lucidrains/vit-pytorch issues and pull requests

#297 - Add implementation of LongVit

Issue - State: closed - Opened by jpfeil 7 months ago - 4 comments

#296 - Problems regarding training 3D Vision transformer : model does not converge

Issue - State: open - Opened by Uljibuh 8 months ago

#295 - Multi-target Regression Question

Issue - State: open - Opened by stethemJ 8 months ago

#294 - can we use CvT model for segmentation?

Issue - State: open - Opened by HawkingRadiation42 8 months ago

#293 - Masking attention with batches

Issue - State: open - Opened by ashrafflh 8 months ago

#292 - Question regarding 1d fft use

Issue - State: closed - Opened by chengengliu 9 months ago - 1 comment

#291 - Trouble loading ViT - Dino structure for channels>3?

Issue - State: open - Opened by AgentM-GEG 9 months ago

#290 - First attempt

Pull Request - State: open - Opened by jefferson-bercaw 10 months ago

#289 - Questions about distill_loss

Issue - State: open - Opened by haoren55555 11 months ago - 1 comment

#288 - how to train

Issue - State: open - Opened by lingxitong 11 months ago - 1 comment

#287 - Layernorm in Cross attention

Issue - State: closed - Opened by turtleman99 11 months ago - 4 comments

#286 - CvT with 1 channel input data

Issue - State: closed - Opened by tranlg99 11 months ago - 2 comments

#285 - Fix typo in vit_1d LayerNorm

Pull Request - State: closed - Opened by l0wgear 11 months ago - 1 comment

#284 - add xcit

Pull Request - State: closed - Opened by lucidrains 12 months ago

#283 - Update README.md

Pull Request - State: closed - Opened by EIFY 12 months ago - 1 comment

#282 - Not correctly understanding the Multi Head Attention part of the ViT implementation...

Issue - State: closed - Opened by JavierUrenaPhDProjects 12 months ago - 3 comments

#281 - Potential regression with PT 2.0 and CUDA 12.2/CuDNN 8.9.4

Issue - State: closed - Opened by roywei about 1 year ago - 1 comment

#280 - Using vision transformers for different image resolutions

Issue - State: open - Opened by Oussamab21 about 1 year ago - 1 comment

#279 - vit_pytorch -> cross_vit.py(mistake)

Issue - State: closed - Opened by RufusRubin about 1 year ago - 1 comment

#278 - Saving and loading model seems to be regressing to lower performance

Issue - State: closed - Opened by aperiamegh about 1 year ago - 1 comment

#277 - structural 3D ViT

Issue - State: closed - Opened by aperiamegh about 1 year ago - 4 comments

#276 - This ViT implementation as generative network

Issue - State: open - Opened by MrCorsair3 about 1 year ago - 1 comment

#275 - TVM compilation failed on SimpleViT

Issue - State: open - Opened by yangxin0926 about 1 year ago

#274 - Update vit.py

Pull Request - State: closed - Opened by LuYuchenOrRobert about 1 year ago - 3 comments

#273 - begin work on NaViT (wip)

Pull Request - State: closed - Opened by lucidrains about 1 year ago

#272 - Support SimpleViT as encoder in MAE

Pull Request - State: closed - Opened by roydenwa about 1 year ago - 3 comments

#271 - MAE Training

Issue - State: open - Opened by mw9385 about 1 year ago

#270 - Is it possible to use the "Accessing Attention" of the vit-pytorch on the timm models?

Issue - State: open - Opened by Shima-shoki about 1 year ago

#269 - Dimension issues in Masked Patch Prediction

Issue - State: closed - Opened by KananVyas over 1 year ago - 4 comments

#267 - When running python train_cifar10.py, RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase.

