tf.contrib.quantize.create_training_graph(input_graph=g, quant_delay=args.quant_delay) # optimizer = tf.train.RMSPropOptimizer(learning_rate, decay=0.0005, momentum=0.9, epsilon=1e-10) optimizer = tf.train.AdamOptimizer(learning_rate, epsilon=1e-8) # optimizer = tf.train.MomentumOptimizer(learning_rate, momentum=0.8, use_locking=True, use_nesterov=True) update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): train_op = optimizer.minimize(total_loss, global_step, colocate_gradients_with_ops=True) logger.info('define model-') # define summary tf.summary.scalar("loss", total_loss) tf.summary.scalar("loss_lastlayer", total_loss_ll) tf.summary.scalar("loss_lastlayer_paf", total_loss_ll_paf) tf.summary.scalar("loss_lastlayer_heat", total_loss_ll_heat) tf.summary.scalar("queue_size", enqueuer.size()) tf.summary.scalar("lr", learning_rate) merged_summary_op = tf.summary.merge_all() valid_loss = tf.placeholder(tf.float32, shape=[]) valid_loss_ll = tf.placeholder(tf.float32, shape=[]) valid_loss_ll_paf = tf.placeholder(tf.float32, shape=[]) valid_loss_ll_heat = tf.placeholder(tf.float32, shape=[]) sample_train = tf.placeholder(tf.float32, shape=(4, 640, 640, 3)) sample_valid = tf.placeholder(tf.float32, shape=(12, 640, 640, 3)) train_img = tf.summary.image('training sample', sample_train, 4) valid_img = tf.summary.image('validation sample', sample_valid, 12) valid_loss_t = tf.summary.scalar("loss_valid", valid_loss) valid_loss_ll_t = tf.summary.scalar("loss_valid_lastlayer", valid_loss_ll) merged_validate_op = tf.summary.merge([train_img, valid_img, valid_loss_t, valid_loss_ll_t])
quant_delay=args.quant_delay) # optimizer = tf.train.RMSPropOptimizer(learning_rate, decay=0.0005, momentum=0.9, epsilon=1e-10) optimizer = tf.compat.v1.train.AdamOptimizer(learning_rate, epsilon=1e-8) # optimizer = tf.train.MomentumOptimizer(learning_rate, momentum=0.8, use_locking=True, use_nesterov=True) update_ops = tf.compat.v1.get_collection(tf.compat.v1.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): train_op = optimizer.minimize(total_loss, global_step) logger.info('define model-') # define summary tf.compat.v1.summary.scalar("loss", total_loss) tf.compat.v1.summary.scalar("loss_lastlayer", total_loss_ll) tf.compat.v1.summary.scalar("loss_lastlayer_paf", total_loss_ll_paf) tf.compat.v1.summary.scalar("loss_lastlayer_heat", total_loss_ll_heat) tf.compat.v1.summary.scalar("queue_size", enqueuer.size()) tf.compat.v1.summary.scalar("lr", learning_rate) merged_summary_op = tf.compat.v1.summary.merge_all() valid_loss = tf.compat.v1.placeholder(tf.float32, shape=[]) valid_loss_ll = tf.compat.v1.placeholder(tf.float32, shape=[]) valid_loss_ll_paf = tf.compat.v1.placeholder(tf.float32, shape=[]) valid_loss_ll_heat = tf.compat.v1.placeholder(tf.float32, shape=[]) sample_train = tf.compat.v1.placeholder(tf.float32, shape=(4, 640, 640, 3)) sample_valid = tf.compat.v1.placeholder(tf.float32, shape=(12, 640, 640, 3)) train_img = tf.compat.v1.summary.image('training sample', sample_train, 4) valid_img = tf.compat.v1.summary.image('validation sample', sample_valid, 12) valid_loss_t = tf.compat.v1.summary.scalar("loss_valid", valid_loss) valid_loss_ll_t = tf.compat.v1.summary.scalar("loss_valid_lastlayer",
boundaries = [step_per_epoch * 5 * i for i, _ in range(len(lrs)) if i > 0] learning_rate = tf.train.piecewise_constant(global_step, boundaries, lrs) # optimizer = tf.train.RMSPropOptimizer(learning_rate, decay=0.0005, momentum=0.9, epsilon=1e-10) optimizer = tf.train.AdamOptimizer(learning_rate, epsilon=1e-8) update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): train_op = optimizer.minimize(total_loss, global_step, colocate_gradients_with_ops=True) logger.info('define model-') # define summary tf.summary.scalar("loss", total_loss) tf.summary.scalar("loss_lastlayer", total_loss_ll) tf.summary.scalar("loss_lastlayer_paf", total_loss_ll_paf) tf.summary.scalar("loss_lastlayer_heat", total_loss_ll_heat) tf.summary.scalar("queue_size", enqueuer.size()) merged_summary_op = tf.summary.merge_all() valid_loss = tf.placeholder(tf.float32, shape=[]) valid_loss_ll = tf.placeholder(tf.float32, shape=[]) valid_loss_ll_paf = tf.placeholder(tf.float32, shape=[]) valid_loss_ll_heat = tf.placeholder(tf.float32, shape=[]) sample_train = tf.placeholder(tf.float32, shape=(4, 640, 640, 3)) sample_valid = tf.placeholder(tf.float32, shape=(12, 640, 640, 3)) train_img = tf.summary.image('training sample', sample_train, 4) valid_img = tf.summary.image('validation sample', sample_valid, 12) valid_loss_t = tf.summary.scalar("loss_valid", valid_loss) valid_loss_ll_t = tf.summary.scalar("loss_valid_lastlayer", valid_loss_ll) merged_validate_op = tf.summary.merge([train_img, valid_img, valid_loss_t, valid_loss_ll_t]) saver = tf.train.Saver(max_to_keep=100)
boundaries = [step_per_epoch * 5 * i for i, _ in range(len(lrs)) if i > 0] learning_rate = tf.train.piecewise_constant(global_step, boundaries, lrs) # optimizer = tf.train.RMSPropOptimizer(learning_rate, decay=0.0005, momentum=0.9, epsilon=1e-10) optimizer = tf.train.AdamOptimizer(learning_rate, epsilon=1e-8) update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): train_op = optimizer.minimize(total_loss, global_step, colocate_gradients_with_ops=True) logger.info('define model-') # define summary tf.summary.scalar("loss", total_loss) tf.summary.scalar("loss_lastlayer", total_loss_ll) tf.summary.scalar("loss_lastlayer_paf", total_loss_ll_paf) tf.summary.scalar("loss_lastlayer_heat", total_loss_ll_heat) tf.summary.scalar("queue_size", enqueuer.size()) merged_summary_op = tf.summary.merge_all() valid_loss = tf.placeholder(tf.float32, shape=[]) valid_loss_ll = tf.placeholder(tf.float32, shape=[]) valid_loss_ll_paf = tf.placeholder(tf.float32, shape=[]) valid_loss_ll_heat = tf.placeholder(tf.float32, shape=[]) sample_train = tf.placeholder(tf.float32, shape=(4, 640, 640, 3)) sample_valid = tf.placeholder(tf.float32, shape=(12, 640, 640, 3)) train_img = tf.summary.image('training sample', sample_train, 4) valid_img = tf.summary.image('validation sample', sample_valid, 12) valid_loss_t = tf.summary.scalar("loss_valid", valid_loss) valid_loss_ll_t = tf.summary.scalar("loss_valid_lastlayer", valid_loss_ll) merged_validate_op = tf.summary.merge([train_img, valid_img, valid_loss_t, valid_loss_ll_t]) saver = tf.train.Saver(max_to_keep=100)