asyml/vision-transformer-pytorch
Pytorch version of Vision Transformer (ViT) with pretrained models. This is part of CASL (https://casl-project.github.io/) and ASYML project.
PythonApache-2.0
Issues
- 0
finetuned file available?
#11 opened by Ferriksw - 0
- 0
Hyper-parameters for Fine-tuning CIFAR-100
#9 opened by superctj - 4
- 1
Performance on train from scratch
#4 opened by yyou1996 - 4
您好,请问怎么把这个用于视频分类?比如5分钟的短视频
#6 opened by dotsonliu - 1
Image resolution for training
#7 opened by a-maiti - 1
- 2
R50+ViT-B/16 hybrid model ?
#2 opened by GuHongyang - 0
A small question in src/train.py.
#3 opened by liuhao-lh - 2
效果不好
#1 opened by luotianhang