facebookresearch deit issues

facebookresearch / deit

Official DeiT repository

Apache License 2.0

3.94k stars 547 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Will you be releasing the accuracy of the official deit III framework trained tiny version on IN1k?

#241 chenziwenhaoshuai opened 4 months ago
0
Gradient accumulation code

#240 King4819 opened 5 months ago
0
Question about different seeds per gpu with DDP

#239 HIT-LiuChen opened 5 months ago
0
Training

#238 ali-88123 opened 5 months ago
0
Inclusion of Transformers Need Registers

#237 mileseverett opened 8 months ago
0
random.seed(seed) in line 205 is commented

#236 Phuoc-Hoan-Le opened 8 months ago
0
Compositional ViT

#235 piotrmwojcik closed 9 months ago
1
Slow Training

#234 mueller-mp closed 8 months ago
2
ViT-B Training for DeiT

#233 ziqipang closed 3 months ago
2
Checkpoints of IN21K pretrained deit III

#232 Byakuya-zi opened 10 months ago
0
Hi，Why can't I find deit_tiny_distilled_patch16_224 in hubconf

#231 GerogeD opened 10 months ago
0
TracerWarning

#230 maingoc1605 opened 10 months ago
0
cosub bugfix

#229 bhheo closed 10 months ago
0
Bump torch from 1.7.0 to 1.13.1

#228 dependabot[bot] closed 10 months ago
1
Fix/forget to guard the nas correlated function

#227 shadowpa0327 closed 11 months ago
1
How to launch a training of CAIT models ?

#226 elias-ramzi opened 1 year ago
0
Dev/feature kd

#225 shadowpa0327 closed 1 year ago
1
Code for cosub

#224 ppalantir closed 1 year ago
0
Fix Spelling Error: Correct "defaul" to "default"

#223 fabfish closed 11 months ago
0
fix argument bug

#222 fabfish closed 1 year ago
1
fix argument bug

#221 fabfish closed 1 year ago
2
batch_size flag

#220 tsengalb99 opened 1 year ago
2
ImageNet21K data preparation for pre-training

#219 mxjecho opened 1 year ago
5
DeiT depth 24 (CaiT - TABLE 1)

#218 GoJunHyeong closed 5 months ago
2
how to implement cosub training use deit-III

#217 xiaoguang-1 opened 1 year ago
2
how to implement cosub training use deit-III

#216 xiaoguang-1 closed 1 year ago
0
The ablation experiment of DeiT

#215 Berry-Wu opened 1 year ago
2
What are the hyperparameters for DeiT-III (epoch 400 or 600)?

#214 GoJunHyeong closed 1 year ago
0
Single machine multi-GPU training

#213 AlexNmSED opened 1 year ago
0
unexpected keyword argument 'pretrained_cfg'

#212 entron closed 1 year ago
2
Nas

#211 shadowpa0327 closed 1 year ago
1
how to implement document layout analysis use Deit-B

#210 sherryhsy closed 1 year ago
2
Update main.py for resolving the dataloader error in distributed training.

#209 yazdanimehdi closed 1 year ago
2
Multi-node support

#208 Phuoc-Hoan-Le closed 1 year ago
0
Meaning of the model name ( ResMLP)

#207 YHYeooooong closed 1 year ago
1
Can I use timm==0.4.12 instead of timm==0.3.2 ?

#206 irhallac closed 1 year ago
1
What batch size number other than 1024 have been tried when training a DeiT model?

#205 Phuoc-Hoan-Le opened 1 year ago
0
Multinode Slurm Training

#204 yazdanimehdi closed 1 year ago
0
Does the EMA is used in DeiT-III?

#203 mzr1996 closed 1 year ago
3
What's the accuracy of deit-S without pre-trained on CIFAR10

#202 hanwenran1 closed 1 year ago
1
Are the hyperparameters for DeiT-T and for DeiT-S any different than DeiT-B?

#201 Phuoc-Hoan-Le closed 1 year ago
1
Fix error "TypeError: type object got multiple values for keyword argument"

#200 pablobots closed 1 year ago
0
What is the ImageNet-1K Top-1 accuracy of Training from 0 to 400 epochs (Fig. 5 of Deit III paper)

#199 sanyalsunny111 opened 1 year ago
0
How long is it supposed to take to train on ImageNet21k for 90 epochs with 8 V100 GPUs

#198 Phuoc-Hoan-Le closed 1 year ago
1
number of classes

#197 Ye-Na-Kim closed 1 year ago
1
What is the difference between class attention in the paper CaiT and traditional multi-headed self-attention？

#196 hutingz closed 1 year ago
1
Config file of ViT-B/16

#195 shashankvkt opened 1 year ago
2
Uneven memory usage among GPUs with DistributedDataParallel

#194 Phuoc-Hoan-Le closed 1 year ago
0
Is it possible if I can see how the validation accuracy changes over the number of epochs for DeiT?

#193 Phuoc-Hoan-Le closed 1 year ago
0
Is "unscale-lr" used in DeiT training on ImageNet1k

#192 Phuoc-Hoan-Le closed 1 year ago
0