daodaofr
daodaofr
Yes, your understanding is right. On CUHK-SYSU and PRW, the pedestrian detection is relatively a simple task, thus the scale misalignment issue mainly impacts the re-id task. On a more...
Hi, we didn't try to train with multiple GPUs. But MMDetection supports distributed training, please refer to https://github.com/daodaofr/AlignPS/blob/master/tools/dist_train.sh
Normally, you can still get fair performance, maybe there needs some adjusting in batch size and learning rate to get the best results.
Thanks for your results, I think the results are normal. According to my experience, the triplet loss only has a very slight influence on PRW, less than 1%. Different environments...
I am sorry, but I haven't tried distributed training. So I cannot give practical suggestions on that. If you want to reproduce the results, please try to use a single...
I also noticed the inconsistency issue of feature size, where the network stops training, so I deleted the reply. It would be nice if you could give an example of...
Great! Thanks :)
> Hi, I tried the distributed implemention of @dqshuai, but the performance got worse. > I notice that there is a toolkit in `mmdet/models/dense_heads/oim_utils.py` and , which contains the distributed...
Yes, I used the hourglass_bn_100 model
I‘ve just fixed this problem. I give exactly the same inputs as in the training phase, and I got reasonable results. Thanks