无法为具有形状“(?, 1)”的 Tensor 'Placeholder_1:0' 提供形状 (10, 1, 1, 1) 的值

Cannot feed value of shape (10, 1, 1, 1) for Tensor 'Placeholder_1:0', which has shape '(?, 1)'

我使用 tensorflow 构建了一个基于 CNN 的 oin RGB 图像,其大小为 224*172。这是我建立的网络:

def deepnn(x):
  """deepnn builds the graph for a deep net for classifying digits.

  Args:
    x: an input tensor with the dimensions (N_examples, 784), where 784 is the
    number of pixels in a standard MNIST image.

  Returns:
    A tuple (y, keep_prob). y is a tensor of shape (N_examples, 10), with values
    equal to the logits of classifying the digit into one of 10 classes (the
    digits 0-9). keep_prob is a scalar placeholder for the probability of
    dropout.
  """
  # Reshape to use within a convolutional neural net.
  # Last dimension is for "features" - there is only one here, since images are
  # grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
  depth = 3
  with tf.name_scope('reshape'):
    x_image = tf.reshape(x, [-1, 224, 172, depth])

  # First convolutional layer - maps one grayscale image to 32 feature maps.
  with tf.name_scope('conv1'):
    W_conv1 = weight_variable([5, 5, depth, 32])
    b_conv1 = bias_variable([32])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

  # Pooling layer - downsamples by 2X.
  with tf.name_scope('pool1'):
    h_pool1 = max_pool_2x2(h_conv1)

  # Second convolutional layer -- maps 32 feature maps to 64.
  with tf.name_scope('conv2'):
    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)

  # Second pooling layer.
  with tf.name_scope('pool2'):
    h_pool2 = max_pool_2x2(h_conv2)

  # Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
  # is down to 7x7x64 feature maps -- maps this to 1024 features.
  with tf.name_scope('fc1'):
    # W_fc1 = weight_variable([7 * 7 * 64, 1024])
    W_fc1 = weight_variable([56 * 42 * 64, 1024])

    b_fc1 = bias_variable([1024])

    h_pool2_flat = tf.reshape(h_pool2, [-1, 56 * 42 * 64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

  # Dropout - controls the complexity of the model, prevents co-adaptation of
  # features.
  with tf.name_scope('dropout'):
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

  # Map the 1024 features to 10 classes, one for each digit
  with tf.name_scope('fc2'):
    W_fc2 = weight_variable([1024, 1])
    b_fc2 = bias_variable([1])

    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
  return y_conv, keep_prob


def conv2d(x, W):
  """conv2d returns a 2d convolution layer with full stride."""
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


def max_pool_2x2(x):
  """max_pool_2x2 downsamples a feature map by 2X."""
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')


def weight_variable(shape):
  """weight_variable generates a weight variable of a given shape."""
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)


def bias_variable(shape):
  """bias_variable generates a bias variable of a given shape."""
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)


def main(_):
  # Import data
  V0Dataset = dr.read_data_sets(FLAGS.data_dir, one_hot=True)

  # Create the model
  x = tf.placeholder(tf.float32, [None, 224*172*3])

  # Define loss and optimizer
  y_ = tf.placeholder(tf.float32, [None, 1])

  # Build the graph for the deep net
  y_conv, keep_prob = deepnn(x)

当我尝试训练我的网络时出现错误:

Cannot feed value of shape (10, 1, 1, 1) for Tensor 'Placeholder_1:0', which has shape '(?, 1)'

我认为我的结构存在问题,或者更可能是我的数据集存在问题。

那部分代码出现问题:

 with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(100):
      batch = V0Dataset.train.next_batch(10)
      train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5}) ##### error

编辑:这是我所做修改的更新。

with tf.name_scope('reshape'):
    x_image = tf.reshape(x, [-1, 224, 172, 1])#(x, [-1, 28, 28, 1])

  # First convolutional layer - maps one grayscale image to 32 feature maps.
  with tf.name_scope('conv1'):
    W_conv1 = weight_variable([5, 5, 1, 32])#([5, 5, 1, 32])
    b_conv1 = bias_variable([32])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

  # Pooling layer - downsamples by 2X.
  with tf.name_scope('pool1'):
    h_pool1 = max_pool_2x2(h_conv1)

  # Second convolutional layer -- maps 32 feature maps to 64.
  with tf.name_scope('conv2'):
    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)

  # Second pooling layer.
  with tf.name_scope('pool2'):
    h_pool2 = max_pool_2x2(h_conv2)

  # Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
  # is down to 7x7x64 feature maps -- maps this to 1024 features.
  with tf.name_scope('fc1'):
    W_fc1 = weight_variable([28 * 43 * 64, 1024])
    b_fc1 = bias_variable([1024])

    h_pool2_flat = tf.reshape(h_pool2, [-1, 28*43*64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

  # Dropout - controls the complexity of the model, prevents co-adaptation of
  # features.
  with tf.name_scope('dropout'):
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

  # Map the 1024 features to 10 classes, one for each digit
  with tf.name_scope('fc2'):
    W_fc2 = weight_variable([1024, 2])
    b_fc2 = bias_variable([2])

