Module dfdx::nn::modules

Structs containing initialized Tensors & impls for super::Module. See super::builders for helpful utilities in creating these in a device/dtype agnostic way.

Re-exports

• pub use super::*;

Structs

• Abs
  Calls abs().
• AddInto
  Add inputs together into a single tensor. T should be a tuple
• AvgPool2D
  Average pool with 2d kernel that operates on images (3d) and batches of images (4d). Each patch reduces to the average of the values in the patch.
• AvgPoolGlobal
  Applies average pooling over an entire image, fully reducing the height and width dimensions:
• BatchNorm1D
  Batch normalization for sequences as described in Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• BatchNorm2D
  Batch normalization for images as described in Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Bias2D
  Adds a learnable 1d bias to 3d and 4d inputs. Can be used with crate::nn::modules::Conv2D to create a Biased conv.
• Conv2D
  Requires Nightly Performs unbiased 2d convolutions on 3d and 4d images.
• Cos
  Calls cos().
• Dropout
  Does nothing as a Module, and calls dropout() as ModuleMut with probability 1.0 / N.
• DropoutOneIn
  Does nothing as a Module, and calls dropout() as ModuleMut with probability 1.0 / N.
• Embedding
  An embedding Initializes Self::weight from a Uniform distribution between [-1 / sqrt(I), 1 / sqrt(I)].
• Exp
  Calls exp().
• Flatten2D
  Requires Nightly Flattens 3d tensors to 1d, and 4d tensors to 2d.
• GeLU
  Calls gelu().
• GeneralizedResidual
  A residual connection R around F: F(x) + R(x), as introduced in Deep Residual Learning for Image Recognition.
• LayerNorm1D
  Implements layer normalization as described in Layer Normalization.
• Linear
  A linear transformation of the form weight * x + bias, where weight is a matrix, x is a vector or matrix, and bias is a vector.
• Ln
  Calls ln().
• MaxPool2D
  Max pool with 2d kernel that operates on images (3d) and batches of images (4d). Each patch reduces to the maximum value in that patch.
• MaxPoolGlobal
  Applies max pooling over an entire image, fully reducing the height and width dimensions:
• MinPool2D
  Minimum pool with 2d kernel that operates on images (3d) and batches of images (4d). Each patch reduces to the minimum of the values in the patch.
• MinPoolGlobal
  Applies min pooling over an entire image, fully reducing the height and width dimensions:
• MultiHeadAttention
  A multi-head attention layer.
• ReLU
  Calls relu().
• Repeated
  Repeats T N times. This requires that T’s input is the same as it’s output.
• Residual
  A residual connection around F: F(x) + x, as introduced in Deep Residual Learning for Image Recognition.
• Sigmoid
  Calls sigmoid().
• Sin
  Calls sin().
• Softmax
  Calls softmax().
• SplitInto
  Splits input into multiple heads. T should be a tuple, where every element of the tuple accepts the same input type.
• Sqrt
  Calls sqrt().
• Square
  Calls square().
• Tanh
  Calls tanh().
• Transformer
  Transformer architecture as described in Attention is all you need.
• TransformerDecoder
  A transformer decoder.
• TransformerDecoderBlock
  A transformer decoder block. Different than the normal transformer block as this self attention accepts an additional sequence from the encoder.
• TransformerEncoderBlock
  A single transformer encoder block
• UnbiasedLinear
  A linear transformation of the form weight * x, where weight is a matrix, x is a vector or matrix.

Type Definitions

• TransformerEncoder
  A transformer encoder.