-
I'm getting the following error when I try to infer from an image.
+ NUM_GPUS=1
+ JOB_NAME=painter_vit_large
+ CKPT_FILE=painter_vit_large.pth
+ PROMPT=ADE_train_00001098
+ SIZE=448
+ MODEL=pa…
-
Trainer fails when you define a **custom_metric**, even for small models and small batch sizes. I tried different metrics as well, but it always fails. If you remove the custom_metric everything works…
-
Hi, thanks for sharing the code! I am trying to reproduce the results and have some problems.
Below are my steps to train a model on the _DailyDialog_ corpus and evaluate it on the _DialSeg_711_ da…
-
Thanks for your working
I want to get boundingbox each block likes [this](https://github.com/VikParuchuri/surya/blob/master/static/images/excerpt_layout.png). I ran detect_layout.py and drew polygo…
-
When running 'bash run_eval.sh $PATH_TO_CFG $PATH_TO_CKPT $GPU_NUM --show --show-dir $PATH' to save occupancy predictions, i got the error KeyError:['visible_mask'].
![image](https://github.com/Jef…
-
Hi all,
Thanks for the wonderful work.
I am currently running code_bert_score to evaluate the similarity between generated code and 'correct' code. However, it just takes way too long locally. …
-
### System Info
Different batch sizes result in inconsistent predicted probabilities when using the trainer for regression task predictions.
How to get the consistent result?
Also, How to get consi…
-
I use the [docker image](https://github.com/albertqjiang/Portal-to-ISAbelle/blob/main/docker/docker_tutorial.md) from the PISA repository and the prediction file from output.zip of your repository(pat…
-
Hi,
I have trouble loading the `EquiformerV2-IS2RE-ODAC` and `Gemnet-OC-IS2RE-ODAC` pretrained models.
With `fairchem-core==1.2.0`, if I run
```python
model_name = "EquiformerV2-IS2RE-ODAC"
c…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussi…