Instructions to use MedMLX/totalsegmentator-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use MedMLX/totalsegmentator-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download MedMLX/totalsegmentator-mlx --local-dir totalsegmentator-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Document safetensors-ready installation
Browse files
README.md
CHANGED
|
@@ -18,8 +18,11 @@ Native MLX safetensors for TotalSegmentator v2 CT inference on Apple Silicon. Th
|
|
| 18 |
The weights were converted from the [official TotalSegmentator v2.0.0 weight archives](https://github.com/wasserth/TotalSegmentator/releases/tag/v2.0.0-weights) for use with [totalsegmentator-mlx](https://github.com/MedMLX/totalsegmentator-mlx). Conversion changes tensor names and layouts for MLX; the models were not retrained.
|
| 19 |
|
| 20 |
```bash
|
| 21 |
-
uv pip install
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
| 23 |
totalsegmentator-mlx predict -i ct.nii.gz -o mask.nii.gz --model-dir models
|
| 24 |
```
|
| 25 |
|
|
|
|
| 18 |
The weights were converted from the [official TotalSegmentator v2.0.0 weight archives](https://github.com/wasserth/TotalSegmentator/releases/tag/v2.0.0-weights) for use with [totalsegmentator-mlx](https://github.com/MedMLX/totalsegmentator-mlx). Conversion changes tensor names and layouts for MLX; the models were not retrained.
|
| 19 |
|
| 20 |
```bash
|
| 21 |
+
uv pip install \
|
| 22 |
+
"nnunet-mlx @ git+https://github.com/MedMLX/nnunet-mlx.git@33e0188e13fe103db791debcf3c66ea575264790" \
|
| 23 |
+
"totalsegmentator-mlx @ git+https://github.com/MedMLX/totalsegmentator-mlx.git@6b94eb08bf59a8f571c5b13f267d88e8f3069873" \
|
| 24 |
+
huggingface-hub
|
| 25 |
+
hf download MedMLX/totalsegmentator-mlx --revision 6c03d6f90ccf53f224c3985cbdecf1eaa96555af --local-dir models
|
| 26 |
totalsegmentator-mlx predict -i ct.nii.gz -o mask.nii.gz --model-dir models
|
| 27 |
```
|
| 28 |
|