MCPcopy Create free account

hub / github.com/HealthX-Lab/MedCLIP-SAMv2 / functions

Functions1,090 in github.com/HealthX-Lab/MedCLIP-SAMv2

⨍ Functions 1,090◇ Types & classes 206↳ Endpoints 7
↓ 1 callersMethod__init__
weak_segmentation/nnunetv2/training/loss/dice.py:10
↓ 1 callersMethod__repr__
(self)
weak_segmentation/nnunetv2/utilities/plans_handling/plans_handler.py:194
↓ 1 callersMethod_build_loss
(self)
weak_segmentation/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py:347
↓ 1 callersMethod_build_loss
(self)
weak_segmentation/nnunetv2/training/nnUNetTrainer/variants/network_architecture/nnUNetTrainerNoDeepSupervision.py:13
↓ 1 callersFunction_build_text_decoder_tower
( embed_dim, multimodal_cfg, quick_gelu: bool = False, cast_dtype: Optional[to
biomedclip_finetuning/open_clip/src/open_clip/coca_model.py:55
↓ 1 callersMethod_calc_capacity
(mu, var)
saliency_maps/scripts/iba.py:110
↓ 1 callersFunction_camel2snake
(s)
biomedclip_finetuning/open_clip/src/open_clip/hf_model.py:31
↓ 1 callersFunction_convert_openclip_transformer
(module: Transformer, prefix)
biomedclip_finetuning/open_clip/src/open_clip/convert.py:115
↓ 1 callersMethod_determine_ignore_label
(self)
weak_segmentation/nnunetv2/utilities/label_handling/label_handling.py:101
↓ 1 callersMethod_embed_boxes
Embeds box prompts.
segment-anything/segment_anything/modeling/prompt_encoder.py:93
↓ 1 callersMethod_embed_masks
Embeds mask inputs.
segment-anything/segment_anything/modeling/prompt_encoder.py:102
↓ 1 callersMethod_embed_masks
(self, input_mask: torch.Tensor, has_mask_input: torch.Tensor)
segment-anything/segment_anything/utils/onnx.py:69
↓ 1 callersMethod_embed_points
Embeds point prompts.
segment-anything/segment_anything/modeling/prompt_encoder.py:73
↓ 1 callersMethod_embed_points
(self, point_coords: torch.Tensor, point_labels: torch.Tensor)
segment-anything/segment_anything/utils/onnx.py:51
↓ 1 callersMethod_generate_beamsearch
( self, image_inputs, pad_token_id=None, eos_token_id=None,
biomedclip_finetuning/open_clip/src/open_clip/coca_model.py:329
↓ 1 callersMethod_generate_masks
(self, image: np.ndarray)
segment-anything/segment_anything/automatic_mask_generator.py:197
↓ 1 callersMethod_get_all_labels
(self)
weak_segmentation/nnunetv2/utilities/label_handling/label_handling.py:62
↓ 1 callersMethod_get_batch_size
Gets the batch size of the output given the batch size of the input prompts.
segment-anything/segment_anything/modeling/prompt_encoder.py:107
↓ 1 callersMethod_get_device
(self)
segment-anything/segment_anything/modeling/prompt_encoder.py:125
↓ 1 callersMethod_get_regions
(self)
weak_segmentation/nnunetv2/utilities/label_handling/label_handling.py:77
↓ 1 callersFunction_get_safe_alternatives
Returns potential safetensors alternatives for a given filename. Use case: When downloading a model from the Huggingface Hub, we first lo
biomedclip_finetuning/open_clip/src/open_clip/pretrained.py:708
↓ 1 callersMethod_internal_get_data_iterator_from_lists_of_filenames
(self, input_list_of_lists: List[List[str]],
weak_segmentation/nnunetv2/inference/predict_from_raw_data.py:251
↓ 1 callersMethod_internal_get_sliding_window_slicers
(self, image_size: Tuple[int, ...])
