Readme changes
Browse files- .gitignore +1 -0
- README.md +17 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
__pycache__
|
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
# ONNX models for MobileSAM
|
| 5 |
+
|
| 6 |
+
* Original repository: [MobileSAM (Github)](https://github.com/ChaoningZhang/MobileSAM)
|
| 7 |
+
* Original weights: [MobileSam (HuggingFace)](https://huggingface.co/dhkim2810/MobileSAM)
|
| 8 |
+
|
| 9 |
+
## Models
|
| 10 |
+
|
| 11 |
+
| Model | Description |
|
| 12 |
+
|-|-|
|
| 13 |
+
| mobile_sam_image_encoder.onnx | Image encoder created from MobileSAM weights |
|
| 14 |
+
| sam_mask_decoder_single.onnx | Mask decoder for SegmentAnything, returns a single mask |
|
| 15 |
+
| sam_mask_decoder_multi.onnx | Mask decoder for SegmentAnything, returns 4 masks |
|
| 16 |
+
|
| 17 |
+
## Export
|
| 18 |
+
|
| 19 |
+
The image encoder was exported with `export_image_enoder.py` found in this repository.
|
| 20 |
+
The mask decoders were exported with `export_models.py` from the MobileSAM repository.
|