ini, 'area_name') area_remark = parameters.get_string_parameters(area_ini, 'area_remark') area_time = parameters.get_string_parameters(area_ini, 'area_time') inf_image_dir = parameters.get_directory(area_ini, 'inf_image_dir') # it is ok consider a file name as pattern and pass it the following functions to get file list inf_image_or_pattern = parameters.get_string_parameters( area_ini, 'inf_image_or_pattern') inf_img_list = io_function.get_file_list_by_pattern( inf_image_dir, inf_image_or_pattern) img_count = len(inf_img_list) if img_count < 1: raise ValueError( 'No image for image translation, please check inf_image_dir and inf_image_or_pattern in %s' % area_ini) gan_project_save_dir = get_gan_project_save_dir( gan_working_dir, gan_dir_pre_name, area_name, area_remark, area_time, area_src_ini) if os.path.isdir(gan_project_save_dir): if generate_image_exists(gan_project_save_dir) is True: basic.outputlogMessage( 'generated new images (generate.txt_done) exist for %s exist, skip' % gan_project_save_dir) continue else: io_function.mkdir(gan_project_save_dir) # parallel run image translation for this area CUDA_VISIBLE_DEVICES = [] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys(): CUDA_VISIBLE_DEVICES = [ int(item.strip()) for item in os.environ['CUDA_VISIBLE_DEVICES'].split(',') ] # get an valid GPU gpuids = [] while len(gpuids) < 1: # get available GPUs # https://github.com/anderskm/gputil deviceIDs = GPUtil.getAvailable(order='first', limit=100, maxLoad=0.5, maxMemory=0.5, includeNan=False, excludeID=[], excludeUUID=[]) # only use the one in CUDA_VISIBLE_DEVICES if len(CUDA_VISIBLE_DEVICES) > 0: deviceIDs = [ item for item in deviceIDs if item in CUDA_VISIBLE_DEVICES ] basic.outputlogMessage('on ' + machine_name + ', available GPUs:' + str(deviceIDs) + ', among visible ones:' + str(CUDA_VISIBLE_DEVICES)) else: basic.outputlogMessage('on ' + machine_name + ', available GPUs:' + str(deviceIDs)) if len(deviceIDs) < 1: print(datetime.now(), 'No available GPUs, will check again in 60 seconds') time.sleep( 60) # wait one minute, then check the available GPUs again continue # set only the first available visible gpuids.append(deviceIDs[0]) basic.outputlogMessage( '%d:image translation for %s on GPU %s of %s' % (area_idx, area_ini, str(gpuids), machine_name)) # run image translation # pytorch consider first GPUs in CUDA_VISIBLE_DEVICES as zero, so need to re-index gpu ids if len(CUDA_VISIBLE_DEVICES) > 0: gpuids = [CUDA_VISIBLE_DEVICES.index(id) for id in gpuids] sub_process = Process(target=image_translate_train_generate_one_domain, args=(gan_project_save_dir, gan_para_file, area_src_ini, area_ini, gpuids, inf_img_list)) sub_process.start() sub_tasks.append(sub_process) # wait until image translation has started or exceed 20 minutes time0 = time.time() elapsed_time = time.time() - time0 while elapsed_time < 20 * 60: elapsed_time = time.time() - time0 if CUT_gan_is_ready_to_train( gan_project_save_dir) is True or sub_process.is_alive( ) is False: break else: time.sleep(5) time.sleep( 10 ) # wait, allowing time for the GAN process to start, and run into problem if sub_process.exitcode is not None and sub_process.exitcode != 0: sys.exit(1) basic.close_remove_completed_process(sub_tasks) # check all the tasks already finished while basic.b_all_process_finish(sub_tasks) is False: basic.outputlogMessage('wait all tasks to finish') time.sleep(60) basic.check_exitcode_of_process(sub_tasks) basic.close_remove_completed_process(sub_tasks) save_image_dir = parameters.get_string_parameters(para_file, 'input_train_dir') save_label_dir = parameters.get_string_parameters(para_file, 'input_label_dir') merge_subImages_from_gan(multi_gan_source_regions, multi_gan_regions, gan_working_dir, gan_dir_pre_name, save_image_dir, save_label_dir) duration = time.time() - SECONDS os.system( 'echo "$(date): time cost of translating sub images to target domains: %.2f seconds">>time_cost.txt' % duration)