lucidrains/vit-pytorch issues and pull requests

#229 - Question about example notebook

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

#228 - EfficientFormer Request!

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

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

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

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

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

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

Issue - State: open - Opened by myzhuang over 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 - 2 comments

#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 almost 3 years ago - 1 comment

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

Issue - State: closed - Opened by Bobo-y almost 3 years ago

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

Issue - State: open - Opened by jdegange almost 3 years ago

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

Issue - State: open - Opened by chandlerbing65nm almost 3 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 ?

Issue - State: open - Opened by aishik11 almost 3 years ago

#199 - suggest any jupyter notebook or python code for use this library

Issue - State: open - Opened by kiashann almost 3 years ago - 1 comment

#198 - RuntimeError: stack expects a non-empty TensorList

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

#197 - [BUG] efficient ViT does not support rectangular images

Issue - State: closed - Opened by gdevos010 almost 3 years ago - 2 comments

#196 - MAE using pretrained VIT

Issue - State: open - Opened by Songloading almost 3 years ago - 3 comments

#192 - NesT implementation doesn't match the author/timm implementation

Issue - State: closed - Opened by MarkYangjiayi almost 3 years ago - 3 comments

#191 - How to get the feature map of the vit encoder

Issue - State: open - Opened by bladetin almost 3 years ago - 4 comments

#190 - does vit-pytorch has mvit?

Issue - State: closed - Opened by RyanHuangNLP almost 3 years ago - 1 comment

#189 - Vit MAE decoder positional embeddings

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

#187 - Vit MAE reconstruction size mismatch

Issue - State: open - Opened by RhinigtasSalvex almost 3 years ago - 2 comments

#185 - where is the train.py? tks

Issue - State: open - Opened by henbucuoshanghai almost 3 years ago - 2 comments

#184 - About different patch embedding in ViT

Issue - State: closed - Opened by wddwzwhhxx almost 3 years ago - 1 comment

#178 - Any chance to have conda installation?

Issue - State: closed - Opened by yliu7366 almost 3 years ago - 3 comments

#173 - Some questions about decoder position embedding for masked tokens

Pull Request - State: open - Opened by chrisway613 about 3 years ago - 1 comment

#169 - MAE image recon

Issue - State: open - Opened by chokyungjin about 3 years ago - 9 comments

#166 - ViT-Dino for Medical images

Issue - State: open - Opened by Mushtaqml about 3 years ago - 3 comments

#164 - Removing FC layer at the top of the transformer model

Issue - State: open - Opened by loukasilias about 3 years ago - 2 comments

#162 - How to save and restore the parameters?

Pull Request - State: open - Opened by lesept777 about 3 years ago

#154 - Training DINO

Issue - State: open - Opened by cmartin-isla about 3 years ago - 4 comments

#152 - Training vit on Imagenet 1k got bad performance.

Issue - State: open - Opened by songlei00 about 3 years ago - 2 comments

#143 - Memory usage

Issue - State: open - Opened by gerben-b over 3 years ago - 1 comment

#140 - Are there any backbones available that can readily be adapted for dense prediction?

Issue - State: closed - Opened by amorehead over 3 years ago

#132 - swin transformer is very good in its paper,does vit-pytorch has it?

Issue - State: closed - Opened by henbucuoshanghai over 3 years ago - 2 comments

#131 - Ask for help: How to use multi GPUs? All input tensors must be on the same device. Received cuda:3 and cuda:2

Issue - State: open - Opened by starrywintersky over 3 years ago - 4 comments

#124 - Understanding of the implementation of MPP loss

Issue - State: closed - Opened by lzx325 over 3 years ago - 5 comments

#119 - ask help: what's the meaning of self.to_latent = nn.Identity() in vit.py

Issue - State: closed - Opened by rocke2020 over 3 years ago - 2 comments

#117 - Problem while trying to use more than 3 channels

Issue - State: open - Opened by SK124 over 3 years ago - 4 comments

#112 - Allow mpp to use non square patches

Issue - State: closed - Opened by FilipAndersson245 over 3 years ago - 3 comments

#103 - Question on DeiT training procedure

Issue - State: open - Opened by hongvin over 3 years ago - 2 comments

#101 - Mpp fix

Pull Request - State: closed - Opened by zankner over 3 years ago - 4 comments

#82 - Get Attention Weights

Issue - State: closed - Opened by joellehanna97 over 3 years ago - 3 comments

#78 - can you provide your pre-trained weight?

Issue - State: open - Opened by NEUdeep almost 4 years ago - 12 comments

#77 - cats_and_dogs.inpynb can't use GPU training

Issue - State: open - Opened by FalconJK almost 4 years ago - 1 comment

#73 - where is the pretrain model ?

Issue - State: open - Opened by ustcerlik almost 4 years ago - 1 comment

#67 - Pretrain model

Issue - State: closed - Opened by zchoi almost 4 years ago - 2 comments

#53 - fastai compatibility

Issue - State: closed - Opened by thenatlog almost 4 years ago - 9 comments

#48 - Multi-label classification

Issue - State: closed - Opened by ramizdundar almost 4 years ago - 5 comments

#45 - Model doesn't converge

Issue - State: open - Opened by liberbey almost 4 years ago - 23 comments

#43 - The model doesn't converge

Issue - State: closed - Opened by SuX97 almost 4 years ago - 14 comments

#37 - cls_token

Issue - State: open - Opened by shibin2018 almost 4 years ago - 2 comments

#21 - How to load the pretrain model

Issue - State: closed - Opened by nooralahzadeh about 4 years ago - 6 comments

#13 - how to get train.zip.

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

GitHub / lucidrains/vit-pytorch issues and pull requests