def main(FLAGS): style_features_t = losses.get_style_features(FLAGS) # Make sure the training path exists. training_path = os.path.join(FLAGS.model_path, FLAGS.naming) if not(os.path.exists(training_path)): os.makedirs(training_path) with tf.Graph().as_default(): with tf.Session() as sess: """Build Network""" network_fn = nets_factory.get_network_fn( FLAGS.loss_model, num_classes=1, is_training=False) image_preprocessing_fn, image_unprocessing_fn = preprocessing_factory.get_preprocessing( FLAGS.loss_model, is_training=False) processed_images = reader.image(FLAGS.batch_size, FLAGS.image_size, FLAGS.image_size, 'train2014/', image_preprocessing_fn, epochs=FLAGS.epoch) generated = model.net(processed_images, training=True) processed_generated = [image_preprocessing_fn(image, FLAGS.image_size, FLAGS.image_size) for image in tf.unstack(generated, axis=0, num=FLAGS.batch_size) ] processed_generated = tf.stack(processed_generated) _, endpoints_dict = network_fn(tf.concat([processed_generated, processed_images], 0), spatial_squeeze=False) # Log the structure of loss network tf.logging.info('Loss network layers(You can define them in "content_layers" and "style_layers"):') for key in endpoints_dict: tf.logging.info(key) """Build Losses""" content_loss = losses.content_loss(endpoints_dict, FLAGS.content_layers) style_loss, style_loss_summary = losses.style_loss(endpoints_dict, style_features_t, FLAGS.style_layers) tv_loss = losses.total_variation_loss(generated) # use the unprocessed image loss = FLAGS.style_weight * style_loss + FLAGS.content_weight * content_loss + FLAGS.tv_weight * tv_loss # Add Summary for visualization in tensorboard. """Add Summary""" tf.summary.scalar('losses/content_loss', content_loss) tf.summary.scalar('losses/style_loss', style_loss) tf.summary.scalar('losses/regularizer_loss', tv_loss) tf.summary.scalar('weighted_losses/weighted_content_loss', content_loss * FLAGS.content_weight) tf.summary.scalar('weighted_losses/weighted_style_loss', style_loss * FLAGS.style_weight) tf.summary.scalar('weighted_losses/weighted_regularizer_loss', tv_loss * FLAGS.tv_weight) tf.summary.scalar('total_loss', loss) for layer in FLAGS.style_layers: tf.summary.scalar('style_losses/' + layer, style_loss_summary[layer]) tf.summary.image('generated', generated) # tf.image_summary('processed_generated', processed_generated) # May be better? tf.summary.image('origin', tf.stack([ image_unprocessing_fn(image) for image in tf.unstack(processed_images, axis=0, num=FLAGS.batch_size) ])) summary = tf.summary.merge_all() writer = tf.summary.FileWriter(training_path) """Prepare to Train""" global_step = tf.Variable(0, name="global_step", trainable=False) variable_to_train = [] for variable in tf.trainable_variables(): if not(variable.name.startswith(FLAGS.loss_model)): variable_to_train.append(variable) train_op = tf.train.AdamOptimizer(1e-3).minimize(loss, global_step=global_step, var_list=variable_to_train) variables_to_restore = [] for v in tf.global_variables(): if not(v.name.startswith(FLAGS.loss_model)): variables_to_restore.append(v) saver = tf.train.Saver(variables_to_restore, write_version=tf.train.SaverDef.V1) sess.run([tf.global_variables_initializer(), tf.local_variables_initializer()]) # Restore variables for loss network. init_func = utils._get_init_fn(FLAGS) init_func(sess) # Restore variables for training model if the checkpoint file exists. last_file = tf.train.latest_checkpoint(training_path) if last_file: tf.logging.info('Restoring model from {}'.format(last_file)) saver.restore(sess, last_file) """Start