Functions — github.com/JunMa11/SegLossOdyssey

CodeHub MCPcopy Create free account

hub / github.com/JunMa11/SegLossOdyssey / functions

Functions250 in github.com/JunMa11/SegLossOdyssey

⨍ Functions 250◇ Types & classes 108

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV1/network_training/nnUNetTrainer_TopK10.py:6

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV1/network_training/nnUNetTrainer_ExpLog.py:7

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV1/network_training/nnUNetTrainerWCE.py:7

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV1/network_training/nnUNetTrainer_Iou.py:7

(self, weight=None)

test/nnUNetV1/loss_functions/ND_Crossentropy.py:110

Generalized Dice; Copy from: https://github.com/LIVIAETS/surface-loss/blob/108bd9892adca476e6cdf424124bc6268707498e/losses.py#L29

test/nnUNetV1/loss_functions/dice_loss.py:79

Generalized Dice; Copy from: https://github.com/wolny/pytorch-3dunet/blob/6e5a24b6438f8c631289c10638a17dea14d42051/unet3d/losses.py#L

test/nnUNetV1/loss_functions/dice_loss.py:138

Drozdzal et al. https://arxiv.org/abs/1608.04117

test/nnUNetV1/loss_functions/dice_loss.py:250

paper: Milletari et al. https://arxiv.org/abs/1606.04797

test/nnUNetV1/loss_functions/dice_loss.py:320

paper: https://link.springer.com/chapter/10.1007/978-3-319-50835-1_22

test/nnUNetV1/loss_functions/dice_loss.py:360

paper: https://arxiv.org/pdf/1706.05721.pdf

test/nnUNetV1/loss_functions/dice_loss.py:400

(self, tversky_kwargs, gamma=0.75)

test/nnUNetV1/loss_functions/dice_loss.py:445

paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8573779

test/nnUNetV1/loss_functions/dice_loss.py:457

(self, soft_dice_kwargs, ce_kwargs, aggregate="sum")

test/nnUNetV1/loss_functions/dice_loss.py:496

(self, gdice_kwargs)

test/nnUNetV1/loss_functions/dice_loss.py:515

(self, soft_dice_kwargs, ce_kwargs, aggregate="sum")

test/nnUNetV1/loss_functions/dice_loss.py:529

(self, soft_dice_kwargs, wce_kwargs, gamma=0.3)

test/nnUNetV1/loss_functions/dice_loss.py:551

(self, soft_dice_kwargs, focal_kwargs)

test/nnUNetV1/loss_functions/dice_loss.py:572

(self, reduction='mean')

test/nnUNetV1/loss_functions/lovasz_loss.py:23

test/nnUNetV1/loss_functions/boundary_loss.py:65

(self, soft_dice_kwargs, bd_kwargs, aggregate="sum")

test/nnUNetV1/loss_functions/boundary_loss.py:177

compute haudorff loss for binary segmentation https://arxiv.org/pdf/1904.10030v1.pdf

test/nnUNetV1/loss_functions/boundary_loss.py:237

(self, soft_dice_kwargs, hd_kwargs, aggregate="sum")

test/nnUNetV1/loss_functions/boundary_loss.py:287

(self, apply_nonlin=None, alpha=None, gamma=2, balance_index=0, smooth=1e-5, size_average=True)

test/nnUNetV1/loss_functions/focal_loss.py:22

(self, weight=None, ignore_index=-100, k=10)

test/nnUNetV1/loss_functions/TopK_loss.py:24

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV2/network_training/nnUNetTrainerV2_Loss_TopK10.py:21

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV2/network_training/nnUNetTrainerV2_Loss_DiceTopK10CE.py:21

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV2/network_training/nnUNetTrainerV2_Loss_DiceFocal.py:6

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV2/network_training/nnUNetTrainerV2_Loss_CE.py:19

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV2/network_training/nnUNetTrainerV2_Loss_DiceTopK10Focal.py:21

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV2/network_training/nnUNetTrainerV2_Loss_Dice.py:22

(self, plans_file, fold, output_folder=None, dataset_directory=None, batch_dice=True, stage=None,

test/nnUNetV2/network_training/nnUNetTrainerV2_Loss_DiceTopK10.py:21

test/nnUNetV2/loss_functions/dice_loss.py:160

test/nnUNetV2/loss_functions/dice_loss.py:199

based on matthews correlation coefficient https://en.wikipedia.org/wiki/Matthews_correlation_coefficient Does not work. Real

test/nnUNetV2/loss_functions/dice_loss.py:239

squares the terms in the denominator as proposed by Milletari et al.

test/nnUNetV2/loss_functions/dice_loss.py:287

CAREFUL. Weights for CE and Dice do not need to sum to one. You can set whatever you want. :param soft_dice_kwargs: :param ce

test/nnUNetV2/loss_functions/dice_loss.py:346

DO NOT APPLY NONLINEARITY IN YOUR NETWORK! THIS LOSS IS INTENDED TO BE USED FOR BRATS REGIONS ONLY :param soft_dice_kwargs:

test/nnUNetV2/loss_functions/dice_loss.py:406

(self, gdl_dice_kwargs, ce_kwargs, aggregate="sum")

test/nnUNetV2/loss_functions/dice_loss.py:434

(self, soft_dice_kwargs, ce_kwargs, aggregate="sum", square_dice=False)

test/nnUNetV2/loss_functions/dice_loss.py:451

(self, soft_dice_kwargs, focal_kwargs)

test/nnUNetV2/loss_functions/dice_loss.py:471

(self, soft_dice_kwargs, topk_kwargs, ce_kwargs, aggregate="sum", square_dice=False)

test/nnUNetV2/loss_functions/dice_loss.py:485

(self, soft_dice_kwargs, topk_kwargs, focal_kwargs, aggregate="sum", square_dice=False)

test/nnUNetV2/loss_functions/dice_loss.py:507

(self, apply_nonlin=None, alpha=None, gamma=2, balance_index=0, smooth=1e-5, size_average=True)

test/nnUNetV2/loss_functions/focal_loss.py:22

(self, weight=None, ignore_index=-100, k=10)

test/nnUNetV2/loss_functions/TopK_loss.py:24

(self, alpha=2.0, erosions=10, **kwargs)

losses_pytorch/hausdorff.py:86

(self, weight=None)

losses_pytorch/ND_Crossentropy.py:54

Generalized Dice; Copy from: https://github.com/LIVIAETS/surface-loss/blob/108bd9892adca476e6cdf424124bc6268707498e/losses.py#L29

losses_pytorch/dice_loss.py:85

Generalized Dice; Copy from: https://github.com/wolny/pytorch-3dunet/blob/6e5a24b6438f8c631289c10638a17dea14d42051/unet3d/losses.py

losses_pytorch/dice_loss.py:144

paper: https://arxiv.org/pdf/1606.04797.pdf

losses_pytorch/dice_loss.py:256

paper: https://link.springer.com/chapter/10.1007/978-3-319-50835-1_22

losses_pytorch/dice_loss.py:294

paper: https://arxiv.org/pdf/1706.05721.pdf

losses_pytorch/dice_loss.py:334

(self, tversky_kwargs, gamma=0.75)

losses_pytorch/dice_loss.py:379

paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8573779

losses_pytorch/dice_loss.py:391

(self, soft_dice_kwargs, ce_kwargs, aggregate="sum")

losses_pytorch/dice_loss.py:430

(self, gdice_kwargs)

losses_pytorch/dice_loss.py:449

(self, soft_dice_kwargs, ce_kwargs, aggregate="sum")

losses_pytorch/dice_loss.py:463

(self, soft_dice_kwargs, wce_kwargs, gamma=0.3)

losses_pytorch/dice_loss.py:485

(self, reduction='mean')

losses_pytorch/lovasz_loss.py:23

losses_pytorch/boundary_loss.py:110

(self, soft_dice_kwargs, bd_kwargs, aggregate="sum")

losses_pytorch/boundary_loss.py:148

(self, smooth=1e-5)

losses_pytorch/boundary_loss.py:198

(self, apply_nonlin=None, alpha=None, gamma=2, balance_index=0, smooth=1e-5, size_average=True)

