John Ho

@WujiangXu I used [`pipreqs`](https://github.com/bndr/pipreqs) to make an `requirements.txt` for this repo. You might want to add in `opencv-python==4.4.0.44` manually. if you are going to use **PWCNet** you will need `cupy`...

@KeesCBakker your *side load* method is basically what *serverless* + *serverless-python-requirements* does; i.e. zip numpy along with the lambda function, then add run time unzip into /tmp I also want...

@hamzanaeem1999 I'd put ``` if isinstance(m, nn.Upsample): m.recompute_scale_factor = False ``` on [line 722](https://github.com/WongKinYiu/yolov7/blob/4ebeeca4050b0aa5ca165deebc7536abd722268b/models/yolo.py#L722) in `models/yolo.py` before the `x = m(x)` statement that way you can keep the latest torch...

with `QQQ.csv` a quick one line hack that does just that would be: ``` cat QQQ.csv | cut -d ',' -f1 > QQQ_tickers_only.csv ```

@jasonmbray I am interested in the workaround if you'd be so kind to share!

any plans to?

interested in the multisports pretrained weight as well any plans to make it available soon?

saw similar issues when evaluating on the [SportsMOT dataset](https://github.com/MCG-NJU/SportsMOT/tree/main/codes) I found that if you set `--USE_PARALLEL True` and `--NUM_PARALLEL_CORE` to a reasonable number (i used only 2 because i'm running...