Training""" coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(coord=coord) start_time = time.time() try: while not coord.should_stop(): _, loss_t, step = sess.run([train_op, loss, global_step]) elapsed_time = time.time() - start_time start_time = time.time() """logging""" # print(step) if step % 10 == 0: tf.logging.info('step: %d, total Loss %f, secs/step: %f' % (step, loss_t, elapsed_time)) """summary""" if step % 25 == 0: tf.logging.info('adding summary...') summary_str = sess.run(summary) writer.add_summary(summary_str, step) writer.flush() """checkpoint""" if step % 1000 == 0: saver.save(sess, os.path.join(training_path, 'fast-style-model.ckpt'), global_step=step) except tf.errors.OutOfRangeError: saver.save(sess, os.path.join(training_path, 'fast-style-model.ckpt-done')) tf.logging.info('Done training -- epoch limit reached') finally: coord.request_stop() coord.join(threads)
def main(FLAGS): # 得到风格特征 style_features_t = losses.get_style_features(FLAGS) # Make sure the training path exists. training_path = os.path.join(FLAGS.model_path, FLAGS.naming) if not (os.path.exists(training_path)): os.makedirs(training_path) with tf.Graph().as_default(): with tf.Session() as sess: """Build Network""" # 构造vgg网络,按照FLAGS.loss_model中的网络名字,可以在/nets/nets_factory.py 中的networks_map找到对应 network_fn = nets_factory.get_network_fn(FLAGS.loss_model, num_classes=1, is_training=False) # 根据不同网络做不同的预处理 image_preprocessing_fn, image_unprocessing_fn = preprocessing_factory.get_preprocessing( FLAGS.loss_model, is_training=False) # 读取一个批次的数据,并且预处理 # 这里的数据你可以不用coco,可以直接给一个包含很多图片的文件夹即可 # 因为coco过于大 processed_images = reader.image(FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 'F:/CASIA/train_frame/real/', image_preprocessing_fn, epochs=FLAGS.epoch) # 通过生成网络,生成图片,相当于y^ generated = model.net(processed_images, training=True) # 因为一会要把生成图片喂入到后面vgg进行计算两个损失,所以要先进行预处理 processed_generated = [ image_preprocessing_fn(image, FLAGS.image_height, FLAGS.image_width) for image in tf.unstack(generated, axis=0, num=FLAGS.batch_size) ] # 因为上面是list格式,所以用tf.stack堆叠成tensor processed_generated = tf.stack(processed_generated) # 按照batch那一个维度,拼起来,比如原来两个是[batch_size,h,w,c],concat后变为[2*batch_size,h,w,c] # 这样一次前向传播把y^ 和y_c的特征都计算出来了 _, endpoints_dict = network_fn(tf.concat( [processed_generated, processed_images], 0), spatial_squeeze=False) # Log the structure of loss network tf.logging.info( 'Loss network layers(You can define them in "content_layers" and "style_layers"):' ) for key in endpoints_dict: tf.logging.info(key) """Build Losses""" # 计算三个损失 content_loss = losses.content_loss(endpoints_dict, FLAGS.content_layers) style_loss, style_loss_summary = losses.style_loss( endpoints_dict, style_features_t, FLAGS.style_layers) tv_loss = losses.total_variation_loss( generated) # use the unprocessed image loss = FLAGS.style_weight * style_loss + FLAGS.content_weight * content_loss + FLAGS.tv_weight * tv_loss # Add Summary for visualization in tensorboard. """Add Summary""" # 为了tensorboard,可以忽略 tf.summary.scalar('losses/content_loss', content_loss) tf.summary.scalar('losses/style_loss', style_loss) tf.summary.scalar('losses/regularizer_loss', tv_loss) tf.summary.scalar('weighted_losses/weighted_content_loss', content_loss * FLAGS.content_weight) tf.summary.scalar('weighted_losses/weighted_style_loss', style_loss * FLAGS.style_weight) tf.summary.scalar('weighted_losses/weighted_regularizer_loss', tv_loss * FLAGS.tv_weight) tf.summary.scalar('total_loss', loss) for layer in FLAGS.style_layers: