-
[Segment Anything](https://segment-anything.com/) is an image classification model. Research on how to create a extractor that will be able to inference with that model
[Git](https://github.com/facebo…
-
F:\GS+\fenge\GaussianEditor\segment-anything-2\sam2\modeling\sam\transformer.py:23: UserWarning: You are using PyTorch 2.0.1+cu117 without Flash Attention v2 support. Consider upgrading to PyTorch 2.2…
-
Hey,
I can understand that in checkpoint
checkpoints/
├── flux/ # Main Flux model files
├── qwen2-vl/ # Qwen2VL model files
├── controlnet/ # ControlNet model (optio…
-
Is anyone else getting an issue when trying to set up sam2 image ml backend?
I get this after I modify model.py to match my checkpoints and other environmental variables.
```bash
(test-environ…
-
Traceback (most recent call last):
File "d:\software\anaconda3\envs\pytorch\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 92, in _call_target
return _target_(*args, **k…
-
### Model description
I know the transformers library has not included object tracking models in the past, but this one can either plug into any object detection model or be an end-to-end open world …
-
Hello, I'm trying to run Sam2 with docker compose on my local system for video tracking. However, the upstream repo for Segment anything 2 updated the checkpoints to point to Sam2.1 and as a result th…
-
- Here's the summary of consulting a LLM specialist:
---
- We have an initial thought in #74 as follows:
 and [discussions](https://github.com/ultralytics/ultralytics/discussion…