The test not passes due to the shape. I have no idea how to correct it. For exmaple, sequential (None, 1, 128) but it should be (None, 128).
This is my model structure.
Your issue is with the below code line
Define both inputs. Remember to call then ‘input_1’ and ‘input_2’ using the name parameter.
Be mindful of the data type and size
Check the below image on how to write the codes for this
- Next for the code line
Define the Concatenate layer. You should concatenate columns, you can fix this using theaxisparameter.
This layer is applied over the outputs of each branch of the Siamese network
When you apply the each branch using the concatenate list of inputs, both branches recalled from the previous code recall
Define the output of each branch of your Siamese network. Remember that both branches have the same coefficients,
but they each receive different inputs.
**branch1 and branch2 are concatenated using the same instruction mentioned in the image shared.
Regards
DP
That’s not my solution. My solution is change keepdims to the right boolean. Thanks
1 Like
Hi Deepti,
I’m lost on the input_shape for Input layer. Could you shed some light on what this should look like. Thanks
Hi @Alex_Tu
can I know if you have got any error or incorrect output for the test cell you are enquiring about as I need to know you are talking about which grade cell and does your issue is same as the post creator. You can share screenshot of the error or incorrect output you got, or the best would be to make a new topic with necessary details without sharing any codes.
Regards
DP
Issue was resolved. Thanks
How did you resolve the unittest?? I keep failing 3 tests out of 22.
Layer ‘sequential’ has an incorrect output shape.
Expected:(None, 16),
Got:(None, 128).
Layer ‘conc_1_2’ has an incorrect input shape.
Expected:[(None, 16), (None, 16)],
Got:[(None, 128), (None, 128)].
Layer ‘conc_1_2’ has an incorrect output shape.
Expected:(None, 32),
Got:(None, 256).