423A35C7/sam2
1
0
Fork 0
mirror of https://github.com/facebookresearch/sam2.git synced 2025-11-04 19:42:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Move HF to separate section

Browse Source
This commit is contained in:
Niels 2024-08-05 22:10:57 +02:00
parent c3393d8b5f
commit e9503c96fe
1 changed files with 20 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
README.md
View File

@ -72,19 +72,6 @@ with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
masks, _, _ = predictor.predict(<input_prompts>)
```
or from Hugging Face, as follows:
```python
import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor
predictor = SAM2ImagePredictor.from_pretrained("facebook/sam2-hiera-large")
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
predictor.set_image(<your_image>)
masks, _, _ = predictor.predict(<input_prompts>)
```
Please refer to the examples in [image_predictor_example.ipynb](./notebooks/image_predictor_example.ipynb) for static image use cases.
SAM 2 also supports automatic mask generation on images just like SAM. Please see [automatic_mask_generator_example.ipynb](./notebooks/automatic_mask_generator_example.ipynb) for automatic mask generation in images.
@ -110,7 +97,26 @@ with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
...
```
or from Hugging Face, as follows:
Please refer to the examples in [video_predictor_example.ipynb](./notebooks/video_predictor_example.ipynb) for details on how to add prompts, make refinements, and track multiple objects in videos.
## Load from Hugging Face
Alternatively, models can also be loaded from Hugging Face using the `from_pretrained` method:
For image prediction:
```python
import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor
predictor = SAM2ImagePredictor.from_pretrained("facebook/sam2-hiera-large")
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
predictor.set_image(<your_image>)
masks, _, _ = predictor.predict(<input_prompts>)
```
For video prediction:
```python
import torch
@ -123,8 +129,6 @@ with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
masks, _, _ = predictor.predict(<input_prompts>)
```
Please refer to the examples in [video_predictor_example.ipynb](./notebooks/video_predictor_example.ipynb) for details on how to add prompts, make refinements, and track multiple objects in videos.
## Model Description
| **Model** | **Size (M)** | **Speed (FPS)** | **SA-V test (J&F)** | **MOSE val (J&F)** | **LVOS v2 (J&F)** |