Issue - State: closed - Opened by laserljy over 1 year ago

#266 - ViVit pos encoding

Issue - State: closed - Opened by eyalmazuz over 1 year ago - 2 comments

#265 - add ViTResiDual

Pull Request - State: closed - Opened by Hazqeel09 over 1 year ago - 7 comments

#264 - Number of patches in height and width dimension should be in a single…

Pull Request - State: closed - Opened by Vishu26 over 1 year ago - 2 comments

#263 - Integrate Aim - an open-source experiment tracker

Issue - State: closed - Opened by tatyusha over 1 year ago - 1 comment

#262 - PyTorch 2.0 support

Issue - State: open - Opened by kxzxvbk over 1 year ago - 2 comments

#261 - Multi-head attention part on ViT

Issue - State: closed - Opened by andreYoo over 1 year ago

#260 - Add Masked Position Prediction

Pull Request - State: closed - Opened by Vishu26 over 1 year ago - 1 comment

#259 - ViT for regression task such as Real Estate Price Prediction or Stock Exchange Datasets, any regression dataset.

Issue - State: closed - Opened by saifhassan over 1 year ago - 7 comments

#258 - Small Typo in CCT description

Issue - State: closed - Opened by DSARichard over 1 year ago - 1 comment

#257 - Why the accuracy rate to 100% using its examples' dataset

Issue - State: closed - Opened by zx-fxs over 1 year ago - 2 comments

#256 - Using SimpleVit to estimate odometry

Issue - State: open - Opened by Deadrosas over 1 year ago

#255 - Apply Tanh activation function to ViT - MLP Head

Issue - State: open - Opened by joeycouse over 1 year ago

#254 - How to use torchvision.models.feature_extraction.create_feature_extractor() with vit_pytorch?

Issue - State: closed - Opened by ArturasDruteika over 1 year ago

#253 - MAE bug!

Issue - State: closed - Opened by hotco87 over 1 year ago - 2 comments

#252 - [Feature Request] ViTDet

Issue - State: open - Opened by austinmw over 1 year ago - 7 comments
Labels: enhancement

#251 - Training a VIT from pre-trained patches embeddings

Issue - State: closed - Opened by AdrianBZG over 1 year ago - 1 comment

#249 - add an interpolate_embeddings helper function

Issue - State: open - Opened by DanTaranis almost 2 years ago

#248 - The problem of reprinting vivit

Issue - State: closed - Opened by kuangxiaoye almost 2 years ago - 1 comment

#247 - 自动驾驶更新笔记 Autopilot Updating Notes

Issue - State: closed - Opened by nwaysir almost 2 years ago

#246 - How to use mask in ViT

Issue - State: closed - Opened by Ma-Zijing almost 2 years ago - 3 comments

#244 - LayerNorm for Vit

Issue - State: closed - Opened by zjhdxh almost 2 years ago

#243 - Neighbourhood Attention Implementation

Issue - State: closed - Opened by RisabBiswas almost 2 years ago - 5 comments

#242 - Update mae.py

Pull Request - State: closed - Opened by Vishu26 almost 2 years ago - 4 comments

#241 - MAE `decoder_tokens` computation

Issue - State: closed - Opened by Vishu26 almost 2 years ago - 1 comment

#240 - How to retrain ViT

Issue - State: open - Opened by anusmitabose almost 2 years ago - 2 comments

#239 - Support for loading pretrained weights into networks:

Issue - State: open - Opened by PrithivirajDamodaran about 2 years ago - 2 comments

#238 - Tensors must have same number of dimensions : got 5 and 3

Issue - State: closed - Opened by satwiksunnam19 about 2 years ago - 8 comments

#237 - Quesiton about attention's qkv matrix

Issue - State: open - Opened by JearSYY about 2 years ago - 2 comments

#236 - simplify `to_patch_embedding` using Conv2d

Issue - State: closed - Opened by avihu111 about 2 years ago - 4 comments

#235 - Issues loading RegionVIT pre-trained checkpoints

Issue - State: open - Opened by PrithivirajDamodaran about 2 years ago - 1 comment

#234 - Loading weights of custom ViT models

Issue - State: closed - Opened by PrithivirajDamodaran about 2 years ago - 1 comment

#233 - Visualize the attention weights

Issue - State: open - Opened by code-pan94 about 2 years ago - 1 comment

#232 - Distillation RuntimeError

Issue - State: open - Opened by NeelKanwal about 2 years ago - 1 comment

#231 - add efficientformer

Pull Request - State: closed - Opened by Andrechang about 2 years ago - 3 comments

#230 - Attention maps for PiT

Issue - State: open - Opened by Maxlanglet about 2 years ago

#229 - Question about example notebook

Issue - State: closed - Opened by albusdemens about 2 years ago - 1 comment

#228 - EfficientFormer Request!

