Sagar Gupta

@sdv4 First of all, for the problem of GPU memory being shown nearly 500MB I did find a simple solution which works for me. Whenever you execute `train.py` you will...

@sdv4 your classification type is different. That might be a reason for it. labels:- y - 2120 n - 593 d - 1136 This is the breakdown of labels.csv, so...

@sdv4 there is nothing as correcting the classification type. Your results were for different classification and they were correct for that. I guess we want results for both!

@marco-c Can you please share a screenshot of how windows are opening? I made sure that they don't overlap in https://github.com/marco-c/autowebcompat/blob/b127fdfe75d647568db86d97c44065b963574825/label.py#L249-L251 and just touch each other.

This is unexpected. It works fine for me. In your screenshot third window is opening fine. There is a problem with first or the second one. I will try to...

For a temporary fix you can add some value to 20 in above part of code. I will try to find a solution till then!

@Shashi456 I think we should declare it in `run_test_both` and pass it to `jump_back` also.

Infinite website is just a concern. Generally it starts loading when we reach very end (what I have noticed experimentally). So height provided is its initial height. Just wanted to...

We actually want it: This happened now for Testing https://planet.mozilla.org/ (bug 10256) in firefox I got more than 4832 images (all white and blank)

Generally for pretrained models we use size of 224x224 or 227x227. We can think about it.