-
It seems that the examples here are all examples of inference, where are the examples of training？
-
Hi,
I am trying to launch `dinov2/train/train.py` script directly without the Slurm scheduler. I use the following command to launch the training:
```
export CUDA_VISIBLE_DEVICES=0,1 && python dino…
-
Thanks for your valuable work.
I have a question.
` loss2 =label2*(torch.min(cam_1,cam_2).mean(dim=1)-0.1*torch.max(cam_1,cam_2))`
The shape of the loss function does not match, so errors con…
-
I am facing a very weird issue here.
### Issue
- The training speed slows down with time for batch sizes 64 and 128. For batch size 32 it seems to be staying fairly constant.
- The tensorboard g…
-
Should we train the Discrete autoencoder or the Continuous autoencoder first? If we train the Continuous autoencoder first, So what does -finetune_model [PATH TO CONTINUOUS MODEL] mean
-
Epoch 1, Batch 3, Loss: 7.225614070892334
Train step: 2it [00:05, 2.95s/it]
Traceback (most recent call last):
File "/mnt/e/code/silent_speech/transduction_model.py", line 365, in
main()
…
-
I don't know where the trained models are that you published in your paper with. Where can I find those? Or are we supposed to train it on all semantic kitti data to get our own models?
Also how do…
-
**What can it be used for?**
We currently have `fa-train` for train icons. It would be great tohave a separate icon for high speed trains with their distinctive look as found in Europe or Asia.
**…
-
Hello! The run log of train.py shows that AVG ACC is always close to 0, e.g. 0.0, 0.05, is this normal? Thanks!
bieyl updated
2 months ago
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
][INFO|trainer.py:4117] 2024-11-29 00:18:59,105 >>
***** Running Evaluation *****
[INFO|trainer.py:4119…