Issue - State: open - Opened by umitkacar about 2 years ago - 1 comment

#227 - what are the changes i should use for the large release?

Issue - State: closed - Opened by mathshangw about 2 years ago

#226 - Global average pool mean is taking cls token into account as well

Issue - State: open - Opened by EmreTaha about 2 years ago

#225 - How to calculate Params and Flops for Vit?

Issue - State: open - Opened by myzhuang about 2 years ago - 5 comments

#224 - Although there is no bug in this line, '1 n d' should be '1 1 d' in my opinion, it would be confused.

Issue - State: closed - Opened by KKIverson over 2 years ago - 2 comments

#223 - MaxViT's MbConv doesn't match article.

Issue - State: closed - Opened by arquolo over 2 years ago - 1 comment

#222 - Add another MLP head in vision transformer

Issue - State: open - Opened by Atul997 over 2 years ago - 2 comments

#221 - Accessing last layer hidden states or embeddings for models like CrossViT, RegionViT (Extractor doesn't seem to work)

Issue - State: closed - Opened by PrithivirajDamodaran over 2 years ago - 8 comments

#220 - Improving Readability

Pull Request - State: closed - Opened by ryanrussell over 2 years ago

#219 - Attention maps rectangular input

Issue - State: closed - Opened by lucaswannen over 2 years ago

#218 - Masked Auto Encoder, class token and linear probing

Issue - State: open - Opened by Gasp34 over 2 years ago - 1 comment

#217 - why not combine key and query linar layer into one

Issue - State: open - Opened by locysty over 2 years ago - 1 comment

#216 - update simmim using conv decoder which replace simple header

Pull Request - State: open - Opened by wnma3mz over 2 years ago - 4 comments

#215 - Can anyone show me the example of Distillation please

Issue - State: open - Opened by adewidyatamadb over 2 years ago - 1 comment

#214 - issue VIT + Loss function

Issue - State: open - Opened by jeremyEudaric over 2 years ago

#213 - my own datasets? train.py pre.py?

Issue - State: open - Opened by henbucuoshanghai over 2 years ago - 2 comments

#212 - fix bibtex typo

Pull Request - State: closed - Opened by vztu over 2 years ago - 1 comment

#211 - maxvit intent to build

Pull Request - State: closed - Opened by lucidrains over 2 years ago

#210 - intent to build

Pull Request - State: closed - Opened by lucidrains over 2 years ago

#209 - Did you miss dropout?

Issue - State: closed - Opened by Fei-Wang over 2 years ago - 2 comments

#208 - CCT and non-square images

Issue - State: closed - Opened by Gasp34 over 2 years ago - 2 comments

#207 - A new idea

Issue - State: open - Opened by chenguanxi22 over 2 years ago

#206 - Question about code of `vit_for_small_dataset.py`

Issue - State: closed - Opened by RaymondJiangkw over 2 years ago - 2 comments

#205 - Could you release tutorials and examples as many as possible? And is the .zip file from the COCO dataset?

Issue - State: open - Opened by BenoitKAO over 2 years ago

#204 - How to train custom dataset

Issue - State: open - Opened by BenoitKAO over 2 years ago - 1 comment

#203 - Has a big time gap between GPU and CPU for Rearrange op.

Issue - State: closed - Opened by Bobo-y over 2 years ago

#202 - Loading MAE pre-trained model for image classification fine tuning.

Issue - State: open - Opened by jdegange over 2 years ago

#201 - How to use Multi-Head Attention in ViT

Issue - State: open - Opened by chandlerbing65nm over 2 years ago - 1 comment

#200 - I want to use pretrained VITMAE to embed patches without any masks which inturn I plan to feed into a decoder, Can someone point me in the correct direction ?

GitHub / lucidrains/vit-pytorch issues and pull requests