![]() ![]() Pads the input tensor boundaries with a constant value. Pads the input tensor boundaries with zero. ![]() Pads the input tensor using replication of the input boundary. Pads the input tensor using the reflection of the input boundary. Registers a backward hook common to all the modules.Īpplies a 1D convolution over an input signal composed of several input planes.Īpplies a 2D convolution over an input signal composed of several input planes.Īpplies a 3D convolution over an input signal composed of several input planes.Īpplies a 1D transposed convolution operator over an input image composed of several input planes.Īpplies a 2D transposed convolution operator over an input image composed of several input planes.Īpplies a 3D transposed convolution operator over an input image composed of several input planes.Ī torch.nn.Conv1d module with lazy initialization of the in_channels argument of the Conv1d that is inferred from the input.size(1).Ī torch.nn.Conv2d module with lazy initialization of the in_channels argument of the Conv2d that is inferred from the input.size(1).Ī torch.nn.Conv3d module with lazy initialization of the in_channels argument of the Conv3d that is inferred from the input.size(1).Ī torch.nn.ConvTranspose1d module with lazy initialization of the in_channels argument of the ConvTranspose1d that is inferred from the input.size(1).Ī torch.nn.ConvTranspose2d module with lazy initialization of the in_channels argument of the ConvTranspose2d that is inferred from the input.size(1).Ī torch.nn.ConvTranspose3d module with lazy initialization of the in_channels argument of the ConvTranspose3d that is inferred from the input.size(1).Įxtracts sliding local blocks from a batched input tensor.Ĭombines an array of sliding local blocks into a large containing tensor.Īpplies a 1D max pooling over an input signal composed of several input planes.Īpplies a 2D max pooling over an input signal composed of several input planes.Īpplies a 3D max pooling over an input signal composed of several input planes.Īpplies a 1D average pooling over an input signal composed of several input planes.Īpplies a 2D average pooling over an input signal composed of several input planes.Īpplies a 3D average pooling over an input signal composed of several input planes.Īpplies a 2D fractional max pooling over an input signal composed of several input planes.Īpplies a 3D fractional max pooling over an input signal composed of several input planes.Īpplies a 1D power-average pooling over an input signal composed of several input planes.Īpplies a 2D power-average pooling over an input signal composed of several input planes.Īpplies a 1D adaptive max pooling over an input signal composed of several input planes.Īpplies a 2D adaptive max pooling over an input signal composed of several input planes.Īpplies a 3D adaptive max pooling over an input signal composed of several input planes.Īpplies a 1D adaptive average pooling over an input signal composed of several input planes.Īpplies a 2D adaptive average pooling over an input signal composed of several input planes.Īpplies a 3D adaptive average pooling over an input signal composed of several input planes. Registers a global forward hook for all the modules ![]() Registers a forward pre-hook common to all modules. Non-linear Activations (weighted sum, nonlinearity)ĭataParallel Layers (multi-GPU, distributed)Ī kind of Tensor that is to be considered a module parameter.īase class for all neural network modules. These are the basic building blocks for graphs: Extending torch.func with autograd.Function. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |