Giters
facebookresearch
/
deit
Official DeiT repository
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
3911
Watchers:
49
Issues:
197
Forks:
545
facebookresearch/deit Issues
ViT-B Training for DeiT
Closed
3 months ago
Comments count
2
Will you be releasing the accuracy of the official deit III framework trained tiny version on IN1k?
Updated
4 months ago
DeiT depth 24 (CaiT - TABLE 1)
Closed
4 months ago
Comments count
2
Gradient accumulation code
Updated
4 months ago
Question about different seeds per gpu with DDP
Updated
4 months ago
Training
Updated
5 months ago
Inclusion of Transformers Need Registers
Updated
7 months ago
Slow Training
Closed
8 months ago
Comments count
2
random.seed(seed) in line 205 is commented
Updated
8 months ago
Checkpoints of IN21K pretrained deit III
Updated
10 months ago
Hi,Why can't I find deit_tiny_distilled_patch16_224 in hubconf
Updated
10 months ago
TracerWarning
Updated
10 months ago
batch_size flag
Updated
10 months ago
Comments count
2
how to implement document layout analysis use Deit-B
Closed
a year ago
Comments count
2
How to launch a training of CAIT models ?
Updated
a year ago
Code for cosub
Closed
a year ago
The ablation experiment of DeiT
Updated
a year ago
Comments count
2
ImageNet21K data preparation for pre-training
Updated
a year ago
Comments count
5
Meaning of the model name ( ResMLP)
Closed
a year ago
Comments count
1
Can I use timm==0.4.12 instead of timm==0.3.2 ?
Closed
a year ago
Comments count
1
unexpected keyword argument 'pretrained_cfg'
Closed
a year ago
Comments count
2
Are the hyperparameters for DeiT-T and for DeiT-S any different than DeiT-B?
Closed
a year ago
Comments count
1
ImageNet21k pretrained model without finetuning on 1k
Closed
a year ago
Comments count
2
How long is it supposed to take to train on ImageNet21k for 90 epochs with 8 V100 GPUs
Closed
a year ago
Comments count
1
number of classes
Closed
a year ago
Comments count
1
What's the accuracy of deit-S without pre-trained on CIFAR10
Closed
a year ago
Comments count
1
how to implement cosub training use deit-III
Updated
a year ago
Comments count
2
What are the hyperparameters for DeiT-III (epoch 400 or 600)?
Closed
a year ago
how to implement cosub training use deit-III
Closed
a year ago
Single machine multi-GPU training
Updated
a year ago
Multi-node support
Closed
a year ago
Multinode Slurm Training
Closed
a year ago
What batch size number other than 1024 have been tried when training a DeiT model?
Updated
a year ago
Does the EMA is used in DeiT-III?
Closed
a year ago
Comments count
3
Question about Throughput
Closed
2 years ago
Comments count
1
cifar100 pretrain model?
Closed
2 years ago
Comments count
1
The concatenation of 'cls_tokens' and 'patch_embedding' is not necceassay.
Closed
2 years ago
Comments count
1
What is the difference between class attention in the paper CaiT and traditional multi-headed self-attention?
Closed
2 years ago
Comments count
1
What is the ImageNet-1K Top-1 accuracy of Training from 0 to 400 epochs (Fig. 5 of Deit III paper)
Updated
2 years ago
Config file of ViT-B/16
Updated
2 years ago
Comments count
2
Object detection from the DeiT III pretrained model
Closed
2 years ago
Comments count
2
Uneven memory usage among GPUs with DistributedDataParallel
Closed
2 years ago
Is it possible if I can see how the validation accuracy changes over the number of epochs for DeiT?
Closed
2 years ago
Is "unscale-lr" used in DeiT training on ImageNet1k
Closed
2 years ago
Reproduce PatchConvnet
Closed
2 years ago
Comments count
2
LAMB and amp
Closed
2 years ago
Comments count
1
Question about training DeiT-small distilled
Closed
2 years ago
Comments count
2
Is uniform drop-path rates beneficial ?
Closed
2 years ago
Comments count
2
DeiT-tiny pth size is not 5M, it is 22M
Closed
2 years ago
Comments count
1
Confusion about fine-tuning
Closed
2 years ago
Comments count
4
Previous
Next