FasterViT
FasterViT copied to clipboard
NVlabs
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
`ImportError: cannot import name '_update_default_kwargs' from 'timm.models._builder'` In timm github repo you may see recent name '_update_default_model_kwargs' https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/_builder.py
Changed `_update_default_kwargs` to `_update_default_model_kwargs` function as the timm library changed the name
Congrats on the acceptance and great work! Any chance you could provide an ImageNet-21K faster-vit checkpoint **without** ImageNet-1K fine-tuning. I would be very interested to see how the ImageNet-21K-based learned...
 I want to apply this model for my downstream task. And it is very necessary to draw heatmap that model focus on. So, is this model possible to draw...
First, thank you for sharing your wonderful work as an open source. I appreciate your work. I found in the TRAINING.md you provided that the args.mesa parameter settings differ for...
# PR Summary Small PR - Commit 848b042a1fa3be6a4672e839f40794d127fc1308 moved object detection sources. This PR adjusts sources to changes. It also fixes a few typos along the way.
python train.py \ --config /content/FasterViT/fastervit/configs/faster_vit_1_224_1k.yaml \ --model faster_vit_1_224 \ --tag faster_vit_1_224_exp_1 \ --batch-size 64 \ --lr 0.005 \ --mesa 0.2 \ --model-ema \ --opt adamw \ --weight-decay 0.005 \ --amp...
This issue relates to the implementation in `downstream/object_detection/dino/models/dino /fastervit.py`. I'm using this FasterViT implementation as a backbone for my own object detector, so I only needed the `forward_raw()` method. However...
I'm experimenting with FasterViT in an MMDetection project. In this project the validation data augmentation pipeline does not crop the image, and simply pads it to the minimum size. This...
Can't use torch.jit.trace + torch.jit.script. Error: `RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!` Reproduce: ``` import torch import...
