def log_run_start(run_type, hyper_dict, version_description):
"""
Log the start info of a neural network run
"""
dl_data = (DATASET_NAME, run_type)
return log.dl_run_start(DL_RUN, DL_NETWORK, DL_MODEL_FILE_PATH, dl_data, \
hyper_dict, version_description)
dl_network = 'Lenet'
dl_model_file_path = 'tf_lenet.py'
dl_data = ('TF_MNIST', 'Train')
dl_environment = 'Default'
hyper_dict = { 'epochs' : EPOCHS, 'batch size' : BATCH_SIZE, 'learning rate' : \
LEARNING_RATE }
# Train the model
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
num_examples = len(X_train)
print("Training...")
run_id = log.dl_run_start(dl_run, dl_network, dl_model_file_path, dl_data, hyper_dict)
print()
for i in range(EPOCHS):
X_train, y_train = shuffle(X_train, y_train)
for offset in range(0, num_examples, BATCH_SIZE):
end = offset + BATCH_SIZE
batch_x, batch_y = X_train[offset:end], y_train[offset:end]
sess.run(training_operation, feed_dict={x: batch_x, y: batch_y})
validation_accuracy = evaluate(X_validation, y_validation)
print("EPOCH {} ...".format(i+1))
print("Validation Accuracy = {:.3f}".format(validation_accuracy))
print()
saver.save(sess, 'lenet')
