Xiuye Gu

In main.py, you should add this line (>>>)? for bids_auc in bids_grouped: >>> last_row = None for i, row in bids_auc[1].iterrows(): if last_row is None: last_row = row continue time_difference...

Trained models not found

1

Hi, thank you for your great work! I find that the trained models listed in the README in this page: https://github.com/aayushbansal/PixelNet/tree/master/models/generalizability are not found (404). Where can I download the...

Performance gap compared with the official TensorFlow implementation

4

Hi, Thanks for the great repo! I saw that you mentioned "I have trained the 256px model on FFHQ 550k iterations. I got FID about 4.5. Maybe data preprocessing, resolution,...

Thanks for the clean code! I have a confusion about the `_get_gt_dt` function, in line https://github.com/lvis-dataset/lvis-api/blob/031ac21f939bcb5f1ca8de2ab8704082e101ff9b/lvis/eval.py#L158 and https://github.com/lvis-dataset/lvis-api/blob/031ac21f939bcb5f1ca8de2ab8704082e101ff9b/lvis/eval.py#L163, according to the doc string of the function that parameter `cat_id` is...

[Discussion] mp: duplicate of torch.cuda.set_device(local_rank) and images = images.cuda(local_rank, non_blocking=True)

4

Hi there, Great repo! I'm studying this topic, and found out that the [official repo](https://github.com/pytorch/examples/blob/master/imagenet/main.py) of imagenet classification also uses multiprocessing. I noticed one place that they not only use...

As is described. I also wonder if there is some standard for computing number of flops. Say, flops usually count the number of multiplication and addition, so sometimes people don’t...

a small question regarding adcensus.cu

2

I was looking for the docs of adcensus.cu, but cannot find one. And later, I noticed your adcensus repo. So is the adcensus.cu a part of your adcensus repo?