Keras：input_shape=train_data.shape 产生“列表索引超出范围”

我想使用 Keras 构建 CNN-LSTM 网络。但是，我很难找到第一层的正确形状input_shape范围。

My train_data是形状的 ndarray(1433, 32, 32); 1433 张尺寸为 32x32 的图片。

正如发现的这个例子 https://github.com/keras-team/keras/blob/master/examples/cifar10_cnn.py，我尝试使用input_shape=train_data.shape[1:]，这会导致与以下相同的错误input_shape=train_data.shape:

IndexError：列表索引超出范围

相关代码是：

train_data, train_labels = get_training_data()
# train_data = train_data.reshape(train_data.shape + (1,))
model = Sequential()
model.add(TimeDistributed(Conv2D(
      CONV_FILTER_SIZE[0],
      CONV_KERNEL_SIZE,
      activation="relu",
      padding="same"),
   input_shape=train_data.shape[1:]))

我发现这个错误的所有结果都是在不同的环境下产生的；不通过input_shape。那么我该如何调整我的输入呢？我是否必须在完全不同的地方寻找错误？

Update:完整错误：

Traceback (most recent call last):
File "trajecgen_keras.py", line 131, in <module>
    tf.app.run()
File "/home/.../lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 124, in run
    _sys.exit(main(argv))
File "trajecgen_keras.py", line 85, in main
    input_shape=train_data.shape))
File "/home/.../lib/python3.5/site-packages/keras/models.py", line 467, in add
    layer(x)
File "/home/.../lib/python3.5/site-packages/keras/engine/topology.py", line 619, in __call__
    output = self.call(inputs, **kwargs)
File "/home/.../lib/python3.5/site-packages/keras/layers/wrappers.py", line 211, in call
    y = self.layer.call(inputs, **kwargs)
File "/home/.../lib/python3.5/site-packages/keras/layers/convolutional.py", line 168, in call
    dilation_rate=self.dilation_rate)
File "/home/.../lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 3335, in conv2d
    data_format=tf_data_format)
File "/home/.../lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 753, in convolution
    name=name, data_format=data_format)
File "/home/.../lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 799, in __init__
    input_channels_dim = input_shape[num_spatial_dims + 1]
File "/home/../lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 521, in __getitem__
    return self._dims[key]
IndexError: list index out of range

当使用TimeDistributed层与Conv2D层，看来input_shape至少需要长度为 4 的元组：input_shape = (number_of_timesteps, height, width, number_of_channels).

您可以尝试像这样修改代码：

model = Sequential()
model.add(TimeDistributed(Conv2D(
      CONV_FILTER_SIZE[0],
      CONV_KERNEL_SIZE,
      activation="relu",
      padding="same"),
    input_shape=(None, 32, 32, 1))

更多信息here https://keras.io/layers/wrappers/.