Conv2D.compute_output_shape() returns a shape while the layer failed to generate an output about keras HOT 2 OPEN

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
[<ipython-input-10-83efd0f3eb7a>](https://localhost:8080/#) in <cell line: 1>()
----> 1 l3(x3)

1 frames
[/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py](https://localhost:8080/#) in tf___jit_compiled_convolution_op(self, inputs, kernel)
     10                 try:
     11                     do_return = True
---> 12                     retval_ = ag__.converted_call(ag__.ld(self).convolution_op, (ag__.ld(inputs), ag__.ld(kernel)), None, fscope)
     13                 except:
     14                     do_return = False

ValueError: Exception encountered when calling layer 'conv3d_4' (type Conv3D).

in user code:

    File "/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py", line 277, in _jit_compiled_convolution_op  *
        return self.convolution_op(inputs, kernel)
    File "/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py", line 262, in convolution_op  **
        return tf.nn.convolution(

    ValueError: Negative dimension size caused by subtracting 2 from 1 for '{{node Conv3D}} = Conv3D[T=DT_FLOAT, data_format="NDHWC", dilations=[1, 1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1, 1]](Conv3D/SpaceToBatchND, kernel)' with input shapes: [72,2,2,1,4], [2,2,2,2,6].


Call arguments received by layer 'conv3d_4' (type Conv3D):
  • inputs=tf.Tensor(shape=(3, 4, 4, 4, 4), dtype=float32)