-
Dear authors,
I would like to run T2T on ImageNet100 on 2 gpus. But I have gotten just 8.5 in top-1 accuracy after 200 epochs! Also the train loss is high. Do you know what can be a reason for that…
-
Now I realize that the released models and the model from the [keras code examples](https://keras.io/examples/nlp/nl_image_search/) are different, and are possibly trained differently. As far as I ca…
-
Thank you so much for sharing your codes. I try to employ Vit as the encoder and follow a common decoder to build a segmentation network. I train it from scratch but found the loss can't drop since th…
-
I recently experienced a weird issue wherein the open-source app Kore was reported by AFWall+ to be sending pings to sites like walmart.com, among others: https://github.com/xbmc/Kore/issues/434
He…
-
Thank you so much for sharing your codes. I try to employ Vit as the encoder and follow a common decoder to build a segmentation network. I train it from scratch but found the loss can't drop since th…
-
pRO will be launching today for CBT let's all be updated for the new 3rd party programs we can use.... FF
-
First, thanks for sharing codes and the pretrained models.
I have a question related to #2
As you replied,
> Note that for the published checkpoints we pretrained on imagenet21k (see README),…
-
Thanks for your excellent job! I want follow your job in remote-sensing.
My dataset just like [DOTA](https://captain-whu.github.io/DOTA/index.html). And the task is multi-label classification.
But …
-
Thanks for making ViT models available! Do you plan to opensource the hybrid models as well? If so, any idea on when it will be available by?
-
## 🐛 Bug
### To Reproduce
```python
import argparse
import torch
import wandb
import sys
# import apex
import torchmetrics
import pytorch_lightning as pl
import kornia.augmentatio…