-
Hello!
I would like to train T2t_vit_14 model on ImageNet-100 dataset and 3 gpus Quadro RTX 5000 but I have gotten Nan in loss and the error. Could you please help to run the code?
I run the follo…
-
It seems that the 'cutmix_prob' is an important hyper-parameter yet you did not mention in the paper. May I ask the value you adopted to get the results in the paper?
-
I got existing code to train EfficientNet using PyTorch which contains custom augmentations like CutMix, MixUp etc. in my training loop. This runs perfectly on GPU. Now I want to change my code such t…
-
When running YOLOv4 on exactly the same data and configuration as a previous model built successfully using YOLOv3 I got a CUDA out of memory error. The error message indicated that I should increa…
-
Pruning 한 모델을 Shrink 하려 하는데 다음과 같은 에러가 납니다.
densenet_small_lth.py 를 가지고 Pruning하였고 `../../model_compression/my_work/models/LTH/171_62_87.pth.tar ` 이 경로에 Pruning된 weight이 저장되어있는데 제가 잘못하고있는건가요?
```…
-
Hi All,
here is my system details .
CUDA 11.2
cuDNN - 8.1.1
OPENCV - 4.5.0
OS - CentOS
in make file
GPU-1
CUDNN_HALF -1
OPENCV -1
weight file is yolov4.conv.137
make file compi…
-
In 'Ablation Studies', you applied CuMix on different feature levels, have you tried to apply it on both feature-level and image-level at the same time?
-
We are interesting to use cutmix in object detection. But the problem is that whats the bbox drop rule?
-
* AI News
- EU AI regulation: https://digital-strategy.ec.europa.eu/en/library/proposal-regulation-european-approach-artificial-intelligence
- AI 시스템 risk 4단계 정의
- 단계별 규제 범위 정의
- 굉장히…
-
It seems that the code cannot generate "./train_pkl/samples_bytes_0.pkl" successfully.
The first running, generate pkl, but return error:
> ./train_pkl/samples_bytes_0.pkl
> global_rank 0 cache…