tf.summary.scalar('style_losses/' + layer, style_loss_summary[layer]) tf.summary.image('generated', generated) # tf.image_summary('processed_generated', processed_generated) # May be better? tf.summary.image( 'origin', tf.stack([ image_unprocessing_fn(image) for image in tf.unstack( processed_images, axis=0, num=FLAGS.batch_size) ])) summary = tf.summary.merge_all() writer = tf.summary.FileWriter(training_path) """Prepare to Train""" # 步数 global_step = tf.Variable(0, name="global_step", trainable=False) variable_to_train = [] for variable in tf.trainable_variables(): # 把非vgg网络里面的可训练变量加入variable_to_train if not (variable.name.startswith(FLAGS.loss_model)): variable_to_train.append(variable) # 注意var_list train_op = tf.train.AdamOptimizer(1e-3).minimize( loss, global_step=global_step, var_list=variable_to_train) variables_to_restore = [] for v in tf.global_variables(): # 把非vgg中的可存储变量加入variables_to_restore if not (v.name.startswith(FLAGS.loss_model)): variables_to_restore.append(v) # 注意variables_to_restore saver = tf.train.Saver(variables_to_restore, write_version=tf.train.SaverDef.V1) sess.run([ tf.global_variables_initializer(), tf.local_variables_initializer() ]) # Restore variables for loss network. # slim的,可以根据FLAGS里面配置把网络参数加载到sess这个会话里面 init_func = utils._get_init_fn(FLAGS) init_func(sess) # Restore variables for training model if the checkpoint file exists. last_file = tf.train.latest_checkpoint(training_path) if last_file: tf.logging.info('Restoring model from {}'.format(last_file)) saver.restore(sess, last_file) """Start Training""" coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(coord=coord) start_time = time.time() try: while not coord.should_stop(): _, loss_t, step = sess.run([train_op, loss, global_step]) elapsed_time = time.time() - start_time start_time = time.time() """logging""" print(step) if step % 10 == 0: tf.logging.info( 'step: %d, total Loss %f, secs/step: %f' % (step, loss_t, elapsed_time)) """summary""" if step % 25 == 0: tf.logging.info('adding summary...') summary_str = sess.run(summary) writer.add_summary(summary_str, step) writer.flush() """checkpoint""" if step % 1000 == 0: saver.save(sess, os.path.join(training_path, 'fast-style-model.ckpt'), global_step=step) except tf.errors.OutOfRangeError: saver.save( sess, os.path.join(training_path, 'fast-style-model.ckpt-done')) tf.logging.info('Done training -- epoch limit reached') finally: coord.request_stop() coord.join(threads)
def main(argv=None): content_layers = FLAGS.content_layers.split(',') style_layers = FLAGS.style_layers.split(',') style_layers_weights = [ float(i) for i in FLAGS.style_layers_weights.split(",") ] #num_steps_decay = 82786 / FLAGS.batch_size num_steps_decay = 10000 style_features_t = losses.get_style_features(FLAGS) training_path = os.path.join(FLAGS.model_path, FLAGS.naming) if not (os.path.exists(training_path)): os.makedirs(training_path) with tf.Session() as sess: """Build Network""" network_fn = nets_factory.get_network_fn(FLAGS.loss_model, num_classes=1, is_training=False) image_preprocessing_fn, image_unprocessing_fn = preprocessing_factory.get_preprocessing( FLAGS.loss_model, is_training=False) processed_images = reader.image(FLAGS.batch_size, FLAGS.image_size, FLAGS.image_size, 'train2014/', image_preprocessing_fn, epochs=FLAGS.epoch) generated = model.net(processed_images, FLAGS.alpha) processed_generated = [ image_preprocessing_fn(image, FLAGS.image_size, FLAGS.image_size) for image in tf.unstack(generated, axis=0, num=FLAGS.batch_size) ] processed_generated = tf.stack(processed_generated) _, endpoints_dict = network_fn(tf.concat( [processed_generated, processed_images], 