Functions — github.com/WanderRainy/OARENet

hub / github.com/WanderRainy/OARENet / functions

Functions240 in github.com/WanderRainy/OARENet

⨍ Functions 240◇ Types & classes 64

↓ 15 callersMethodconv_stage

(self, dim_in, dim_out, kernel_size=3, stride=1, padding=1, bias=True, useBN=False)

networks/unet.py:48

↓ 11 callersMethodload

(self, path)

framework.py:45

↓ 9 callersMethod__init__

(self, num_classes=1)

networks/dinknet.py:401

↓ 9 callersFunction_resnet

( arch: str, block: Type[Union[BasicBlock, Bottleneck]], layers: List[int], pretrained: bo

networks/resnet.py:252

↓ 7 callersMethodupsample

(self, ch_coarse, ch_fine)

networks/unet.py:68

↓ 6 callersMethod__init__

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

networks/swin_transformer.py:46

↓ 5 callersFunctionbuild

Build a module. Args: cfg (dict, list[dict]): The config of modules, is is either a dict or a list of configs. regist

networks/builder.py:13

↓ 5 callersFunctionbuild_erase

(in_channel=64,erase_channel=16)

networks/intersection.py:129

↓ 5 callersFunctionload_url_dist

In distributed setting, this function only download checkpoint at local rank 0.

networks/checkpoint.py:109

↓ 5 callersFunctionres2net50

Constructs a Res2Net-50 model. Res2Net-50 refers to the Res2Net-50_26w_4s. Args: pretrained (bool): If True, returns a model pre-train

networks/res2net.py:162

↓ 4 callersFunctionResidualNet

(network_type, depth, num_classes, att_type, path=None)

networks/cabm_resnet.py:189

↓ 4 callersMethod__init__

(self, levels, channels, num_classes=1000, block=Bottle2neck, residual_root=False, return_lev

networks/dla.py:272

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1)

networks/res2next.py:133

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1)

networks/res2net.py:125

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1, att_type=None)

networks/cabm_resnet.py:143

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1, att_type=None)

networks/backbone.py:96

↓ 4 callersMethod_make_layer

(self, block: Type[Union[BasicBlock, Bottleneck]], planes: int, blocks: int, stride: int

networks/resnet.py:205

↓ 4 callersFunctionbuild_decoder

(filters = [256, 512, 1024, 2048])

networks/decoder.py:232

↓ 4 callersMethodinit_weights

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to No

networks/swin_transformer.py:597

↓ 4 callersMethodsave

(self, path)

framework.py:42

↓ 3 callersMethod__init__

(self,filters = [256, 512, 1024, 2048])

networks/decoder.py:137

↓ 3 callersMethod__init__

(self, gate_channels, reduction_ratio=16, pool_types=['avg', 'max'], no_spatial=False)

networks/cbam.py:85

↓ 3 callersMethod__init__

(self)

networks/testNet.py:34

↓ 3 callersFunctionconv1x1

1x1 convolution

networks/resnet.py:32

↓ 3 callersFunctionconv3x3

3x3 convolution with padding

networks/resnet.py:26

↓ 3 callersMethodconv_stage

(self, dim_in, dim_out, kernel_size=3, stride=1, padding=1, bias=True, useBN=False)

networks/dunet.py:70

↓ 3 callersFunctionrandomHorizontalFlip

(image, mask, u=0.5)

data.py:36

↓ 3 callersFunctionrandomRotate90

(image, mask, u=0.5)

data.py:50

↓ 3 callersFunctionrandomVerticleFlip

(image, mask, u=0.5)

data.py:43

↓ 3 callersFunctionrandom_crop

(image, crop_shape, mask=None)

data.py:15

↓ 3 callersMethodupdate_lr

(self, new_lr, mylog, factor=False)

framework.py:48

↓ 3 callersMethodupsample

(self, ch_coarse, ch_fine)

↓ 2 callersMethod__init__

(self, gate_channel)

networks/bam.py:43

↓ 2 callersMethod__init__

(self, block, layers, network_type, num_classes, att_type=None)

networks/cabm_resnet.py:101

↓ 2 callersMethod__init__

( self, block: Type[Union[BasicBlock, Bottleneck]], layers: List[int], num

networks/resnet.py:146

↓ 2 callersMethod_freeze_stages

(self)

networks/swin_transformer.py:580

↓ 2 callersFunction_get_mmcv_home

()

networks/checkpoint.py:30

↓ 2 callersMethod_make_conv_level

(self, inplanes, planes, convs, stride=1, dilation=1)

networks/dla.py:327

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

networks/cabm_resnet.py:10

↓ 2 callersMethodforward

(self, volatile=False)

framework.py:28

↓ 2 callersFunctionget_torchvision_models

()

networks/checkpoint.py:172

↓ 2 callersFunctionresnet50

r"""ResNet-50 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. Args: pretrain

