Question

我正在尝试将RGB图像从模拟器传递到我的自定义神经网络中。在RGB生成（模拟器）的来源处，RGB图像的尺寸为(3,144,256)。

这是我构建神经网络的方式：

rgb_model = Sequential()
rgb = env.shape() // this is (3, 144, 256)
rgb_shape = (1,) + rgb
rgb_model.add(Conv2D(96, (11, 11), strides=(3, 3), padding='valid', activation='relu', input_shape=rgb_shape, data_format = "channels_first"))
Now, my rbg_shape is (1, 3, 144, 256).

这是我得到的错误：

rgb_model.add(Conv2D(96, (11, 11), strides=(3, 3), padding='valid', activation='relu', input_shape=rgb_kshape, data_format = "channels_first"))
File "/usr/local/lib/python2.7/dist-packages/keras/engine/sequential.py", line 166, in add
layer(x)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/base_layer.py", line 414, in call
self.assert_input_compatibility(inputs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/base_layer.py", line 311, in assert_input_compatibility
str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer conv2d_1: expected ndim=4, found ndim=5

为什么我的实际尺寸为4时，keras抱怨预期尺寸为5？

P.S：我有与this问题相同的问题。理想情况下，我想评论该帖子，但信誉不高。

编辑：

以下是处理错误的代码：

rgb_shape = env.rgb.shape
rgb_model = Sequential()
rgb_model.add(Conv2D(96, (11, 11), strides=(3, 3), padding='valid', activation='relu', input_shape=rgb_shape, data_format = "channels_first"))
rgb_model.add(Conv2D(128, (3, 3), strides=(2, 2), padding='valid', activation='relu', data_format = "channels_first" ))
rgb_model.add(Conv2D(384, (3, 3), strides=(1, 1), padding='valid', activation='relu', data_format = "channels_first"))
rgb_model.add(Conv2D(384, (3, 3), strides=(1,1), padding='valid', activation='relu', data_format = "channels_first"))
rgb_model.add(Conv2D(256, (3,3), strides=(1,1), padding='valid', activation='relu', data_format = "channels_first"))
rgb_model.add(Flatten())
rgb_input = Input(shape=rgb_shape)
rgb = rgb_model(rgb_input)

这是我在env.rgb.shape中以input_shape身份通过Conv2D时的新错误：

dqn.fit(env, callbacks=callbacks, nb_steps=250000, visualize=False, verbose=0, log_interval=100)
  File "/usr/local/lib/python2.7/dist-packages/rl/core.py", line 169, in fit
    action = self.forward(observation)
  File "/usr/local/lib/python2.7/dist-packages/rl/agents/dqn.py", line 228, in forward
    q_values = self.compute_q_values(state)
  File "/usr/local/lib/python2.7/dist-packages/rl/agents/dqn.py", line 69, in compute_q_values
    q_values = self.compute_batch_q_values([state]).flatten()
  File "/usr/local/lib/python2.7/dist-packages/rl/agents/dqn.py", line 64, in compute_batch_q_values
    q_values = self.model.predict_on_batch(batch)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1276, in predict_on_batch
    x, _, _ = self._standardize_user_data(x)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 754, in _standardize_user_data
    exception_prefix='input')
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training_utils.py", line 126, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking input: expected input_1 to have 4 dimensions, but got array with shape (1, 1, 3, 144, 256)

Answer 1

Conv2D图层的输入形状为(num_channels, width, height)。因此，您不应添加其他尺寸（实际上，输入形状为(batch_size, num_channels, width, height)，但无需在此处设置batch_size；它将通过fit方法进行设置）。只需将input_shape=env.shape传递给Conv2D，就可以正常工作。

编辑：

为什么要定义Input层并将其传递给模型？那不是它的工作原理。首先，您需要使用compile方法编译模型，然后使用fit方法在训练数据上训练模型，然后使用predict方法进行预测。我强烈建议您阅读official guide，以了解这些工作原理。

ValueError：输入0与层conv2d_1不兼容：预期ndim = 4，找到的ndim = 5

1 个答案: