yitu-opensource/T2T-ViT

Issues

• load_for_transfer_learning

  #79 opened 9 months ago by lurong-xing
  0

• Problem about visualization_vit.ipynb

  #52 opened 4 years ago by StevenAZy
  4

• On the Parameter Selection Problem of 'pretrained' in Creating Models

  #77 opened a year ago by xuanRyc
  0

• Input size is not a square, what should I do in this line?

  #76 opened 2 years ago by JerryKingQAQ
  0

• colab

  #75 opened 2 years ago by SMaryamHosseini
  0

• data preprocessing

  #74 opened 2 years ago by abcsimple
  0

• What exactly does args.num gpu refer to?

  #73 opened 2 years ago by yu868
  0

• Fail to obtain the reported MACs for performer-based models.

  #47 opened 4 years ago by blackfeather-wang
  5

• "T2T-ViT-14, 384" cannot be loaded into "T2t_vit_14" model

  #72 opened 3 years ago by Carlisle-Liu
  1

• TransferLearning Cifar10

  #42 opened 4 years ago by maryamag85
  3

• gained 0.094 for eval_top1, and 0.33 for eval_top5, after 36-epoch training on 8 gpus

  #56 opened 3 years ago by CheerM
  4

• Downloads all say "tar: This does not look like a tar archive" when I try to un-tar

  #71 opened 3 years ago by lowfuel
  2

• [maybe a bug] loss nan

  #69 opened 3 years ago by xmy0916
  4

• training T2T-ViT is slower than training resnet?

  #64 opened 3 years ago by lixincn2015
  1

• 'bool' object has no attribute 'pos_embed

  #67 opened 3 years ago by helloworld-wu
  2

• My case to solve NaN loss when using AMP

  #65 opened 3 years ago by CreamNuts
  2

• 关于token_transformer中attention的部分

  #68 opened 3 years ago by stillwaterman
  0

• 请问您在8台GPU上训练了多久？

  #66 opened 3 years ago by chenhui2016
  0

• Bug in utils.py ->load_for_transfer_learning

  #63 opened 3 years ago by AmnonGeifman
  0

• Attention scale value from pretrained model

  #62 opened 3 years ago by TooTouch
  0

• Benefit of DropPath

  #61 opened 3 years ago by askerlee
  0

• Problem about visualization_vit.ipynb

  #60 opened 3 years ago by koala719
  0

• Problem in TransferLearning Cifar100

  #59 opened 3 years ago by MihaoYoung
  0

• Transformer block

  #58 opened 3 years ago by Summer-sss
  1

• How to register new models?

  #57 opened 3 years ago by lucastononrodrigues
  0

• train T2T-ViT on the custom dataset

  #55 opened 4 years ago by 123-xin
  1

• could you share the log of training T2T-ViT_t-24 and T2T-ViT_t-19?

  #54 opened 4 years ago by wangpichao
  2

• Unable to train T2T-ViT for 384 x 384 image

  #53 opened 4 years ago by SK124
  1

• Local variable 'input' referenced before assignment

  #34 opened 4 years ago by laohanlin
  1

• How to change the input size of the picture？

  #39 opened 4 years ago by mikaizhu
  1

• position embedding

  #45 opened 4 years ago by jingliang95
  1

• resizing images for feature visualization

  #48 opened 4 years ago by kahnchana
  2

• Questions about the results of the experiment

  #41 opened 4 years ago by chenyucong1
  1

• Pre-train ViT on unsupervised task?

  #43 opened 4 years ago by neel04
  1

• Questions about feature visualization of vit_large_patch16_384

  #33 opened 4 years ago by Hongyu-He
  3

• The FPS of T2T-ViT-14 and T2T-ViT-7

  #31 opened 4 years ago by mmobai
  1

• Larger models learn slowly?

  #50 opened 4 years ago by chenwydj
  2

• Question about the 'unfold operation.

  #28 opened 4 years ago by JaminFong
  2

• ImageNet100 very low accuracy

  #36 opened 4 years ago by Evgeneus
  1

• dataset

  #46 opened 4 years ago by Summer-sss
  1

• finetune on a custom dataset with different image size

  #44 opened 4 years ago by GuoleiSun
  1

• Sorry! This problem has been solved

  #49 opened 4 years ago by mxqin
  0

• Confusion matrix and classify validation images?

  #27 opened 4 years ago by zxsitu
  1

• How to calculate MACs/FLOPs?

  #37 opened 4 years ago by chenwydj
  2

• Hard to train

  #40 opened 4 years ago by huixiancheng
  3

• small question about lr_scheduler

  #38 opened 4 years ago by huixiancheng
  3

• Which hyperparameters should I change if I have different input size?

  #35 opened 4 years ago by chenwydj
  2

• Fine-tuning

  #32 opened 4 years ago by davidmoralesrodriguez
  2

• Transfer learning CIFAR10

  #29 opened 4 years ago by aldahdooh
  4

• How the "kernel_ratio" influences the performance?

  #30 opened 4 years ago by PkuRainBow
  1