def optimize_cnn(hype_space):
"""Build a convolutional neural network and train it."""
try:
model, model_name, result, _ = build_and_train(hype_space, save_best_weights=True, log_for_tensorboard=True)
# Save training results to disks with unique filenames
h.save_json_result(model_name, result)
K.clear_session()
del model
return result
except Exception as err:
try:
K.clear_session()
except:
pass
err_str = str(err)
print(err_str)
traceback_str = str(traceback.format_exc())
print(traceback_str)
return {
'status': STATUS_FAIL,
'err': err_str,
'traceback': traceback_str
}
print("\n\n")
def optimize_cnn(hype_space):
"""Build a convolutional neural network and train it."""
if not is_gpu_available():
tf.logging.warning('GPUs are not available')
tf.logging.debug("Hyperspace: ", hype_space)
tf.logging.debug("\n")
try:
model, model_name, result, _ = build_and_train(
hype_space, log_for_tensorboard=True)
tf.logging.info("Training ended with success:")
tf.logging.info("Model name: %s", model_name)
# Save training results to disks with unique filenames
save_json_result(model_name, result)
export_model(model_name)
K.clear_session()
del model
tf.logging.info('before return result')
return result
except Exception as err:
err_str = str(err)
tf.logging.error(err_str)
traceback_str = str(traceback.format_exc())
tf.logging.error(traceback_str)
return {
'status': STATUS_FAIL,
'err': err_str,
'traceback': traceback_str
}
def optimize_cnn(hype_space):
"""Build a convolutional neural network and train it."""
if not is_gpu_available():
tf.logging.warning('GPUs are not available')
tf.logging.debug("Hyperspace: ", hype_space)
tf.logging.debug("\n")
try:
model, model_name, result, _ = build_and_train(hype_space)
tf.logging.info("Training ended with success:")
tf.logging.info("Model name: ", model_name)
# Save training results to disks with unique filenames
# TODO do we need this? this save to json on disc not to mongo. Not sure if we want always save to disc
save_json_result(model_name, result)
K.clear_session()
del model
tf.logging.info('before return result')
return result
except Exception as err:
try:
K.clear_session()
except:
pass
err_str = str(err)
tf.logging.error(err_str)
traceback_str = str(traceback.format_exc())
tf.logging.error(traceback_str)
return {
'status': STATUS_FAIL,
'err': err_str,
'traceback': traceback_str
}
def optimize_cnn(hype_space):
"""Build a convolutional neural network and train it."""
try:
model, model_name, result, model_uuid = build_and_train(
hype_space, save_best_weights=True)
# Save training results to disks with unique filenames
save_json_result(model_name, result)
# Save .png plot of the model according to its hyper-parameters
plot(result['space'], model_uuid)
K.clear_session()
del model
return result
except Exception as err:
try:
K.clear_session()
except:
pass
err_str = str(err)
print(err_str)
traceback_str = str(traceback.format_exc())
print(traceback_str)
print("\n\n")
return {
'status': STATUS_FAIL,
'err': err_str,
'traceback': traceback_str
}
from keras.layers.core import K
import os
__author__ = "Vooban Inc."
__copyright__ = "Copyright 2017, Vooban Inc."
__license__ = "MIT License"
# See: https://github.com/Vooban/Hyperopt-Keras-CNN-CIFAR-100/blob/master/LICENSE"
if __name__ == "__main__":
"""Retrain best model with TensorBoard. Also save best weights."""
space_best_model = load_best_hyperspace()
print("Hyperspace:")
print_json(space_best_model)
model, model_name, results, log_path = build_and_train(
space_best_model, save_best_weights=True, log_for_tensorboard=True)
print("Model Name:", model_name)
print("Note: results 'json' file not saved to 'results/' since it is now "
"available in TensorBoard. See above console output for json-styled "
"results.")
print("Model summary:")
model.summary()
print("TensorBoard logs directory:", log_path)
print("You may now want to run this command to launch TensorBoard:\n"
"tensorboard --logdir={}".format(TENSORBOARD_DIR))