    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
  return y_conv, keep_prob


def conv2d(x, W):
  """conv2d returns a 2d convolution layer with full stride."""
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


def max_pool_2x2(x):
  """max_pool_2x2 downsamples a feature map by 2X."""
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')


def weight_variable(shape):
  """weight_variable generates a weight variable of a given shape."""
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)


def bias_variable(shape):
  """bias_variable generates a bias variable of a given shape."""
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)


def main(_):
  # Import data
  V0Dataset = dr.read_data_sets(FLAGS.data_dir, one_hot=True)

  # Create the model
  x = tf.placeholder(tf.float32, [None, 224*172])

  # Define loss and optimizer
  y_ = tf.placeholder(tf.float32, [None, 2])
  print("logits shape {}".format(y_))


  # Build the graph for the deep net
  y_conv, keep_prob = deepnn(x)



  with tf.name_scope('loss'):
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,
                                                            logits=y_conv)
  cross_entropy = tf.reduce_mean(cross_entropy)

  with tf.name_scope('adam_optimizer'):
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

  with tf.name_scope('accuracy'):
    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
    correct_prediction = tf.cast(correct_prediction, tf.float32)

  accuracy = tf.reduce_mean(correct_prediction)

  graph_location = tempfile.mkdtemp()
  print('Saving graph to: %s' % graph_location)
  train_writer = tf.summary.FileWriter("/tmp/tensorflow/")
  train_writer.add_graph(tf.get_default_graph())


  with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(100):
      batch = V0Dataset.train.next_batch(10)
      # print("----size0 {}".format(batch[0]))
      # print("----size1 {}".format(batch[1]))
      # print("----size2 {}".format(len(batch[0][0])))
      # print("batch {}".format(batch))
    #   if i % 100 == 0:
    #     train_accuracy = accuracy.eval(feed_dict={
    #         x: batch[0], y_: batch[1], keep_prob: 1.0})
    #     print('step %d, training accuracy %g' % (i, train_accuracy))
      # print("batch {}".format(batch[1]))
      # batch1 = batch[1].reshape(20,2)
      # print("batch {}".format(batch1))
      a =  batch[1];
      a = a.reshape(10,2)
      train_step.run(feed_dict={x: batch[0], y_: a, keep_prob: 0.5})

    # print('test accuracy %g' % accuracy.eval(feed_dict={
    #     x: V0Dataset.test.images, y_: V0Dataset.test.labels, keep_prob: 1.0}))

if __name__ == '__main__':
  parser = argparse.ArgumentParser()
  parser.add_argument('--data_dir', type=str,
                      default='/tmp/tensorflow/mnist/input_data',
                      help='Directory for storing input data')
  FLAGS, unparsed = parser.parse_known_args()
  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

我得到的错误是:

logits shape Tensor("Placeholder_1:0", shape=(?, 2), dtype=float32)
Saving graph to: /tmp/tmptzko8so7
2018-01-16 17:03:23.257533: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
start 0  batch_size 10
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1323, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1302, in _run_fn
    status, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits and labels must be same size: logits_size=[20,2] labels_size=[10,2]
     [[Node: loss/SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](loss/Reshape, loss/Reshape_1)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "deep_charging_station_train.py", line 238, in <module>
    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "deep_charging_station_train.py", line 227, in main
    train_step.run(feed_dict={x: batch[0], y_: a, keep_prob: 0.5})
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2042, in run
    _run_using_default_session(self, feed_dict, self.graph, session)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 4490, in _run_using_default_session
    session.run(operation, feed_dict)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 889, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1120, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1317, in _do_run
    options, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1336, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits and labels must be same size: logits_size=[20,2] labels_size=[10,2]
     [[Node: loss/SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](loss/Reshape, loss/Reshape_1)]]

Caused by op 'loss/SoftmaxCrossEntropyWithLogits', defined at:
  File "deep_charging_station_train.py", line 238, in <module>
    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "deep_charging_station_train.py", line 192, in main
    logits=y_conv)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_ops.py", line 1783, in softmax_cross_entropy_with_logits
    precise_logits, labels, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 4364, in _softmax_cross_entropy_with_logits
    name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[20,2] labels_size=[10,2]
     [[Node: loss/SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](loss/Reshape, loss/Reshape_1)]]

编辑:

我找到了解决办法。显然,输入尺寸必须具有相同的宽度和高度。我输入 width=height=100 现在可以了。

错误是因为您输入占位符 y_ 的张量不匹配。

V0Dataset = dr.read_data_sets(FLAGS.data_dir, one_hot=True)

在上面的行中,您启用了 one_hot 编码,因此如果您正在进行多 class class 化,那么在执行 batch = V0Dataset.train.next_batch(10) 之后,您将获得一个列表批量 [1].

中的大小“1 x class_size

例如,如果您正在进行 10 向 classification,那么在 next_batch() 调用之后 y_ 的输出将类似于 [1, 0, 0, 0, 0, 0 , 0, 0, 0, 0]表示这个输入属于第一个class。

所以修改这行代码y_ = tf.placeholder(tf.float32, [None, 1])。将此 1 替换为输出数量 classes.

看来你的标签形状不对。然后用 numpy 重塑。

labels =  np.reshape(batch[1],(10,1))