0), spatial_squeeze=False) """Build Losses""" content_loss = losses.content_loss(endpoints_dict, content_layers) style_loss, style_losses = losses.style_loss(endpoints_dict, style_features_t, style_layers, style_layers_weights) tv_loss = losses.total_variation_loss( generated) # use the unprocessed image content_loss = FLAGS.content_weight * content_loss style_loss = FLAGS.style_weight * style_loss tv_loss = FLAGS.tv_weight * tv_loss loss = style_loss + content_loss + tv_loss """Prepare to Train""" global_step = tf.Variable(0, name="global_step", trainable=False) variable_to_train = [] for variable in tf.trainable_variables(): if not (variable.name.startswith(FLAGS.loss_model)): variable_to_train.append(variable) lr = tf.train.exponential_decay(learning_rate=1e-1, global_step=global_step, decay_steps=num_steps_decay, decay_rate=1e-1, staircase=True) optimizer = tf.train.AdamOptimizer(learning_rate=lr, epsilon=1e-8) train_op = optimizer.minimize(loss, global_step=global_step, var_list=variable_to_train) #train_op = tf.train.AdamOptimizer(1e-3).minimize(loss, global_step=global_step, var_list=variable_to_train) variables_to_restore = [] for v in tf.global_variables(): if not (v.name.startswith(FLAGS.loss_model)): variables_to_restore.append(v) saver = tf.train.Saver(variables_to_restore) sess.run([ tf.global_variables_initializer(), tf.local_variables_initializer() ]) init_func = utils._get_init_fn(FLAGS) init_func(sess) last_file = tf.train.latest_checkpoint(training_path) if last_file: saver.restore(sess, last_file) """Start Training""" coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(coord=coord) try: while not coord.should_stop(): _, c_loss, s_losses, t_loss, total_loss, step = sess.run([ train_op, content_loss, style_losses, tv_loss, loss, global_step ]) """logging""" if step % 10 == 0: print(step, c_loss, s_losses, t_loss, total_loss) """checkpoint""" if step % 10000 == 0: saver.save(sess, os.path.join(training_path, 'fast-style-model'), global_step=step) if step == FLAGS.max_iter: saver.save( sess, os.path.join(training_path, 'fast-style-model-done')) break except tf.errors.OutOfRangeError: saver.save(sess, os.path.join(training_path, 'fast-style-model-done')) tf.logging.info('Done training -- epoch limit reached') finally: coord.request_stop() coord.join(threads)
def main(FLAGS): style_features_t = losses.get_style_features(FLAGS) #style target的Gram #make sure the training path exists training_path = os.path.join(FLAGS.model_path,FLAGS.naming) #model/wave/ ;用于存放训练好的模型 if not (os.path.exists(training_path)): os.makedirs(training_path) with tf.Graph().as_default(): #默认计算图 with tf.Session() as sess:#没有as_default(),因此,走出with 语句,sess停止执行,不能在被用 """build loss network""" network_fn =nets_factory.get_network_fn(FLAGS.loss_model,num_classes=1,is_training=False) #取出loss model,且该model不用训练 #对要进入loss_model的content_image,和generated_image进行preprocessing image_preprocessing_fn,image_unpreprocessing_fn = preprocessing_factory.get_preprocessing(FLAGS.loss_model,is_training=False) #取出用于loss_model的,对image进行preprocessing和unpreprocessing的function processed_image = reader.image(FLAGS.batch_size,FLAGS.image_size,FLAGS.image_size,'train2014/',image_preprocessing_fn,epochs=FLAGS.epoch) #这里要preprocessing的image是一个batch,为training_data generated = model.net(processed_images,training=True) #输入“图像生成网络”的image为经过preprocessing_image,“图像生成网络”为要训练的网络 processed_generated = [image_preprocessing_fn(image,FLAGS.image_size,FLAGS.image_size) for image in tf.unstack(generated,axis=0,num=FLAGS.batch_size)] processed_generated = tf.stack(processed_generated) #计算generated_image和content_image进入loss_model后,更layer的output _,endpoints_dict= network_fn(tf.concat([processed_generated,processed_images],0),spatial_squeeze=False)#endpoints_dict中存储的是2类image各个layer的值 #log the structure of loss network tf.logging.info('loss network layers(you can define them in "content layer" and "style layer"):') for key in endpoints_dict: tf.logging.info(key) #屏幕输出loss_model的各个layer name """build losses""" content_loss = losses.content_loss(endpoints_dict,FLAGS.content_layers) style_loss,style_loss_summary = losses.style_loss(endpoints_dict,style_features_t,FLAGS.style_layers) tv_loss = losses.total_variation_loss(generated) loss = FLAGS.style_weight * style_loss + FLAGS.content_weight * content_loss + FLAGS.tv_weight * tv_loss # Add Summary for visualization in tensorboard """Add Summary""" tf.summary.scalar('losses/content_loss',content_loss) tf.summary.scalar('losses/style_loss',style_loss) tf.summary.scalar('losses/regularizer_loss',tv_loss) tf.summary.scalar('weighted_losses/weighted content_loss',content_loss * FLAGS.content_weight) tf.summary.scalar('weighted_losses/weighted style_loss',style_loss * FLAGS.style_weight) tf.summary.scalar('weighted_losses/weighted_regularizer_loss',tv_loss * FLAGS.tv_weight) tf.summary.scalar('total_loss',loss) for layer in FLAGS.style_layers: tf.summary.scalar('style_losses/' + layer,style_loss_summary[layer]) tf.summary.image('genearted',generated) tf.summary.image('origin',tf.stack([image_unprocessing_fn(image) for image in tf.unstack(processed_images,axis=0,num=FLAGS.batch_size)])) summary = tf.summary.merge_all() writer = tf.summary.FileWriter(training_path) """prepare to train""" global_step = tf.Variable(0,name='global_step',trainable=False)#iteration step variable_to_train = []#需要训练的变量 for variable in tf.trainable_variables():#在图像风格迁移网络(图像生成网络+损失网络)各参数中,找需要训练的参数 if not (variable.name.startswith(FLAGS.loss_model)): variable_to_train.append(variable) train_op = tf.train.AdamOptimizer(1e-3).minimize(loss,global_step = global_step,var_list = variable_to_train) #需要放入sess.run() variable_to_restore = []#在所有的全局变量中,找需要恢复默认设置的变量; 注意:local_variable指的是一些临时变量和中间变量,用于线程中,线程结束则消失 for v tf.global_variables(): if not (v.name.startswith(FLAGS.loss_model)): variables_to_restore.append(v) saver = tf.train.Saver(variables_to_restore,write_version=tf.train.SaverDef.V1)#利用saver.restore()恢复默认设置;这里的variable_to_restore,是需要save and restore的var_list sess.run([tf.global_variables_initializer(),tf.local_variables_initializer()])#对全局变量和局部变量进行初始化操作:即恢复默认设置 #restore variables for loss model 恢复loss model中的参数 init_func = utils._get_init_fn(FLAGS) init_func(sess) #restore variables for training model if the checkpoint file exists. 如果training_model已有训练好的参数,将其载入 last_file = tf.train.latest_checkpoint(training_path)#将train_path中的model参数数据取出 if last_file: tf.logging.info('restoringmodel from {}'.format(last_file)) saver.restore(sess,last_file) #那如果last_file不存在,就不执行restore操作吗?需要restore的参数只是图像生成网络吗? """start training""" coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(coord=coord) start_time = time.time() try: while not coord.should_stop():#查看线程是否停止(即:是否所有数据均运行完毕) _,loss_t,step = sess.run([train_op,loss,global_step]) elapsed_time = time.time() """logging""" #print(step) if step % 10 == 0: tf.logging.info('step:%d, total loss %f, secs/step: %f' % (step,loss_t,elapsed_time)) """summary""" if step % 25 == 0: tf.logging.info('adding summary...') summary_str = sess.run(summary) writer.add_summary(summary_str,step) writer.flush() """checkpoint""" if step % 1000 == 0: saver.save(sess,os.path.join(training_path,'fast-style-model.ckpt'),global_step=step)#保存variable_to_restore中的参数值 except tf.errors.OutOfRangeError: saver.save(sess,os.path.join(training_path,'fast-style-model.ckpt-done')) tf.logging.info('Done training -- epoch limit reached') finally: coord.request_stop()#要求停止所有线程 coord.join(threads)#将线程并入主线程,删除
