Jongmin Gim

``` def train(train_loader, pfld_backbone, auxiliarynet, criterion, optimizer, epoch): losses = AverageMeter() weighted_loss, loss = None, None for img, landmark_gt, attribute_gt, euler_angle_gt in train_loader: img = img.to(device) attribute_gt = attribute_gt.to(device) landmark_gt...

multi gpu

2

I saw that "import torch.distributed as dist" in HAIS's train.py code. Can I use a multi gpu when I train a HAIS model?? If not, could give me any advise...

About the freeze_train option in train.py

2

Hi, thanks for the great code. I have a question about the option in train.py Is there a difference of the Freeze_Train and pretrained ? And if Freeze_Train is Ture,...

Image reconstruction via Transformer.

2

Hello, I have a question about the image reconsturction via VAR. I want the transformer model to predict the ground truth tokens, just like in the training situation, by obtaining...

### Search before asking - [x] I have searched the Yolo Tracking [issues](https://github.com/mikel-brostrom/boxmot/issues) and [discussions](https://github.com/mikel-brostrom/boxmot/discussions) and found no similar questions. ### Yolo Tracking Component Evaluation ### Bug I’m trying to...