weak_segmentation/nnunetv2/inference/predict_from_raw_data.py:508
↓ 1 callersMethod_internal_maybe_mirror_and_predict
(self, x: torch.Tensor)
weak_segmentation/nnunetv2/inference/predict_from_raw_data.py:542
↓ 1 callersMethod_internal_resolve_configuration_inheritance
(self, configuration_name: str, visited: Tuple[str, ...] =
weak_segmentation/nnunetv2/utilities/plans_handling/plans_handler.py:197
↓ 1 callersMethod_manage_input_and_output_lists
(self, list_of_lists_or_source_folder: Union[str, List[List[str]]], out
weak_segmentation/nnunetv2/inference/predict_from_raw_data.py:150
↓ 1 callersFunction_natural_key
(string_)
biomedclip_finetuning/open_clip/src/open_clip/factory.py:28
↓ 1 callersMethod_normalize
(self, data: np.ndarray, seg: np.ndarray, configuration_manager: ConfigurationManager, fore
weak_segmentation/nnunetv2/preprocessing/preprocessors/default_preprocessor.py:179
↓ 1 callersMethod_process_batch
( self, points: np.ndarray, im_size: Tuple[int, ...], crop_box: List[int],
segment-anything/segment_anything/automatic_mask_generator.py:266
↓ 1 callersMethod_process_crop
( self, image: np.ndarray, crop_box: List[int], crop_layer_idx: int,
segment-anything/segment_anything/automatic_mask_generator.py:225
↓ 1 callersMethod_recombine_heads
(self, x: Tensor)
segment-anything/segment_anything/modeling/transformer.py:213
↓ 1 callersMethod_run_text_training
(self, text_t, image_t)
saliency_maps/scripts/iba.py:161
↓ 1 callersMethod_run_vision_training
(self, text_t, image_t)
saliency_maps/scripts/iba.py:167
↓ 1 callersMethod_sample_foreground_locations
(seg: np.ndarray, classes_or_regions: Union[List[int], List[Tuple[int, ...]]],
weak_segmentation/nnunetv2/preprocessing/preprocessors/default_preprocessor.py:151
↓ 1 callersMethod_sample_t
(mu, noise_var)
saliency_maps/scripts/iba.py:103
↓ 1 callersMethod_sanity_check
(self, label_dict: dict)
weak_segmentation/nnunetv2/utilities/label_handling/label_handling.py:51
↓ 1 callersMethod_save_debug_information
(self)
weak_segmentation/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py:232
↓ 1 callersFunction_setup_size
(size, error_msg)
biomedclip_finetuning/open_clip/src/open_clip/transform.py:75
↓ 1 callersFunctionaccuracy
(output, target, topk=(1,))
biomedclip_finetuning/open_clip/src/open_clip_train/zero_shot.py:11
↓ 1 callersFunctionadd_decomposed_rel_pos
Calculate decomposed Relative Positional Embeddings from :paper:`mvitv2`. https://github.com/facebookresearch/mvit/blob/19786631e330df9f362
segment-anything/segment_anything/modeling/image_encoder.py:325
↓ 1 callersMethodapply_boxes
Expects a numpy array shape Bx4. Requires the original image size in (H, W) format.
segment-anything/segment_anything/utils/transforms.py:47
↓ 1 callersMethodapply_image
Expects a numpy array with shape HxWxC in uint8 format.
segment-anything/segment_anything/utils/transforms.py:26
↓ 1 callersFunctionapply_postprocessing
(segmentation: np.ndarray, pp_fns: List[Callable], pp_fn_kwargs: List[dict])
weak_segmentation/nnunetv2/postprocessing/remove_connected_components.py:37
↓ 1 callersFunctionarea_from_rle
(rle: Dict[str, Any])
segment-anything/segment_anything/utils/amg.py:152
↓ 1 callersMethodauto_detect_available_folds
(model_training_output_dir, checkpoint_name)
weak_segmentation/nnunetv2/inference/predict_from_raw_data.py:141
↓ 1 callersFunctionaverage_probabilities
(list_of_files: List[str])
weak_segmentation/nnunetv2/ensembling/ensemble.py:17
↓ 1 callersFunctionbatch_iterator
(batch_size: int, *args)
segment-anything/segment_anything/utils/amg.py:98
↓ 1 callersFunctionbatched
Batch data into lists of length *n*. The last batch may be shorter. NOTE based on more-itertools impl, to be replaced by python 3.12 itertools.bat
biomedclip_finetuning/open_clip/src/open_clip/zero_shot_classifier.py:9
↓ 1 callersMethodbpe
(self, token)
biomedclip_finetuning/open_clip/src/open_clip/tokenizer.py:172
↓ 1 callersFunctionbuild_all_layer_point_grids
Generates point grids for all crop layers.
segment-anything/segment_anything/utils/amg.py:188
↓ 1 callersMethodbuild_attention_mask
(self)
biomedclip_finetuning/open_clip/src/open_clip/transformer.py:878
↓ 1 callersMethodbuild_causal_mask
(self)
biomedclip_finetuning/open_clip/src/open_clip/transformer.py:762
↓ 1 callersMethodbuild_cls_mask
(self, text, cast_dtype: torch.dtype)
biomedclip_finetuning/open_clip/src/open_clip/transformer.py:770
↓ 1 callersMethodbuild_network_architecture
(plans_manager: PlansManager, dataset_json,
weak_segmentation/nnunetv2/training/nnUNetTrainer/variants/network_architecture/nnUNetTrainerBN.py:15
↓ 1 callersFunctionbuild_point_grid
Generates a 2D grid of points evenly spaced in [0,1]x[0,1].
