Exception: "concat" mode can only merge layers with matching output shapes

[sansinghsanjay]

I am getting following exception at line 61 in model.py :

Exception: "concat" mode can only merge layers with matching output shapes except for the concat axis. Layer shapes: [(None, 2, 20, 512), (None, 1, 20, 256)]

I am new to keras.

Thanks...

[raghakot]

i did not test this against theano backend. Are u getting this with tensorflow backend?

[sansinghsanjay]

I tried your updated code and I think that I was missing following instructions specified in readme file:
{
"image_dim_ordering": "th",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "tensorflow"
}

I followed above instructions and changed "image_dim_ordering" from "tf" to "th". It helps and resolves this issue.

Thanks...