def main(FLAGS): style_features_t = losses.get_style_features(FLAGS) training_path = os.path.join(FLAGS.model_path, FLAGS.naming) if not (os.path.exists(training_path)): os.makedirs(training_path) with tf.Graph().as_default(): with tf.Session() as sess: """创建Network""" network_fn = nets_factory.get_network_fn( FLAGS.loss_model, num_classes=1, is_training=False) image_preprocessing_fn, image_unprocessing_fn = preprocessing_factory.get_preprocessing( FLAGS.loss_model, is_training=False) """训练图片预处理""" processed_images = reader.batch_image(FLAGS.batch_size, FLAGS.image_size, FLAGS.image_size, 'train2014/', image_preprocessing_fn, epochs=FLAGS.epoch) generated = model.transform_network(processed_images, training=True) processed_generated = [image_preprocessing_fn(image, FLAGS.image_size, FLAGS.image_size) for image in tf.unstack(generated, axis=0, num=FLAGS.batch_size) ] processed_generated = tf.stack(processed_generated) _, endpoints_dict = network_fn(tf.concat([processed_generated, processed_images], 0), spatial_squeeze=False) tf.logging.info('Loss network layers(You can define them in "content_layers" and "style_layers"):') for key in endpoints_dict: tf.logging.info(key) """创建 Losses""" content_loss = losses.content_loss(endpoints_dict, FLAGS.content_layers) style_loss, style_loss_summary = losses.style_loss(endpoints_dict, style_features_t, FLAGS.style_layers) tv_loss = losses.total_variation_loss(generated) # use the unprocessed image loss = FLAGS.style_weight * style_loss + FLAGS.content_weight * content_loss + FLAGS.tv_weight * tv_loss """准备训练""" global_step = tf.Variable(0, name="global_step", trainable=False) variable_to_train = [] for variable in tf.trainable_variables(): # 只训练和保存生成网络中的变量 if not (variable.name.startswith(FLAGS.loss_model)): variable_to_train.append(variable) """优化""" train_op = tf.train.AdamOptimizer(1e-3).minimize(loss, global_step=global_step, var_list=variable_to_train) variables_to_restore = [] for v in tf.global_variables(): if not (v.name.startswith(FLAGS.loss_model)): variables_to_restore.append(v) saver = tf.train.Saver(variables_to_restore, write_version=tf.train.SaverDef.V1) sess.run([tf.global_variables_initializer(), tf.local_variables_initializer()]) init_func = utils._get_init_fn(FLAGS) init_func(sess) last_file = tf.train.latest_checkpoint(training_path) if last_file: tf.logging.info('Restoring model from {}'.format(last_file)) saver.restore(sess, last_file) """开始训练""" coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(coord=coord) start_time = time.time() try: while not coord.should_stop(): _, loss_t, step = sess.run([train_op, loss, global_step]) elapsed_time = time.time() - start_time start_time = time.time() if step % 10 == 0: tf.logging.info( 'step: %d, total Loss %f, secs/step: %f,%s' % (step, loss_t, elapsed_time, time.asctime())) """checkpoint""" if step % 50 == 0: tf.logging.info('saving check point...') saver.save(sess, os.path.join(training_path, FLAGS.naming + '.ckpt'), global_step=step) except tf.errors.OutOfRangeError: saver.save(sess, os.path.join(training_path, 'fast-style-model.ckpt-done')) tf.logging.info('Done training -- epoch limit reached') finally: coord.request_stop() tf.logging.info('coordinator stop') coord.join(threads)