conv_fused.ConvReLU1d

A ConvReLU1d module is a fused module of Conv1d and ReLU, attached with FakeQuantize modules for weight for quantization aware training.

conv_fused.ConvReLU2d

A ConvReLU2d module is a fused module of Conv2d and ReLU, attached with FakeQuantize modules for weight for quantization aware training.

conv_fused.ConvReLU3d

A ConvReLU3d module is a fused module of Conv3d and ReLU, attached with FakeQuantize modules for weight for quantization aware training.

conv_fused.ConvBnReLU1d

A ConvBnReLU1d module is a module fused from Conv1d, BatchNorm1d and ReLU, attached with FakeQuantize modules for weight, used in quantization aware training.

conv_fused.ConvBnReLU2d

A ConvBnReLU2d module is a module fused from Conv2d, BatchNorm2d and ReLU, attached with FakeQuantize modules for weight, used in quantization aware training.

conv_fused.ConvBnReLU3d

A ConvBnReLU3d module is a module fused from Conv3d, BatchNorm3d and ReLU, attached with FakeQuantize modules for weight, used in quantization aware training.

linear_fused.LinearBn1d

A LinearBn1d module is a module fused from Linear and BatchNorm1d, attached with FakeQuantize modules for weight, used in quantization aware training.

linear_relu.LinearReLU

A LinearReLU module fused from Linear and ReLU modules, attached with FakeQuantize modules for weight, used in quantization aware training.

conv_relu.ConvReLU1d

A ConvReLU1d module is a fused module of Conv1d and ReLU

conv_relu.ConvReLU2d

A ConvReLU2d module is a fused module of Conv2d and ReLU

conv_relu.ConvReLU3d

A ConvReLU3d module is a fused module of Conv3d and ReLU

bn_relu.BNReLU2d

A BNReLU2d module is a fused module of BatchNorm2d and ReLU

bn_relu.BNReLU3d

A BNReLU3d module is a fused module of BatchNorm3d and ReLU

conv_add.ConvAdd2d

A ConvAdd2d module is a fused module of Conv2d and Add

conv_add.ConvAddReLU2d

A ConvAddReLU2d module is a fused module of Conv2d, Add and Relu

linear_relu.LinearLeakyReLU

For onednn backend only A LinearLeakyReLU module fused from Linear and LeakyReLU modules We adopt the same interface astorch.ao.nn.quantized.Linear.

linear_relu.LinearReLU

A LinearReLU module fused from Linear and ReLU modules

linear_relu.LinearTanh

A LinearTanh module fused from Linear and Tanh modules

linear_relu.LinearReLU

A LinearReLU module fused from Linear and ReLU modules that can be used for dynamic quantization.

fused.ConvAdd2d

This is a sequential container which calls the Conv2d modules with extra Add.

fused.ConvAddReLU2d

This is a sequential container which calls the Conv2d, add, Relu.

fused.LinearBn1d

This is a sequential container which calls the Linear and BatchNorm1d modules.

fused.LinearLeakyReLU

This is a sequential container which calls the Linear and LeakyReLU modules.

fused.LinearTanh

This is a sequential container which calls the Linear and Tanh modules.

conv.Conv1d

A Conv1d module attached with FakeQuantize modules for weight, used for quantization aware training.

conv.Conv2d

A Conv2d module attached with FakeQuantize modules for weight, used for quantization aware training.

conv.Conv3d

A Conv3d module attached with FakeQuantize modules for weight, used for quantization aware training.

embedding_ops.Embedding

An embedding bag module attached with FakeQuantize modules for weight, used for quantization aware training.

embedding_ops.EmbeddingBag

An embedding bag module attached with FakeQuantize modules for weight, used for quantization aware training.

linear.Linear

A linear module attached with FakeQuantize modules for weight, used for quantization aware training.

activation.MultiheadAttention

rnn.LSTM

A quantizable long short-term memory (LSTM).

rnn.LSTMCell

A quantizable long short-term memory (LSTM) cell.

conv.Conv1d

A dynamically quantized conv module with floating point tensors as inputs and outputs.

conv.Conv2d

A dynamically quantized conv module with floating point tensors as inputs and outputs.

conv.Conv3d

A dynamically quantized conv module with floating point tensors as inputs and outputs.

conv.ConvTranspose1d

A dynamically quantized transposed convolution module with floating point tensors as inputs and outputs.

conv.ConvTranspose2d

A dynamically quantized transposed convolution module with floating point tensors as inputs and outputs.

conv.ConvTranspose3d

A dynamically quantized transposed convolution module with floating point tensors as inputs and outputs.

linear.Linear

A dynamic quantized linear module with floating point tensor as inputs and outputs.

rnn.GRU

Applies a multi-layer gated recurrent unit (GRU) RNN to an input sequence.

rnn.GRUCell

A gated recurrent unit (GRU) cell

rnn.LSTM

A dynamic quantized LSTM module with floating point tensor as inputs and outputs.

rnn.LSTMCell

A long short-term memory (LSTM) cell.

rnn.PackedParameter

rnn.RNNBase

rnn.RNNCell

An Elman RNN cell with tanh or ReLU non-linearity.

rnn.RNNCellBase