losses_pytorch/focal_loss.py:22

Functioncompute_edts_forhdloss

losses_pytorch/boundary_loss.py:164

stolen and adapted from here: https://sgugger.github.io/how-do-you-find-a-good-learning-rate.html :param num_iters: :param in

test/nnUNetV1/network_training/network_trainer.py:556

Methodfinish_online_evaluation

test/nnUNetV1/network_training/nnUNetTrainer.py:558

Functionflatten

Flattens a given tensor such that the channel axis is first. The shapes are transformed as follows: (N, C, D, H, W) -> (C, N * D * H * W)

test/nnUNetV1/loss_functions/ND_Crossentropy.py:193

Functionflatten

Flattens a given tensor such that the channel axis is first. The shapes are transformed as follows: (N, C, D, H, W) -> (C, N * D * H * W)

losses_pytorch/ND_Crossentropy.py:137

(self, inp, target)

test/nnUNetV1/loss_functions/ND_Crossentropy.py:28

(self, inp, target)

test/nnUNetV1/loss_functions/ND_Crossentropy.py:51

(self, inp, target)

test/nnUNetV1/loss_functions/ND_Crossentropy.py:114

(self, net_output, gt)

test/nnUNetV1/loss_functions/ND_Crossentropy.py:141

(self, inp, target)

test/nnUNetV1/loss_functions/ND_Crossentropy.py:231

(self, net_output, gt)

test/nnUNetV1/loss_functions/dice_loss.py:91

(self, net_output, gt)

test/nnUNetV1/loss_functions/dice_loss.py:150

(self, net_output, gt, loss_mask=None)

test/nnUNetV1/loss_functions/dice_loss.py:203

(self, x, y, loss_mask=None)

test/nnUNetV1/loss_functions/dice_loss.py:263

test/nnUNetV1/loss_functions/dice_loss.py:331

(self, x, y, loss_mask=None)

test/nnUNetV1/loss_functions/dice_loss.py:374

(self, x, y, loss_mask=None)

test/nnUNetV1/loss_functions/dice_loss.py:415

(self, net_output, target)

test/nnUNetV1/loss_functions/dice_loss.py:450

(self, x, y, loss_mask=None)

test/nnUNetV1/loss_functions/dice_loss.py:471

(self, net_output, target)

test/nnUNetV1/loss_functions/dice_loss.py:502

(self, net_output, target)

test/nnUNetV1/loss_functions/dice_loss.py:520

(self, net_output, target)

test/nnUNetV1/loss_functions/dice_loss.py:535

(self, net_output, target)

test/nnUNetV1/loss_functions/dice_loss.py:557

(self, net_output, target)

test/nnUNetV1/loss_functions/dice_loss.py:577

(self, inputs, targets)

test/nnUNetV1/loss_functions/lovasz_loss.py:62

(self, x, y, loss_mask=None)

test/nnUNetV1/loss_functions/boundary_loss.py:78

net_output: (batch_size, class, x,y,z) target: ground truth, shape: (batch_size, 1, x,y,z) bound: precomputed distance map, s

test/nnUNetV1/loss_functions/boundary_loss.py:141

(self, net_output, target)

test/nnUNetV1/loss_functions/boundary_loss.py:184

net_output: (batch_size, c, x,y,z) target: ground truth, shape: (batch_size, c, x,y,z)

test/nnUNetV1/loss_functions/boundary_loss.py:245

(self, net_output, target)

test/nnUNetV1/loss_functions/boundary_loss.py:293

(self, logit, target)

test/nnUNetV1/loss_functions/focal_loss.py:35

(self, inp, target)

test/nnUNetV1/loss_functions/TopK_loss.py:28

(self, x, y, loss_mask=None)

test/nnUNetV2/loss_functions/dice_loss.py:41

(self, x, y, loss_mask=None)

test/nnUNetV2/loss_functions/dice_loss.py:170

(self, x, y, loss_mask=None)

test/nnUNetV2/loss_functions/dice_loss.py:209

(self, x, y, loss_mask=None)

test/nnUNetV2/loss_functions/dice_loss.py:253

(self, x, y, loss_mask=None)

test/nnUNetV2/loss_functions/dice_loss.py:298

← previous next →101–200 of 250, ranked by callers