-
When I executed `python demos/test_emotion_recognition_on_images.py --model_type 3dmm --model_name EMOCA-emorec`, it showed `AttributeError: 'NoneType' object has no attribute 'train'`. Then I looked …
-
Hi, I'm trying to use the best model which is downloaded from the dropbox link. I'm trying to do inference only without any training.
After downloading and unzipping the files, the issue mentioned in…
-
## 🐛 Bug
I have been using a torchvision densenet121 with PT1.4+ APEX/AMP for mixed precision training. Today, I tried to migrate my code to PT1.7 and to native mixed precision (amp).
In short,…
-
Hi everyone!
I trained an inception model with my custom images (dataset of 8.000 images), then saved it.
And when I try to make predictions with it, whatever is the input images to predict, it's th…
-
```
python3 -m scripts.triviaqa --train_dataset $QA_PATH/processed/squad-wikipedia-train-4096.json \
--dev_dataset $QA_PATH/processed/squad-wikipedia-dev-4096.json \
--gpus 0 --num_work…
-
Distribution Name | archlinux
Distribution Version | rolling
Linux Kernel | 5.4.0-rc1-mainline
Architecture | x86_64
ZFS Version | 0.8.2
SPL Version | 0.8.2
### Describe the problem you'r…
-
 on how to do speculative decoding with vLLM.
H…
-
Hi, thanks for sharing the work! During the training a CUDA error happened after 49450 steps with batch size of 3.
cudahash: Completely failed to build
Cuda error in file '/home/hjus/spconv/src/cuha…
-
Hi @ducminhkhoi , It is a great contribution to few shot incremental object detection problem. I am trying to replicate the results that given in the paper. I am getting following issue.
1. While r…