Tensorflow培训和验证输入队列分隔

我试图使用TensorFlow复制完全卷积网络结果。我用Marvin Teichmann's implementation from github。我只需要写培训包装。我创建了两个共享变量和两个输入队列的图形，一个用于训练，一个用于验证。为了测试我的培训包装，我使用了两个简短的培训和验证文件列表，并且在每个培训时期后立即进行验证。我还从输入队列中打印出每个图像的形状，以检查是否得到正确的输入。但是，在我开始训练后，似乎只有训练队列中的图像正在排队。因此，训练和验证图都从训练队列中获取输入，并且验证队列从不被访问。任何人都可以帮助解释和解决这个问题？Tensorflow培训和验证输入队列分隔

下面是相关的代码的一部分：

def get_data(image_name_list, num_epochs, scope_name, num_class = NUM_CLASS): 
    with tf.variable_scope(scope_name) as scope: 
     images_path = [os.path.join(DATASET_DIR, i+'.jpg') for i in image_name_list] 
     gts_path = [os.path.join(GT_DIR, i+'.png') for i in image_name_list] 
     seed = random.randint(0, 2147483647) 
     image_name_queue = tf.train.string_input_producer(images_path, num_epochs=num_epochs, shuffle=False, seed = seed) 
     gt_name_queue = tf.train.string_input_producer(gts_path, num_epochs=num_epochs, shuffle=False, seed = seed) 
     reader = tf.WholeFileReader() 
     image_key, image_value = reader.read(image_name_queue) 
     my_image = tf.image.decode_jpeg(image_value) 
     my_image = tf.cast(my_image, tf.float32) 
     my_image = tf.expand_dims(my_image, 0) 
     gt_key, gt_value = reader.read(gt_name_queue) 
     # gt stands for ground truth 
     my_gt = tf.cast(tf.image.decode_png(gt_value, channels = 1), tf.float32) 
     my_gt = tf.one_hot(tf.cast(my_gt, tf.int32), NUM_CLASS) 
     return my_image, my_gt 

train_image, train_gt = get_data(train_files, NUM_EPOCH, 'training') 
val_image, val_gt = get_data(val_files, NUM_EPOCH, 'validation') 
with tf.variable_scope('FCN16') as scope: 
     train_vgg16_fcn = fcn16_vgg.FCN16VGG() 
     train_vgg16_fcn.build(train_image, train=True, num_classes=NUM_CLASS, keep_prob = KEEP_PROB) 
     scope.reuse_variables() 
     val_vgg16_fcn = fcn16_vgg.FCN16VGG() 
     val_vgg16_fcn.build(val_image, train=False, num_classes=NUM_CLASS, keep_prob = 1) 
""" 
Define the loss, evaluation metric, summary, saver in the computation graph. Initialize variables and start a session. 
""" 
for epoch in range(starting_epoch, NUM_EPOCH): 
    for i in range(train_num): 
     _, loss_value, shape = sess.run([train_op, train_entropy_loss, tf.shape(train_image)]) 
     print shape 
    for i in range(val_num): 
     loss_value, shape = sess.run([val_entropy_loss, tf.shape(val_image)]) 
     print shape

来源

2016-08-24 Ruizhi Deng

您是否找到答案？ – thigi

我没有一个好的答案，但建议在单独的过程中运行评估。它更容易和更清洁。如果您不想这样做，您可以创建两个不同的图表和会话，并将您的验证输入队列与此关联起来。 –

要确保你正在阅读不同的图像，你可以运行：

[train_image_np, val_image_np] = sess.run([train_image, val_image])

要重复使用的变量，这是更好，更安全：

with tf.variable_scope('FCN16') as scope: 
    train_vgg16_fcn = fcn16_vgg.FCN16VGG() 
    train_vgg16_fcn.build(train_image, train=True, num_classes=NUM_CLASS, keep_prob = KEEP_PROB) 
with tf.variable_scope(scope, reuse=True): 
    val_vgg16_fcn = fcn16_vgg.FCN16VGG() 
    val_vgg16_fcn.build(val_image, train=False, num_classes=NUM_CLASS, keep_prob = 1)

来源

2017-05-20 06:07:19

Tensorflow培训和验证输入队列分隔

回答

相关问题