MCPcopy Create free account

hub / github.com/ZhendongWang6/Uformer / types & classes

Types & classes38 in github.com/ZhendongWang6/Uformer

⨍ Functions 188◇ Types & classes 38
↓ 9 callersClassBasicUformerLayer
model.py:1013
↓ 7 callersClassUformer
model.py:1069
↓ 3 callersClassGradualWarmupScheduler
Gradually warm-up(increasing) learning rate in optimizer. Proposed in 'Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour'. Args:
warmup_scheduler/scheduler.py:5
↓ 3 callersClassSepConv2d
model.py:344
↓ 2 callersClassAugment_RGB_torch
utils/dataset_utils.py:5
↓ 2 callersClassCharbonnierLoss
Charbonnier Loss (L1)
losses.py:41
↓ 2 callersClassDataLoaderTest
dataset/dataset_denoise.py:116
↓ 2 callersClassDataLoaderTrain
dataset/dataset_denoise.py:20
↓ 2 callersClassDataLoaderVal
dataset/dataset_denoise.py:77
↓ 2 callersClassLeWinTransformerBlock
model.py:850
↓ 2 callersClassLinearProjection
model.py:421
↓ 1 callersClassAttention
model.py:549
↓ 1 callersClassConvBlock
model.py:83
↓ 1 callersClassConvProjection
model.py:381
↓ 1 callersClassDataLoaderTest
dataset/dataset_motiondeblur.py:156
↓ 1 callersClassDataLoaderTrain
dataset/dataset_motiondeblur.py:20
↓ 1 callersClassDataLoaderVal_deblur
dataset/dataset_motiondeblur.py:114
↓ 1 callersClassFastLeFF
model.py:14
↓ 1 callersClassInputProj
model.py:781
↓ 1 callersClassLeFF
model.py:654
↓ 1 callersClassMlp
model.py:623
↓ 1 callersClassOutputProj
model.py:813
↓ 1 callersClassUNet
model.py:107
↓ 1 callersClassWindowAttention
model.py:452
↓ 1 callersClasseca_layer_1d
Constructs a ECA module. Args: channel: Number of channels of the input feature map k_size: Adaptive selection of kernel size
model.py:311
ClassDataLoaderVal
dataset/dataset_motiondeblur.py:77
ClassDownsample
model.py:730
ClassDownsample
utils/antialias.py:7
ClassDownsample1D
utils/antialias.py:61
ClassLPU
Local Perception Unit to extract local infomation. LPU(X) = DWConv(X) + X
model.py:202
ClassMixUp_AUG
utils/dataset_utils.py:34
ClassOptions
docstring for Options
options.py:3
ClassPosCNN
model.py:230
ClassSAM
model.py:66
ClassSELayer
model.py:252
ClassTVLoss
losses.py:20
ClassUpsample
model.py:756
Classeca_layer
Constructs a ECA module. Args: channel: Number of channels of the input feature map k_size: Adaptive selection of kernel size
model.py:279