eezywu

Results 10 comments of eezywu

Confusion about the shape of offset

I have the same confusion here. For every point of output, there should be a offset grid of 2x9 points. So I think the number of channels should be `2N`,...

prune mobilenetv2

@CF2220160244 @luluvi Hi~You can check the code [here](https://github.com/eezywu/Pruned-MobileNet_v2). I will finish the introduction of how to prune MobilenetV2 when I have time.

Confusion about why a single conv layer is able to learn the offsets

Can anyone explain? Thanks!

why use conv-layer to predict conv offset while fc-layer predict pool offset?

Same confusion here

Question about hard sample mining

+1

Question about hard sample mining

@tfzhou hi, could you open source the code of Hardest Example Sampling and Semi-Hard Example Sampling? Thanks!

NLP

I am also looking forward to this chapter. Thanks for all the contributors!

It's a shame of China Open Source.

> Guys, calm down. You're not owed anything. You didn't do the research, nor do you have the skills or resources to do it. So what's up with the entitlement?...

ValueError: Unknown scheme for proxy URL URL('socks://127.0.0.1:10801/')

> `python gradio_canny2image.py logging improved. Traceback (most recent call last): File "gradio_canny2image.py", line 6, in import gradio as gr ... ValueError: Unknown scheme for proxy URL URL('socks://127.0.0.1:10801/') ` How to...

How to perform fusion operation with MLPs?

same question