pmf_cvpr22
pmf_cvpr22 copied to clipboard
hushell
G:\awh\pmf_cvpr22-main\engine.py:115: UserWarning: The structure of is not recognizable. warnings.warn(f'The structure of {data_loaders} is not recognizable.') Traceback (most recent call last): File "test_bscdfsl.py", line 116, in main(args) File "test_bscdfsl.py", line 62,...
Hi there, I'm using dino_base_patch16 arch and I'm using my custom dataset which has 3 classes for image classification. Training is done but I'm not able to use the model...
Hi, Thanks for sharing the code with your fundamental work. I would like to convert the Prototype Net to tensorRT or ONNX, do you have any experience with that? I...
I have 5 classes, but during inference time there is no guarantee that the image will be from these 5 classes. I am using dino_small_patch16 arch. Is there a way...
Hi, I think I found a typo in the meta-test command line you give. I am not sure though ```python -m torch.distributed.launch --nproc_per_node=8 --use_env test_meta_dataset.py --data-path /path/to/meta_dataset/ --dataset meta_dataset --arch...
I noticed that you guys have a torch.cuda.amp.autocast() in the _evaluate function ([line 143](https://github.com/hushell/pmf_cvpr22/blob/main/engine.py#L143)) in engine.py. In my experience, autocasting is typically used in conjunction with a GradScaler as well....
Hi there, Under README.md, last section (Cross-domain few-shot learning) `python test_bscdfsl.py --test_n_way 5 --n_shot 5 --device cuda:0 --arch dino_small_patch16 --deploy finetune --output outputs/your_experiment_name --resume outputs/your_experiment_name/best.pth --ada_steps 100 --ada_lr 0.0001 --aug_prob...
