def train_and_validate(init_learning_rate_log, weight_decay_log):
tf.reset_default_graph()
graph = tf.get_default_graph()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
hp_d['init_learning_rate'] = 10**init_learning_rate_log
hp_d['weight_decay'] = 10**weight_decay_log
model = ConvNet([227, 227, 3], 2, **hp_d)
evaluator = Evaluator()
optimizer = Optimizer(model, train_set, evaluator, val_set=val_set, **hp_d)
sess = tf.Session(graph=graph, config=config)
train_results = optimizer.train(sess, details=True, verbose=True, **hp_d)
# Return the maximum validation score as target
best_val_score = np.max(train_results['eval_scores'])
return best_val_score
""" 2. Set training hyperparameters """ hp_d = dict() # FIXME: Training hyperparameters hp_d['batch_size'] = 128 hp_d['num_epochs'] = 1800 hp_d['augment_train'] = True hp_d['init_learning_rate'] = 0.2 hp_d['momentum'] = 0.9 # FIXME: Regularization hyperparameters hp_d['weight_decay'] = 0.0001 hp_d['dropout_prob'] = 0.0 # FIXME: Evaluation hyperparameters hp_d['score_threshold'] = 1e-4 """ 3. Build graph, initialize a session and start training """ # Initialize graph = tf.get_default_graph() config = tf.ConfigProto() config.gpu_options.allow_growth = True model = ConvNet([32, 32, 3], 10, **hp_d) evaluator = Evaluator() optimizer = Optimizer(model, train_set, evaluator, val_set=val_set, **hp_d) sess = tf.Session(graph=graph, config=config) train_results = optimizer.train(sess, details=True, verbose=True, **hp_d)
# FIXME: Regularization hyperparameters hp_d['weight_decay'] = 0.0005 hp_d['dropout_prob'] = 0.8 # FIXME: Evaluation hyperparameters hp_d['score_threshold'] = 1e-4 old_v = tf.logging.get_verbosity() tf.logging.set_verbosity(tf.logging.ERROR) """ 3. Build graph, initialize a session and start training """ # Initialize graph = tf.get_default_graph() config = tf.ConfigProto() config.gpu_options.allow_growth = True model = ConvNet([28, 28, 1], 10, **hp_d) evaluator = Evaluator() train_set = dataset.DataSet(train_images, train_labels) test_set = dataset.DataSet(test_images, test_labels) # train_set = tf.data.Dataset.from_tensor_slices((train_images, train_labels)).shuffle(buffer_size=1000000).batch(hp_d['batch_size']) # test_set = tf.data.Dataset.from_tensor_slices((test_images, test_labels)).batch(hp_d['batch_size']) optimizer = Optimizer(model, train_set, evaluator, test_set=test_set, **hp_d) sess = tf.Session(graph=graph, config=config) train_results = optimizer.train(sess, details=True, verbose=True, **hp_d)