AlexNet bacward shape missmatch + ReLu return a tuple about singa HOT 7 OPEN

Hi, as pointed out by @chrishkchris , the convention is to use RELU as stateless layer.
usage:
https://github.com/apache/singa/blob/master/examples/cnn/model/cnn.py#L40

For shape mismatch, you might need to check the shape of layers again. Let me know if further info is required.

from singa.

Ok, I'll try but why to provide a statefull ReLU Layer? Is it for a specific purpose?

from singa.

I compared my implementation to other frameworks and it is the same shapes.
Moreover the forward pass does not cause any issue, it is the backward pass.
This is why I suspect a bug. Is it possible?

from singa.

Hi, as pointed out by @chrishkchris , the convention is to use RELU as stateless layer.
usage:
https://github.com/apache/singa/blob/master/examples/cnn/model/cnn.py#L40

For shape mismatch, you might need to check the shape of layers again. Let me know if further info is required.

@dcslin Did you try to run the code pasted by @Belegkarnil ?
Can you reproduce the error?

from singa.

Hi, as pointed out by @chrishkchris , the convention is to use RELU as stateless layer.
usage:
https://github.com/apache/singa/blob/master/examples/cnn/model/cnn.py#L40
For shape mismatch, you might need to check the shape of layers again. Let me know if further info is required.

@dcslin Did you try to run the code pasted by @Belegkarnil ?
Can you reproduce the error?

I am still checking the code

from singa.

Hi @Belegkarnil, you might need to change 256 * 6 * 6, 4096 to 256, 4096 to make it works.

Also you are recommended to use relu/dropout/flatten like this https://github.com/apache/singa/blob/master/examples/cnn/model/cnn.py#L40

from singa.

Ok thanks a lot ! I assumed that it works like other frameworks but that the result of AvgPool has a different shape.

from singa.