segment-anything/segment_anything/utils/amg.py:179
↓ 1 callersFunctionbuild_zero_shot_classifier
Build zero-shot classifier weights by iterating over class names in batches Args: model: CLIP model instance tokenizer: CLIP toke
biomedclip_finetuning/open_clip/src/open_clip/zero_shot_classifier.py:21
↓ 1 callersFunctioncalculate_dice_coefficient
(mask1, mask2)
saliency_maps/generate_saliency_maps.py:28
↓ 1 callersFunctioncenter_crop_or_pad
Center crops and/or pads the given image. If the image is torch Tensor, it is expected to have [..., H, W] shape, where ... means an arbitrary
biomedclip_finetuning/open_clip/src/open_clip/transform.py:167
↓ 1 callersFunctioncleanup_ddp
()
weak_segmentation/nnunetv2/run/run_training.py:113
↓ 1 callersFunctionclip_loss
(similarity: torch.Tensor)
saliency_maps/model/modeling_biomed_clip.py:70
↓ 1 callersFunctioncoco_encode_rle
(uncompressed_rle: Dict[str, Any])
segment-anything/segment_anything/utils/amg.py:293
↓ 1 callersMethodcollect_foreground_intensities
images=image with multiple channels = shape (c, x, y(, z))
weak_segmentation/nnunetv2/experiment_planning/dataset_fingerprint/fingerprint_extractor.py:42
↓ 1 callersFunctioncollect_results
(trainers: dict, datasets: List, output_file: str, configurations=("2d", "3d_fullres", "3d
weak_segmentation/nnunetv2/batch_running/release_trainings/nnunetv2_v1/collect_results.py:12
↓ 1 callersFunctioncompute_dice_coefficient
Compute soerensen-dice coefficient. compute the soerensen-dice coefficient between the ground truth mask `mask_gt` and the predicted mask `mas
evaluation/SurfaceDice.py:481
↓ 1 callersFunctioncompute_dice_coefficient
Compute soerensen-dice coefficient. compute the soerensen-dice coefficient between the ground truth mask `mask_gt` and the predicted mask `mask_p
weak_segmentation/nnunetv2/evaluation/SurfaceDice.py:481
↓ 1 callersFunctioncompute_metrics_on_folder2
(folder_ref: str, folder_pred: str, dataset_json_file: str, plans_file: str, ou
weak_segmentation/nnunetv2/evaluation/evaluate_predictions.py:179
↓ 1 callersFunctioncompute_metrics_on_folder_simple
(folder_ref: str, folder_pred: str, labels: Union[Tuple[int, ...], List[int]],
weak_segmentation/nnunetv2/evaluation/evaluate_predictions.py:201
↓ 1 callersFunctioncompute_surface_dice_at_tolerance
(surface_distances, tolerance_mm)
evaluation/SurfaceDice.py:469
↓ 1 callersFunctioncompute_surface_dice_at_tolerance
(surface_distances, tolerance_mm)
weak_segmentation/nnunetv2/evaluation/SurfaceDice.py:469
↓ 1 callersFunctioncompute_surface_distances
Compute closest distances from all surface points to the other surface. Finds all surface elements "surfels" in the ground truth mask `mask_gt` a
evaluation/SurfaceDice.py:280
↓ 1 callersFunctioncompute_surface_distances
Compute closest distances from all surface points to the other surface. Finds all surface elements "surfels" in the ground truth mask `mask_gt` and
weak_segmentation/nnunetv2/evaluation/SurfaceDice.py:280
↓ 1 callersFunctioncompute_tp_fp_fn_tn
(mask_ref: np.ndarray, mask_pred: np.ndarray, ignore_mask: np.ndarray = None)
weak_segmentation/nnunetv2/evaluation/evaluate_predictions.py:77
↓ 1 callersMethodconfigure_optimizers
(self)
weak_segmentation/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py:466
↓ 1 callersMethodconfigure_optimizers
(self)
weak_segmentation/nnunetv2/training/nnUNetTrainer/variants/optimizer/nnUNetTrainerAdan.py:13
↓ 1 callersMethodconfigure_rotation_dummyDA_mirroring_and_inital_patch_size
This function is stupid and certainly one of the weakest spots of this implementation. Not entirely sure how we can fix it.
weak_segmentation/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py:372
↓ 1 callersMethodconfigure_rotation_dummyDA_mirroring_and_inital_patch_size
(self)
weak_segmentation/nnunetv2/training/nnUNetTrainer/variants/data_augmentation/nnUNetTrainerNoMirroring.py:5
↓ 1 callersFunctionconst_lr
(optimizer, base_lr, warmup_length, steps)
biomedclip_finetuning/open_clip/src/open_clip_train/scheduler.py:13
↓ 1 callersFunctionconst_lr_cooldown
(optimizer, base_lr, warmup_length, steps, cooldown_steps, cooldown_power=1.0, cooldown_end_lr=0.)
