MCPcopy Create free account

hub / github.com/MichaelRamamonjisoa/SharpNet / types & classes

Types & classes24 in github.com/MichaelRamamonjisoa/SharpNet

⨍ Functions 105◇ Types & classes 24
↓ 5 callersClassResNet
resnet.py:109
↓ 3 callersClassCompose
Composes several transforms together.
data_transforms.py:316
↓ 3 callersClassDecoder
sharpnet_model.py:7
↓ 3 callersClassNormalize
Given mean: (R, G, B) and std: (R, G, B), will normalize each channel of the torch.*Tensor, i.e. channel = (channel - mean) / std
data_transforms.py:7
↓ 3 callersClassSharpNet
sharpnet_model.py:140
↓ 3 callersClassToTensor
Converts a PIL.Image or numpy.ndarray (H x W x C) in the range [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0].
data_transforms.py:268
↓ 2 callersClassDepth
Depth: overwrite scale
representations.py:175
↓ 2 callersClassInputImage
Image class
representations.py:56
↓ 2 callersClassMask
Mask:
representations.py:216
↓ 2 callersClassNYUDataset
dataset_manager.py:177
↓ 2 callersClassPBRSDataset
dataset_manager.py:119
↓ 2 callersClassSharpNetLoss
loss.py:45
↓ 1 callersClassContours
Contours: overwrite scale to always have contours with 1 pixel width
representations.py:191
↓ 1 callersClassDepthBoundaryConsensusLoss
loss.py:266
↓ 1 callersClassDoobNetLoss
loss.py:9
↓ 1 callersClassHuberLoss
loss.py:150
↓ 1 callersClassLainaBerHuLoss
loss.py:119
↓ 1 callersClassNormalDepthConsensusLoss
loss.py:317
↓ 1 callersClassNormals
Normals: overwrite transforms to handle specificity of normals transforms
representations.py:134
↓ 1 callersClassSpatialGradientsLoss
loss.py:189
ClassBasicBlock
resnet.py:35
ClassBottleneck
resnet.py:67
ClassGeoDataset
dataset_manager.py:13
ClassRepresentation
Intermediate representation object
representations.py:10