help="test on old and augmented test datasets")
parser.add_argument('--finetune', default=False, type=lambda x: (str(x).lower() in ['true','1', 'yes']), \
help="finetune mode")
parser.add_argument('--use_kfac', default=False, type=lambda x: (str(x).lower() in ['true','1', 'yes']), \
help="usek fac true gradient")
parser.add_argument('--log', default='',
help="test log postfix")
if __name__ == '__main__':
# Set the random seed for the whole graph
tf.set_random_seed(230)
# Load the parameters
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
params.dict['loss_fn'] = args.loss_fn
params.dict['collect'] = False
params.dict['use_kfac'] = args.use_kfac
params.dict['finetune'] = args.finetune
params.dict['training_keep_prob'] = 1.0
# Load the parameters from the dataset, that gives the size etc. into params
json_path = os.path.join(args.data_dir, 'dataset_params.json')
assert os.path.isfile(json_path), "No json file found at {}, run build.py".format(json_path)
params.update(json_path)
# Set the logger
set_logger(os.path.join(args.model_dir, 'test{}.log'.format(args.log)))
# # Get paths for tfrecords
dataset = 'test'
if args.combine:
params.dict['test_size'] = params.dict['test_size'] * 2
# usage: python main.py --restore_dir experiments/base_model/best_weights
parser.add_argument(
'--restore_dir',
default=None, # experimens/base_model/best_weights
help="Optional, directory containing weights to reload")
if __name__ == '__main__':
tf.reset_default_graph()
# Set the random seed for the whole graph for reproductible experiments
tf.set_random_seed(230)
# Load the parameters from the experiment params.json file in model_dir
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# print('params.mlp_sizes\n', params.mlp_sizes)
# print('params.top_ks\n', params.top_ks)
if params.mlp_sizes is None or len(params.mlp_sizes) == 0:
logging.error(
'mlp_sizes are not set correctly, at least one MLP layer is required'
)
params.dict['loss_fn'] = args.loss_fn
# # Load the parameters from the dataset, that gives the size etc. into params
json_path = os.path.join(args.data_dir, 'dataset_params.json')
assert os.path.isfile(
json_path
), "No json file found at {}, please run prepare_data.py".format(json_path)
params.update(json_path)
# Set the logger
default='data/mnist',
help="Directory containing the dataset")
parser.add_argument('--sprite_filename',
default='experiments/mnist_10k_sprite.png',
help="Sprite image for the projector")
if __name__ == '__main__':
tf.reset_default_graph()
tf.logging.set_verbosity(tf.logging.INFO)
# Load the parameters from json file
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# Define the model
tf.logging.info("Creating the model...")
config = tf.estimator.RunConfig(
tf_random_seed=230,
model_dir=args.model_dir,
save_summary_steps=params.save_summary_steps)
estimator = tf.estimator.Estimator(model_fn, params=params, config=config)
# EMBEDDINGS VISUALIZATION
# Compute embeddings on the test set
tf.logging.info("Predicting")
predictions = estimator.predict(
lambda: test_input_fn(args.data_dir, params))
parser.add_argument('--restore_dir', default=None,
help="Optional, directory containing weights to reload before training")
if __name__ == '__main__':
args = parser.parse_args()
args.model_dir = os.path.join("experiments", args.data_dir, args.model_dir)
if args.restore_dir is not None:
args.restore_dir = os.path.join("experiments", args.data_dir, args.restore_dir)
args.data_dir = os.path.join("data", args.data_dir)
print(args)
if not os.path.isdir(args.model_dir):
os.makedirs(args.model_dir)
# Load the parameters from the experiment params.json file in model_dir
params = Params('params.json')
# Load the parameters from the dataset, that gives the size etc. into params
json_path = os.path.join(args.data_dir, 'dataset_params.json')
assert os.path.isfile(json_path), "No json file found at {}, run build_vocab.py".format(json_path)
params.update(json_path)
# Set the random seed for the whole graph for reproductible experiments
tf.set_random_seed(params.seed)
# Save the params in model_dir
json_path = os.path.join(args.model_dir, 'params.json')
params.save(json_path)
