Maxpool 2D layer error `Negative dimension size caused by subtracting 2 from 1 input shape shape=(128, 128, 1, 16)`

[shreya-ibind]

Im trying to convert tensorflow model to onnx.
I have attached my python file.

Error

       raise e.with_traceback(filtered_tb) from None

    ValueError: Exception encountered when calling layer 'max_pooling2d' (type MaxPooling2D).
    
    Negative dimension size caused by subtracting 2 from 1 for '{{node model/max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", explicit_paddings=[], ksize=[1, 2, 2, 1], padding="VALID", strides=[1, 2, 2, 1]](model/leaky_re_lu_1/LeakyRelu)' with input shapes: [128,128,1,16].
    
    Call arguments received by layer 'max_pooling2d' (type MaxPooling2D):
      • inputs=tf.Tensor(shape=(128, 128, 1, 16), dtype=float32)

steps to reproduce

1. Run the py file attached python case_unet.py
   case_unet.zip