Conv2D input shape is 4D（batch_size, rows, cols, depth）while this work input shape is 5D (batch_size, target_seq_len, rows, cols, depth)

[katieliao]

Hello, I was trying to run this code. However, when I was trying to train the model, an error occur:

Input 0 of layer conv2d is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: [8, 5, 40, 40, 1]

8 is batch size, 5 is target sequence length, 40x40 is rows x cols and 1 is depth.

I just checked the source code and found that in "encoding" and "decoding" step, we have to run conv2d function, which requires a 4D input [batch size, rows, cols, channels]

How to tackle this problem?

[iamrakesh28]

Hi, Can you tell me which file you were trying run? I have defined some main functions inside datasets/.

[Aditya-1202]

Can you share the mnist_reshaped dataset?

[iamrakesh28]

Download the mnist dataset and use the generator to generate data of your dimension. You can refer the generator here: https://github.com/iamrakesh28/Deep-Learning-for-Weather-and-Climate-Science/tree/master/Moving-MNIST

On the top of file, you can specify the reshaped rows and cols dimension.