num_oov_buckets = params.num_oov_buckets # number of buckets for unknown words
# Check that we are not overwriting some previous experiment
help="usek fac true gradient")
parser.add_argument('--log', default='',
help="train log postfix")
if __name__ == '__main__':
# Train the model
tf.reset_default_graph()
# Set the random seed for the whole graph for reproductible experiments
tf.set_random_seed(230)
# Load the parameters from the experiment params.json file in model_dir
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(json_path), "No json configuration file found at {}".format(json_path)
# Set the logger
set_logger(os.path.join(args.model_dir, 'collect{}.log'.format(args.log)))
params = Params(json_path)
params.dict['loss_fn'] = args.loss_fn
params.dict['collect'] = True
params.dict['finetune'] = args.finetune
params.dict['use_kfac'] = args.use_kfac
# Load the parameters from the dataset, that gives the size etc. into params
json_path = os.path.join(args.data_dir, 'dataset_params.json')
assert os.path.isfile(json_path), "No json file found at {}, \
please generate tfrecords".format(json_path)
params.update(json_path)
global_epoch = 0
args.restore_dir = 'best_weights'
path_train_tfrecords = os.path.join(args.data_dir, 'train-{}'.format(args.train_range) + args.tfrecords_filename)
path_sample_train_tfrecords = os.path.join(args.data_dir, 'sample' + args.tfrecords_filename)
training_files = glob.glob(path_train_tfrecords)
if args.train_range == '[0-4]':
# Write parameters in json file
json_path = os.path.join(model_dir, 'params.json')
params.save(json_path)
# Launch training with this config
cmd = "{python} train.py --model_dir {model_dir} --data_dir {data_dir}".format(python=PYTHON,
model_dir=model_dir, data_dir=data_dir)
print(cmd)
check_call(cmd, shell=True)
if __name__ == "__main__":
# Load the "reference" parameters from parent_dir json file
args = parser.parse_args()
json_path = os.path.join(args.parent_dir, 'params.json')
assert os.path.isfile(json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# Perform hypersearch over one parameter
learning_rates = [1e-4, 1e-3, 1e-2]
for learning_rate in learning_rates:
# Modify the relevant parameter in params
params.learning_rate = learning_rate
# Launch job (name has to be unique)
job_name = "learning_rate_{}".format(learning_rate)
launch_training_job(args.parent_dir, args.data_dir, job_name, params)
parser.add_argument(
'--restore_from',
default=None,
help=
"Optional, directory or file containing weights to reload before training")
if __name__ == '__main__':
# Set the random seed for the whole graph for reproductible experiments
tf.set_random_seed(0)
# Load the parameters from json file
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# Check that we are not overwriting some previous experiment
# Comment these lines if you are developing your model and don't care about overwritting
model_dir_has_best_weights = os.path.isdir(
os.path.join(args.model_dir, "best_weights"))
overwritting = model_dir_has_best_weights and args.restore_from is None
assert not overwritting, "Weights found in model_dir, aborting to avoid overwrite"
# Set the logger
set_logger(os.path.join(args.model_dir, 'train.log'))
# Create the input data pipeline
logging.info("Creating the datasets...")
data_dir = args.data_dir
train_data_dir = os.path.join(data_dir, "train")
help="Directory containing the dataset")
parser.add_argument(
'--restore_from',
default='best_weights',
help="Subdirectory of model dir or file containing the weights")
if __name__ == '__main__':
# Set the random seed for the whole graph
tf.set_random_seed(230)
# Load the parameters
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# Load the parameters from the dataset, that gives the size etc. into params
json_path = os.path.join(args.data_dir, 'dataset_params.json')
assert os.path.isfile(
json_path), "No json file found at {}, run build.py".format(json_path)
params.update(json_path)
# Set the logger
set_logger(os.path.join(args.model_dir, 'evaluate.log'))
# Get paths for vocabularies and dataset
path_eval_x = os.path.join(args.data_dir, 'dev.x')
path_eval_y = os.path.join(args.data_dir, 'dev.y')
# Create the input data pipeline
