google-research

google-research/vision_transformer

Stars: 12.7k
Forks: 1.5k
Open beginner issues: 0
Indexed issues: 129

Dominant language: Jupyter Notebook
License: Apache-2.0
Last GitHub push: Aug 1, 2026
Latest indexed: Sep 16, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Open All

129 open issues indexed

training on our own dataset Open

google-research/vision_transformer#3 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Object detection using ViT Open

google-research/vision_transformer#4 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
The accuracy here refers to the training accuracy or the test accuracy？ Open

google-research/vision_transformer#8 · 15 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Will models pretrained on JFT300M dataset be released ? Open

google-research/vision_transformer#9 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
ValueError: Unknown split "train". Should be one of [] Open

google-research/vision_transformer#11 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
minimum GPU memory required for running vision_transformer Open

google-research/vision_transformer#17 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Is Batch size 4096/512 during training/fine-tuning for a 8 GPUs machine or a single GPU? Open

google-research/vision_transformer#26 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Advertised fine-tuning hyper-parameters & results Open

google-research/vision_transformer#29 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
In CIFAR10, why the fine-tuning training accuracy (<90%) is much lower than test accuracy (96.6%)? Open

google-research/vision_transformer#30 · 8 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
img_size=224 in ImageNet21k Open

google-research/vision_transformer#31 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Load the pretrained weights to TF2 ViT implementation, thanks Open

google-research/vision_transformer#33 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Ideas for image verification Open

google-research/vision_transformer#37 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Correct imagenet top-1 accuracy uploaded pretrained weights of hybrid ViT? Open

google-research/vision_transformer#39 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
RuntimeError: Internal: Failed to load in-memory CUBIN: CUDA_ERROR_OUT_OF_MEMORY: out of memory: while running replica 0 and partition 0 of a replicated computation (other replicas may have failed as well). Open

google-research/vision_transformer#40 · 8 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
when i run the command "python3 -m vit_jax.train --name ViT-B_16-cifar10_`date +%F_%H%M%S` --model ViT-B_16 --logdir /tmp/vit_logs --dataset cifar10",I encountered the error"Error executing an HTTP request: libcurl code 6 meaning 'Couldn't resolve host name', error details: Couldn't resolve host 'metadata'Error executing an HTTP request: libcurl code 6 meaning 'Couldn't resolve host name', error details: Couldn't resolve host 'metadata'"."." Open

google-research/vision_transformer#42 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Anybody manages to run it on Windows? Thanks Open

google-research/vision_transformer#44 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Suggestions for image generation Open

google-research/vision_transformer#48 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Further Details Open

google-research/vision_transformer#49 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
About accuracy of training from scratch on ImageNet-1k Open

google-research/vision_transformer#50 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Can't perform inference Open

google-research/vision_transformer#51 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Unexpected memory consumption with mixup Open

google-research/vision_transformer#52 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Visualization of position embeddings Open

google-research/vision_transformer#55 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
The Importance of Pretrained Model Weight. Open

google-research/vision_transformer#56 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Can provide pretrain model of self-supervision condition Open

google-research/vision_transformer#58 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
gap vs token Open

google-research/vision_transformer#60 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 16, 2026
Inquiry on pretraining acc Open

google-research/vision_transformer#62 · 22 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Could anyone help me run the train code? Open

google-research/vision_transformer#63 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Mean Attention Distance Open

google-research/vision_transformer#64 · 0 comments · 6 reactions · 0 assignees · Indexed Sep 16, 2026
ObjectNet numbers Open

google-research/vision_transformer#65 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
self-supervision prediction Open

google-research/vision_transformer#66 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
how to deal with video，which has 5min length Open

google-research/vision_transformer#67 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
How to access my own dataset? Open

google-research/vision_transformer#68 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
RuntimeError: CUDA error: device-side assert triggered Open

google-research/vision_transformer#69 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
i use it to video classification. when there has hundreds of frames ,How to deal with it? Open

google-research/vision_transformer#70 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
How to handle rectangle images? Open

google-research/vision_transformer#71 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
RuntimeError: Unimplemented: DNN library is not found Open

google-research/vision_transformer#73 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Edit the model Open

google-research/vision_transformer#74 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Will there be an official tensorflow version? Open

google-research/vision_transformer#75 · 2 comments · 2 reactions · 0 assignees · Indexed Sep 16, 2026
Why using weight normalization in StdConv2d? Open

google-research/vision_transformer#76 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Codes about self-supervision Open

google-research/vision_transformer#77 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
How to perform Regression Open

google-research/vision_transformer#79 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Can I use this model for multi-label classification task？ Open

google-research/vision_transformer#80 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Cannot run the code on TPU Open

google-research/vision_transformer#81 · 11 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
run the code on multi-host tpu Open

google-research/vision_transformer#82 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Fine-tune VIT-B-16 on imagenet2012 Open

google-research/vision_transformer#85 · 15 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
question about fine-tuning dimension Open

google-research/vision_transformer#92 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
to_patch_embedding Explanation Open

google-research/vision_transformer#93 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
what is the Optimizer Open

google-research/vision_transformer#94 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
load R26+ViT-B_32 model Open

google-research/vision_transformer#95 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
train a network from scratch Open

google-research/vision_transformer#96 · 1 comment · 2 reactions · 0 assignees · Indexed Sep 16, 2026

A short digest of beginner-friendly GitHub issues.