Instructions to use VBoussot/ImpactReg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KonfAI
How to use VBoussot/ImpactReg with KonfAI:
pip install "konfai[imaging]" konfai-apps
# List the apps this repository holds konfai-apps list VBoussot/ImpactReg # Run one of them on an image konfai-apps infer VBoussot/ImpactReg:<app> -i image.nii.gz -o Output
- Notebooks
- Google Colab
- Kaggle
Download FireANTs_IMPACT_MRCT/Prediction_tile.yml from VBoussot/ImpactReg: direct link, hf CLI and curl.
- Browser
- Download file 3.25 kB
-
https://huggingface.co/VBoussot/ImpactReg/resolve/main/FireANTs_IMPACT_MRCT/Prediction_tile.yml
- Command line
-
hf download hf://VBoussot/ImpactReg/FireANTs_IMPACT_MRCT/Prediction_tile.yml
-
curl -L -o Prediction_tile.yml https://huggingface.co/VBoussot/ImpactReg/resolve/main/FireANTs_IMPACT_MRCT/Prediction_tile.yml
3.25 kB
| Predictor: | |
| Model: | |
| classpath: impact_reg_konfai.models.fireants:RegistrationNet | |
| RegistrationNet: | |
| scales: | |
| - 4 | |
| - 2 | |
| - 1 | |
| affine_iterations: | |
| - 200 | |
| - 100 | |
| - 50 | |
| deformable_iterations: | |
| - 200 | |
| - 100 | |
| - 50 | |
| cc_kernel: 5 | |
| affine_metric: mi | |
| affine_lr: 0.03 | |
| deformable_method: syn | |
| deformable_metric: impact | |
| deformable_lr: 0.25 | |
| smooth_warp_sigma: 0.5 | |
| smooth_grad_sigma: 1.0 | |
| seed: 42 | |
| outputs_criterions: None | |
| linear_method: none | |
| models: | |
| '0': | |
| ref: VBoussot/impact-torchscript-models:TS/M730.pt | |
| layers_mask: '0000001' | |
| layers_weight: | |
| - 1.0 | |
| pca: 8 | |
| distance: LNCC | |
| feature_normalization: l2 | |
| '1': | |
| ref: VBoussot/impact-torchscript-models:MIND/R1D2_3D.pt | |
| layers_mask: '1' | |
| layers_weight: | |
| - 1.0 | |
| pca: 6 | |
| distance: LNCC | |
| feature_normalization: l2 | |
| mode: Static | |
| feature_patch: 0 | |
| feature_chunk: 0 | |
| feature_overlap: 0.25 | |
| lncc_kernel: 5 | |
| Dataset: | |
| groups_src: | |
| Volume_0: | |
| groups_dest: | |
| Fixed: | |
| transforms: | |
| TensorCast: | |
| dtype: float32 | |
| inverse: false | |
| patch_transforms: None | |
| is_input: true | |
| Volume_1: | |
| groups_dest: | |
| Moving: | |
| transforms: | |
| TensorCast: | |
| dtype: float32 | |
| inverse: false | |
| patch_transforms: None | |
| is_input: true | |
| Volume_2: | |
| groups_dest: | |
| FixedMask: | |
| transforms: | |
| TensorCast: | |
| dtype: float32 | |
| inverse: false | |
| patch_transforms: None | |
| is_input: true | |
| Volume_3: | |
| groups_dest: | |
| MovingMask: | |
| transforms: | |
| TensorCast: | |
| dtype: float32 | |
| inverse: false | |
| patch_transforms: None | |
| is_input: true | |
| augmentations: | |
| DataAugmentation_0: | |
| data_augmentations: | |
| Flip: | |
| f_prob: | |
| - 0 | |
| - 0.5 | |
| - 0.5 | |
| vector_field: true | |
| prob: 1 | |
| nb: 2 | |
| Patch: | |
| patch_size: | |
| - 0 | |
| - 0 | |
| - 0 | |
| overlap: 20% | |
| pad_value: None | |
| extend_slice: 0 | |
| mode: tile | |
| max_voxels: None | |
| subset: None | |
| dataset_filenames: | |
| - ./Dataset/:mha | |
| batch_size: 1 | |
| num_workers: None | |
| pin_memory: false | |
| prefetch_factor: None | |
| persistent_workers: None | |
| outputs_dataset: | |
| DisplacementField: | |
| OutputDataset: | |
| name_class: OutputDataset | |
| before_reduction_transforms: None | |
| after_reduction_transforms: None | |
| final_transforms: | |
| TensorCast: | |
| dtype: float32 | |
| inverse: false | |
| dataset_filename: Transform:itktransform | |
| group: Transform | |
| same_as_group: Volume_0:Fixed | |
| patch_combine: Cosinus | |
| reduction: Mean | |
| Mean: {} | |
| train_name: ImpactReg-FireANTs-IMPACT-MRCT | |
| manual_seed: 42 | |
| gpu_checkpoints: None | |
| combine: Mean | |
| autocast: false | |
| data_log: None | |