biomedclip_finetuning/open_clip/src/open_clip_train/scheduler.py:24
↓ 1 callersFunctionconvert
remember that old tasks were called TaskXXX_YYY and new ones are called DatasetXXX_YYY source_folder
weak_segmentation/nnunetv2/dataset_conversion/convert_raw_dataset_from_old_nnunet_format.py:8
↓ 1 callersFunctionconvert_acdc
(src_data_folder: str, dataset_id=27)
weak_segmentation/nnunetv2/dataset_conversion/Dataset027_ACDC.py:51
↓ 1 callersFunctionconvert_amos_task1
AMOS doesn't say anything about how the validation set is supposed to be used. So we just incorporate that into the train set. Having a 5-fol
weak_segmentation/nnunetv2/dataset_conversion/Dataset218_Amos2022_task1.py:7
↓ 1 callersFunctionconvert_amos_task2
AMOS doesn't say anything about how the validation set is supposed to be used. So we just incorporate that into the train set. Having a 5-fol
weak_segmentation/nnunetv2/dataset_conversion/Dataset219_Amos2022_task2.py:7
↓ 1 callersFunctionconvert_ensemble_folder_to_model_identifiers_and_folds
(ensemble_folder: str)
weak_segmentation/nnunetv2/utilities/file_path_utilities.py:73
↓ 1 callersFunctionconvert_int8_model_to_inference_mode
(model)
biomedclip_finetuning/open_clip/src/open_clip/utils.py:84
↓ 1 callersFunctionconvert_kits2023
(kits_base_dir: str, nnunet_dataset_id: int = 220)
weak_segmentation/nnunetv2/dataset_conversion/Dataset220_KiTS2023.py:7
↓ 1 callersFunctionconvert_labels_back_to_BraTS
(seg: np.ndarray)
weak_segmentation/nnunetv2/dataset_conversion/Dataset137_BraTS21.py:32
↓ 1 callersFunctionconvert_state_dict
(state_dict)
saliency_maps/model/convert.py:83
↓ 1 callersFunctionconvert_state_dict
(model: Union[CustomTextCLIP, CLIP], state_dict)
biomedclip_finetuning/open_clip/src/open_clip/convert.py:193
↓ 1 callersFunctionconvert_to_custom_text_state_dict
(state_dict: dict)
biomedclip_finetuning/open_clip/src/open_clip/model.py:432
↓ 1 callersFunctionconvert_trainer_plans_config_to_identifier
(trainer_name, plans_identifier, configuration)
weak_segmentation/nnunetv2/utilities/file_path_utilities.py:11
↓ 1 callersFunctioncopy_BraTS_segmentation_and_convert_labels_to_nnUNet
(in_file: str, out_file: str)
weak_segmentation/nnunetv2/dataset_conversion/Dataset137_BraTS21.py:12
↓ 1 callersFunctioncopy_codebase
(args)
biomedclip_finetuning/open_clip/src/open_clip_train/main.py:502
↓ 1 callersFunctioncopy_files
Copy files from the ACDC dataset to the nnUNet dataset folder. Returns the number of training cases.
weak_segmentation/nnunetv2/dataset_conversion/Dataset027_ACDC.py:25
↓ 1 callersFunctioncosine_lr
(optimizer, base_lr, warmup_length, steps)
biomedclip_finetuning/open_clip/src/open_clip_train/scheduler.py:43
↓ 1 callersFunctioncreate_loss
(args)
biomedclip_finetuning/open_clip/src/open_clip/factory.py:417
↓ 1 callersFunctioncreate_nonzero_mask
:param data: :return: the mask is True where the data is nonzero
weak_segmentation/nnunetv2/preprocessing/cropping/cropping.py:8
↓ 1 callersFunctioncreate_random_image_data
(path, size, batches = 1, batch_size = 1)
biomedclip_finetuning/open_clip/tests/util_test.py:91
↓ 1 callersFunctioncreate_random_text_data
( path, min_length = 75, max_length = 75, batches = 1, batch_size = 1
biomedclip_finetuning/open_clip/tests/util_test.py:77
↓ 1 callersFunctioncreate_test_data
( models, batches = 1, batch_size = 1, overwrite = False )
biomedclip_finetuning/open_clip/tests/util_test.py:172
↓ 1 callersFunctioncreate_test_data_for_model
( model_name, pretrained = None, precision = 'fp32', jit = False, pret
biomedclip_finetuning/open_clip/tests/util_test.py:110
← previousnext →301–400 of 1,090, ranked by callers