Functions — github.com/HXY-99/brats

CodeHub MCPcopy Create free account

hub / github.com/HXY-99/brats / functions

Functions121 in github.com/HXY-99/brats

⨍ Functions 121◇ Types & classes 26

↓ 13 callersFunctionDice

(output, target, eps=1e-5)

model/criterions.py:43

↓ 10 callersFunctionmap_

(fn: Callable[[A], B], iter: Iterable[A])

↓ 8 callersMethod__init__

(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)

model/swintransformer.py:20

↓ 8 callersFunctionsset

(a: Tensor, sub: Iterable)

↓ 7 callersFunctionone_hot

(t: Tensor, axis=1)

↓ 3 callersFunctionsimplex

(t: Tensor, axis=1)

↓ 3 callersFunctionwindow_partition

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size,

model/swintransformer.py:38

↓ 2 callersMethod__init__

(self, in_channels)

model/edge.py:66

↓ 2 callersMethod__init__

(self, num_feature, num_node, bias=False)

model/graph.py:8

↓ 2 callersFunctionclass2one_hot

(seg: Tensor, K: int)

↓ 2 callersFunctionexpand_target

Converts NxDxHxW label image to NxCxDxHxW, where each label is stored in a separate channel :param input: 4D input image (NxDxHxW)

model/criterions.py:8

↓ 2 callersFunctionflatten

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)

model/criterions.py:30

↓ 2 callersFunctionintersection

(a: Tensor, b: Tensor)

↓ 2 callersFunctionuniq

↓ 1 callersMethod__init__

(self, patch_size)

model/ShiftedPatch.py:58

↓ 1 callersMethod__init__

(self, in_channels, out_channels)

model/fusion.py:23

↓ 1 callersMethod__init__

model/model.py:23

↓ 1 callersFunctionadjust_learning_rate

(optimizer, epoch, max_epoch, init_lr, power=0.9)

↓ 1 callersFunctionall_reduce_tensor

(tensor, op=dist.ReduceOp.SUM, world_size=1)

↓ 1 callersFunctiondrop_path

Obtained from: github.com:rwightman/pytorch-image-models Drop paths (Stochastic Depth) per sample (when applied in main path of residual bl

model/drop.py:4

↓ 1 callersFunctiong_center

↓ 1 callersFunctionget_sobel

(in_chan, out_chan)

model/edge.py:8

↓ 1 callersFunctionlog_args

↓ 1 callersFunctionmain_worker

↓ 1 callersFunctionppv

(output, target)

↓ 1 callersFunctionprobs2class

(probs: Tensor)

↓ 1 callersMethodreset

↓ 1 callersFunctionrun_sobel

(conv_x, conv_y, input)

model/edge.py:42

↓ 1 callersFunctionsensitivity_score

(output, target)

↓ 1 callersFunctionunion

(a: Tensor, b: Tensor)

↓ 1 callersFunctionwindow_reverse

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

model/swintransformer.py:52

FunctionCross_entropy_loss

(prediction, label)

FunctionDual_focal_loss

(output, target)

model/criterions.py:124

FunctionGeneralized_dice

(output, target, eps=1e-5, weight_type='square')

model/criterions.py:93

Method__getitem__

(self, drop_prob=None)

model/drop.py:29

(self, in_channels, out_channels)

model/edge.py:50

model/edge.py:86

(self, in_feature, num_node)

model/graph.py:22

(self, in_channel)

model/graph.py:36

(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.,

model/swintransformer.py:81

(self, dim, input_resolution, num_heads, window_size=7, shift_size=0, mlp_ratio=4., qkv_bias

model/swintransformer.py:190

(self, dim, norm_layer=nn.LayerNorm)

model/swintransformer.py:311

(self, dim, input_resolution, depth, num_heads, window_size, mlp_ratio=4., qkv_bias=True, qk

model/swintransformer.py:374

(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None)

model/swintransformer.py:464

(self, img_size=224, patch_size=2, in_chans=3, embed_dim=128, depths=[2, 2, 6, 2], num_heads

model/swintransformer.py:522

(self, in_channels, out_channels)

model/swintransformer.py:636

model/swintransformer.py:651

(self, in_dim, dim, merging_size=2, exist_class_t=False, is_pe=False, merging=False)

model/ShiftedPatch.py:9

(self, in_channels, out_channels)

model/fusion.py:5

model/criterions.py:143

(self, in_channels, out_channels)

model/model.py:8

Functionaugment

(*arrs: Union[np.ndarray, Image.Image], rotate_angle: float = 45, flip: bool = True, mirror: bool

Functionaugment_arr

(*arrs_a: np.ndarray, rotate_angle: float = 45, flip: bool = True, mirror: bool = True,

Functionbatch_soft_size

Functioncenter_pad

(arr: np.ndarray, target_shape: Tuple[int, ...])

Functioncount_params

Compute the depth of nested lists

Functiondice_coef

(output, target)

Methodextra_repr

model/swintransformer.py:168

Methodextra_repr

model/swintransformer.py:300

Methodextra_repr

model/swintransformer.py:345

Methodextra_repr

model/swintransformer.py:450

Functionf1_score

(output, target)

Functionflatten_

(to_flat: Iterable[Iterable[A]])

Functionflatten__

model/swintransformer.py:348

(self, input, target)

model/drop.py:33

model/edge.py:57

model/edge.py:74

(self, x, feature=False)

model/edge.py:101

model/graph.py:14

model/graph.py:26

(self, x, y, x_fusion, y_fusion, concat=False)

model/graph.py:46

model/swintransformer.py:29

Args: x: input features with shape of (num_windows*B, N, C) mask: (0/-inf) mask with shape of (num_windows, Wh*Ww,

model/swintransformer.py:122

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

model/swintransformer.py:242

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

model/swintransformer.py:317

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

model/swintransformer.py:409

model/swintransformer.py:482

model/swintransformer.py:600

model/swintransformer.py:642

model/swintransformer.py:661

model/ShiftedPatch.py:30

model/ShiftedPatch.py:62

model/fusion.py:11

(self, seg1, edge1, seg2, edge2)

model/fusion.py:30

(self, input, target)

model/criterions.py:146

model/model.py:14

(self, in_seg, in_edge)

model/model.py:42

Functionget_center

center cropping

Functionhausdorff

(preds: Tensor, target: Tensor, spacing: Tensor = None)

next →1–100 of 121, ranked by callers