Dilshod Tadjibaev

@dcvz no it is done.

> The average pool config that is being used in the squeezenet is using `.with_count_include_pad(false)` which is not supported in Candle. We can fix this by: 1. Modify Candle backend...

Implementation using transpose Conv in pytorch: https://gist.github.com/mjstevens777/9d6771c45f444843f9e3dce6a401b183

We added a chunk operator (see https://github.com/Tracel-AI/burn/issues/970). Would this solve the issue?

@0xkelvin it would be great if you could work on this. It is perfect timing since we have books and plenty of examples. @nathanielsimard , @louisfd , @Luni-4 if you...

I think for a minimum we create a template repository to help new users get started. I have feeling users copy MNIST example cargo. Next we could tackle other use...

I've reviewed the work in progress and believe it will require additional time to be properly fixed. I'm not sure if you have considered integrating `xtask` directly under `example/image-classifier-web`, which,...

I'll close it for now since the approach will be different a little bit. I'll try to reuse code from it.

@Luni-4, wanna give a try? =)

No, it's not urgent. I just could not complete it in time for the example. I'll be traveling soon so I can't finish it.