__author__ = 'Chong Guo <*****@*****.**>' __copyright__ = 'Copyright 2018, Chong Guo' __license__ = 'GPL' import numpy as np import tensorflow as tf from matplotlib import pyplot as plt from config import batch_size, display_step, saving_step, summary_path, testing_summary from common import init_model from image_helper import concat_images if __name__ == '__main__': # Init model is_training, _, _, loss, predict_rgb, color_image_rgb, gray_image, file_paths = init_model(train=False) # Init scaffold, hooks and config scaffold = tf.train.Scaffold() checkpoint_hook = tf.train.CheckpointSaverHook(checkpoint_dir=summary_path, save_steps=saving_step, scaffold=scaffold) config = tf.ConfigProto(allow_soft_placement=True, log_device_placement=True, gpu_options=(tf.GPUOptions(allow_growth=True))) session_creator = tf.train.ChiefSessionCreator(scaffold=scaffold, config=config, checkpoint_dir=summary_path) # Create a session for running operations in the Graph with tf.train.MonitoredSession(session_creator=session_creator, hooks=[checkpoint_hook]) as sess: print("🤖 Start testing...") step = 0 avg_loss = 0 while not sess.should_stop(): step += 1
"""Train model.""" import numpy as np import tensorflow as tf from matplotlib import pyplot as plt from config import display_step, summary_path, saving_step, testing_step, training_iters, training_summary from common import init_model from image_helper import concat_images if __name__ == '__main__': # Init model is_training, global_step, optimizer, loss, predict_rgb, color_image_rgb, gray_image, _ = init_model(train=True) # Init scaffold, hooks and config scaffold = tf.train.Scaffold() summary_hook = tf.train.SummarySaverHook(output_dir=training_summary, save_steps=display_step, scaffold=scaffold) checkpoint_hook = tf.train.CheckpointSaverHook(checkpoint_dir=summary_path, save_steps=saving_step, scaffold=scaffold) num_step_hook = tf.train.StopAtStepHook(num_steps=training_iters) config = tf.ConfigProto(allow_soft_placement=True, log_device_placement=True, gpu_options=(tf.GPUOptions(allow_growth=True))) # Create a session for running operations in the Graph with tf.train.MonitoredTrainingSession(checkpoint_dir=summary_path,hooks=[summary_hook, checkpoint_hook, num_step_hook],scaffold=scaffold,config=config) as sess: print("🤖 Start training...") while not sess.should_stop(): # Run optimizer _, step, l, pred, color, gray = sess.run([optimizer, global_step, loss, predict_rgb, color_image_rgb, gray_image] , feed_dict={is_training: True})
""" Training model """ import sys import numpy as np from matplotlib import pyplot as plt from config import * from common import init_model from image_helper import (concat_images) if __name__ == '__main__': # Init model is_training, global_step, uv, optimizer, cost, predict, predict_rgb, color_image_rgb, gray_image_rgb, file_paths = init_model( train=True) # Saver print "Init model saver" saver = tf.train.Saver() # Init the graph print "Init graph" init = tf.initialize_all_variables() # Create a session for running operations in the Graph with tf.Session() as sess: # Initialize the variables. sess.run(init) # Merge all summaries
import common parser = argparse.ArgumentParser() parser.add_argument("--input-path") parser.add_argument("--model-dir-path") args = parser.parse_args() training_data = common.read_data(args.input_path) dictionary, reverse_dictionary = common.build_dataset(training_data, dict()) vocab_size = len(dictionary) # Parameters learning_rate = 0.001 n_input = 3 pred, x, y = common.init_model(dictionary, n_input) saver = tf.train.Saver() # Loss and optimizer cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y)) optimizer = tf.train.RMSPropOptimizer( learning_rate=learning_rate).minimize(cost) # Model evaluation correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # training_iters = 50000 training_iters = 1