if not os.path.exists(test_file):
create_data4add(test_file, n_test, digit_max=99)
for training_mode in [True, False]: # training & testing
for batch_size in [1, 10, 100]:
tf.reset_default_graph() # Clears the default graph stack and resets the global default graph.
log.info('')
log.info('training_mode: %s, batch_size: %s, total_train_time: %s secs' % (training_mode, batch_size, total_train_time))
model_name = os.path.basename(__file__).replace('.py', '')
model_file = os.path.join(SAMPLE_MODELS_DIR, '%s.n_train_%s.batch_size_%s.total_train_time_%s/model' % (model_name, n_train, batch_size, total_train_time))
model_dir = os.path.dirname(model_file)
log.info('model_name: %s' % model_name)
log.info('model_file: %s' % model_file)
scope_name = '%s.%s.batch_size_%s.total_train_time_%s' % (model_name, DateUtil.current_yyyymmdd_hhmm(), batch_size, total_train_time)
log.info('scope_name: %s' % scope_name)
with tf.device('/gpu:0'):
with tf.Graph().as_default(): # for reusing graph
checkpoint = tf.train.get_checkpoint_state(model_dir)
is_training = True if training_mode or not checkpoint else False # learning or testing
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
with tf.Session(config=config) as sess:
train_pipeline = input_pipeline([train_file], batch_size=batch_size, shuffle=True, delim='\t', splits=3)
valid_pipeline = input_pipeline([valid_file], batch_size=n_valid, shuffle=True, delim='\t', splits=3)
test_pipeline = input_pipeline([test_file], batch_size=n_test, shuffle=True, delim='\t', splits=3)
if is_training: # training
x, y, learning_rate, W1, b1, y_hat, cost, train_step, summary = create_graph(model_name, scope_name, verbose=False)
log.info('')
log.info(
'training_mode: %s, batch_size: %s, total_train_time: %s secs'
% (training_mode, batch_size, total_train_time))
model_name = os.path.basename(__file__).replace('.py', '')
model_file = os.path.join(
MODELS_DIR,
'%s.n_train_%s.batch_size_%s.total_train_time_%s/model' %
(model_name, n_train, batch_size, total_train_time))
model_dir = os.path.dirname(model_file)
log.info('model_name: %s' % model_name)
log.info('model_file: %s' % model_file)
scope_name = '%s.%s.batch_size_%s.total_train_time_%s' % (
model_name, DateUtil.current_yyyymmdd_hhmm(), batch_size,
total_train_time)
log.info('scope_name: %s' % scope_name)
with tf.device('/gpu:0'):
with tf.Graph().as_default(): # for reusing graph
checkpoint = tf.train.get_checkpoint_state(model_dir)
is_training = True if training_mode or not checkpoint else False # learning or testing
config = tf.ConfigProto(gpu_options=tf.GPUOptions(
allow_growth=True, visible_device_list='0'))
with tf.Session(config=config) as sess:
train_pipeline = input_pipeline([train_file],
batch_size=batch_size,
shuffle=True,
delim='\t',