SYMBOL INDEX (96 symbols across 12 files)

FILE: anomaly_map.py
  function heat_map (line 12) | def heat_map(output, target, FE, config):
  function pixel_distance (line 42) | def pixel_distance(output, target):
  function feature_distance (line 52) | def feature_distance(output, target, FE, config):
  function patchify (line 78) | def patchify(features, return_spatial_info=False):

FILE: dataset.py
  class Dataset_maker (line 17) | class Dataset_maker(torch.utils.data.Dataset):
    method __init__ (line 18) | def __init__(self, root, category, config, is_train=True):
    method __getitem__ (line 49) | def __getitem__(self, index):
    method __len__ (line 85) | def __len__(self):

FILE: ddad.py
  class DDAD (line 13) | class DDAD:
    method __init__ (line 14) | def __init__(self, unet, config) -> None:
    method __call__ (line 35) | def __call__(self) -> Any:

FILE: feature_extractor.py
  function loss_fucntion (line 13) | def loss_fucntion(a, b, c, d, config):
  function domain_adaptation (line 27) | def domain_adaptation(unet, config, fine_tune):

FILE: loss.py
  function get_loss (line 6) | def get_loss(model, x_0, t, config):

FILE: main.py
  function build_model (line 12) | def build_model(config):
  function train (line 19) | def train(config):
  function detection (line 32) | def detection(config):
  function finetuning (line 44) | def finetuning(config):
  function parse_args (line 57) | def parse_args():

FILE: metrics.py
  class Metric (line 14) | class Metric:
    method __init__ (line 15) | def __init__(self,labels_list, predictions, anomaly_map_list, gt_list,...
    method image_auroc (line 23) | def image_auroc(self):
    method pixel_auroc (line 27) | def pixel_auroc(self):
    method optimal_threshold (line 47) | def optimal_threshold(self):
    method pixel_pro (line 60) | def pixel_pro(self):
    method miscalssified (line 110) | def miscalssified(self):

FILE: reconstruction.py
  class Reconstruction (line 8) | class Reconstruction:
    method __init__ (line 17) | def __init__(self, unet, config) -> None:
    method __call__ (line 23) | def __call__(self, x, y0, w) -> Any:

FILE: resnet.py
  function conv3x3 (line 29) | def conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: in...
  function conv1x1 (line 35) | def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d:
  class BasicBlock (line 40) | class BasicBlock(nn.Module):
    method __init__ (line 43) | def __init__(
    method forward (line 70) | def forward(self, x: Tensor) -> Tensor:
  class Bottleneck (line 89) | class Bottleneck(nn.Module):
    method __init__ (line 98) | def __init__(
    method forward (line 124) | def forward(self, x: Tensor) -> Tensor:
  class ResNet (line 147) | class ResNet(nn.Module):
    method __init__ (line 149) | def __init__(
    method _make_layer (line 208) | def _make_layer(self, block: Type[Union[BasicBlock, Bottleneck]], plan...
    method _forward_impl (line 233) | def _forward_impl(self, x: Tensor) -> Tensor:
    method forward (line 248) | def forward(self, x: Tensor) -> Tensor:
  function _resnet (line 252) | def _resnet(
  class AttnBasicBlock (line 270) | class AttnBasicBlock(nn.Module):
    method __init__ (line 273) | def __init__(
    method forward (line 304) | def forward(self, x: Tensor) -> Tensor:
  class AttnBottleneck (line 325) | class AttnBottleneck(nn.Module):
    method __init__ (line 329) | def __init__(
    method forward (line 361) | def forward(self, x: Tensor) -> Tensor:
    method __init__ (line 387) | def __init__(self,
    method _make_layer (line 423) | def _make_layer(self, block: Type[Union[BasicBlock, Bottleneck]], plan...
    method _forward_impl (line 448) | def _forward_impl(self, x: Tensor) -> Tensor:
    method forward (line 461) | def forward(self, x: Tensor) -> Tensor:
  function resnet18 (line 465) | def resnet18(pretrained: bool = False, progress: bool = True,**kwargs: A...
  function resnet34 (line 476) | def resnet34(pretrained: bool = False, progress: bool = True, **kwargs: ...
  function resnet50 (line 487) | def resnet50(pretrained: bool = False, progress: bool = True, **kwargs: ...
  function resnet101 (line 498) | def resnet101(pretrained: bool = False, progress: bool = True, **kwargs:...
  function resnet152 (line 509) | def resnet152(pretrained: bool = False, progress: bool = True, **kwargs:...
  function resnext50_32x4d (line 520) | def resnext50_32x4d(pretrained: bool = False, progress: bool = True, **k...
  function resnext101_32x8d (line 533) | def resnext101_32x8d(pretrained: bool = False, progress: bool = True, **...
  function wide_resnet50_2 (line 546) | def wide_resnet50_2(pretrained: bool = False, progress: bool = True, **k...
  function wide_resnet101_2 (line 562) | def wide_resnet101_2(pretrained: bool = False, progress: bool = True, **...

FILE: train.py
  function trainer (line 10) | def trainer(model, category, config):

FILE: unet.py
  class TimestepBlock (line 11) | class TimestepBlock(nn.Module):
    method forward (line 17) | def forward(self, x, emb):
  class TimestepEmbedSequential (line 23) | class TimestepEmbedSequential(nn.Sequential, TimestepBlock):
    method forward (line 29) | def forward(self, x, emb):
  class PositionalEmbedding (line 38) | class PositionalEmbedding(nn.Module):
    method __init__ (line 44) | def __init__(self, dim, scale=1):
    method forward (line 50) | def forward(self, x):
  class Downsample (line 60) | class Downsample(nn.Module):
    method __init__ (line 61) | def __init__(self, in_channels, use_conv, out_channels=None):
    method forward (line 72) | def forward(self, x, time_embed=None):
  class Upsample (line 77) | class Upsample(nn.Module):
    method __init__ (line 78) | def __init__(self, in_channels, use_conv, out_channels=None):
    method forward (line 87) | def forward(self, x, time_embed=None):
  class AttentionBlock (line 95) | class AttentionBlock(nn.Module):
    method __init__ (line 102) | def __init__(self, in_channels, n_heads=1, n_head_channels=-1):
    method forward (line 119) | def forward(self, x, time=None):
  class QKVAttention (line 128) | class QKVAttention(nn.Module):
    method __init__ (line 133) | def __init__(self, n_heads):
    method forward (line 137) | def forward(self, qkv, time=None):
  class ResBlock (line 156) | class ResBlock(TimestepBlock):
    method __init__ (line 157) | def __init__(
    method forward (line 202) | def forward(self, x, time_embed):
  class UNetModel (line 220) | class UNetModel(nn.Module):
    method __init__ (line 222) | def __init__(
    method forward (line 390) | def forward(self, x, time):
  class GroupNorm32 (line 409) | class GroupNorm32(nn.GroupNorm):
    method forward (line 410) | def forward(self, x):
  function zero_module (line 414) | def zero_module(module):
  function update_ema_params (line 423) | def update_ema_params(target, source, decay_rate=0.9999):

FILE: visualize.py
  function visualalize_reconstruction (line 9) | def visualalize_reconstruction(input, recon, target):
  function visualize (line 79) | def visualize(image, noisy_image, GT, pred_mask, anomaly_map, category) :
  function show_tensor_image (line 116) | def show_tensor_image(image):
  function show_tensor_mask (line 129) | def show_tensor_mask(image):