networks/resnet.py:292

↓ 2 callersFunctionwindow_partition

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

networks/swin_transformer.py:64

↓ 1 callersMethod__init__

Constructor Args: baseWidth: baseWidth for ResNeXt. cardinality: number of convolution groups. layers: co

networks/res2next.py:96

↓ 1 callersMethod__init__

(self, in_ch, filters)

networks/intersection.py:101

↓ 1 callersMethod__init__

(self, block, layers, baseWidth = 26, scale = 4, num_classes=1000)

networks/res2net.py:101

↓ 1 callersMethod__init__

(self, block, layers, network_type, att_type=None, pretrained = False)

networks/backbone.py:63

↓ 1 callersMethod__init__

(self)

networks/dunet.py:36

↓ 1 callersMethod_forward_impl

(self, x: Tensor)

networks/resnet.py:230

↓ 1 callersMethod_init_weight

(self)

networks/decoder.py:96

↓ 1 callersMethod_init_weight

(self)

networks/decoder.py:176

↓ 1 callersMethod_init_weight

(self)

networks/decoder.py:223

↓ 1 callersMethod_init_weight

(self)

networks/intersection.py:89

↓ 1 callersMethod_init_weight

(self)

networks/backbone.py:137

↓ 1 callersFunction_load_checkpoint

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

networks/checkpoint.py:225

↓ 1 callersMethod_load_pretrained_model

(self)

networks/backbone.py:147

↓ 1 callersFunction_process_mmcls_checkpoint

(checkpoint)

networks/checkpoint.py:214

↓ 1 callersFunction_save_to_state_dict

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

networks/checkpoint.py:374

↓ 1 callersFunctionbase_predict

(file_path, save_path)

large_test.py:14

↓ 1 callersFunctionbuild_ResNet

(network_type, depth, att_type, pretrained = False)

networks/backbone.py:159

↓ 1 callersFunctionbuild_decoder2

(filters = [256, 512, 1024, 2048])

networks/decoder.py:230

↓ 1 callersFunctionget_deprecated_model_names

()

networks/checkpoint.py:205

↓ 1 callersFunctionget_external_models

()

networks/checkpoint.py:184

↓ 1 callersFunctionget_mmcls_models

()

networks/checkpoint.py:198

↓ 1 callersFunctionget_root_logger

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

networks/swin_transformer.py:18

↓ 1 callersFunctionget_state_dict

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

networks/checkpoint.py:394

↓ 1 callersMethodh_transform

(self, x)

networks/decoder.py:64

↓ 1 callersMethodh_transform

(self, x)

networks/intersection.py:57

↓ 1 callersMethodinv_h_transform

(self, x)

networks/decoder.py:71

↓ 1 callersMethodinv_h_transform

(self, x)

networks/intersection.py:64

↓ 1 callersMethodinv_v_transform

(self, x)

networks/decoder.py:87

↓ 1 callersMethodinv_v_transform

(self, x)

networks/intersection.py:80

↓ 1 callersFunctionload

(module, prefix='')

networks/checkpoint.py:67

↓ 1 callersFunctionload_checkpoint

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,

networks/checkpoint.py:286

↓ 1 callersFunctionload_fileclient_dist

In distributed setting, this function only download checkpoint at local rank 0.

networks/checkpoint.py:151

↓ 1 callersFunctionload_pavimodel_dist

In distributed setting, this function only download checkpoint at local rank 0.

networks/checkpoint.py:123

↓ 1 callersFunctionload_state_dict

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

networks/checkpoint.py:41

↓ 1 callersFunctionlogsumexp_2d

(tensor)

networks/cbam.py:62

↓ 1 callersMethodoptimize

(self)

framework.py:33

↓ 1 callersFunctionres2net101_26w_4s

Constructs a Res2Net-50_26w_4s model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

networks/res2net.py:183

↓ 1 callersFunctionres2next50

Construct Res2NeXt-50. The default scale is 4. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

networks/res2next.py:164

↓ 1 callersFunctionres2next_dla60

(pretrained=None, **kwargs)

networks/dla.py:383

↓ 1 callersMethodset_input

(self, img_batch, mask_batch=None, img_id=None)

framework.py:22

↓ 1 callersMethodsoft_dice_coeff

(self, y_true, y_pred)

loss.py:13

↓ 1 callersMethodsoft_dice_loss

(self, y_true, y_pred)

loss.py:27

↓ 1 callersMethodtrain

Convert the model into training mode while keep layers freezed.

networks/swin_transformer.py:650

↓ 1 callersMethodv_transform

(self, x)

networks/decoder.py:79

↓ 1 callersMethodv_transform

(self, x)

networks/intersection.py:72

↓ 1 callersFunctionweights_to_cpu

Copy a model state_dict to cpu. Args: state_dict (OrderedDict): Model weights on GPU. Returns: OrderedDict: Model weights on

networks/checkpoint.py:359

↓ 1 callersFunctionwindow_reverse

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

networks/swin_transformer.py:79

next →1–100 of 240, ranked by callers