For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Python class

Conv1D

`Conv1D`

class max.nn.Conv1D(kernel_size, in_channels, out_channels, dtype, stride=1, padding=0, dilation=1, num_groups=1, device=None, has_bias=False, permute=False, name=None)

source

Bases: Module

A 1D convolution over an input signal composed of several input planes.

When called, Conv1D accepts a TensorValue of shape (batch, length, in_channels) and returns a TensorValue of shape (batch, new_length, out_channels). If permute=True, the input and output follow PyTorch channel-first layout: (batch, in_channels, length) and (batch, out_channels, new_length).

conv = nn.Conv1D(
    kernel_size=3,
    in_channels=64,
    out_channels=128,
    dtype=DType.float32,
    stride=1,
    padding=0,
    has_bias=False,
    name="conv1d_weight",
    device=DeviceRef.GPU(),
)

Initializes the Conv1D layer with weights and optional bias.

Parameters:

kernel_size (int) – Size of the convolving kernel (width dimension).
in_channels (int) – Number of channels in the input signal.
out_channels (int) – Number of channels produced by the convolution.
dtype (DType) – The data type for both weights and bias.
stride (int) – Stride of the convolution. Controls the step size when sliding the kernel. Default: 1
padding (int | tuple[int, int]) – Padding added to the input sequence. Can be:
- int: symmetric padding applied to both sides (pad_left = pad_right = padding). Default: 0
- tuple[int, int]: asymmetric padding as (pad_left, pad_right) for causal convolutions.
dilation (int) – Spacing between kernel elements. Controls the kernel dilation rate. Default: 1
num_groups (int) – Number of blocked connections from input channels to output channels. Input channels and output channels are divided into groups. Default: 1
device (DeviceRef | None) – The target device for computation. If None, defaults to CPU. Weights are initially stored on CPU and moved to target device during computation.
name (str | None) – Base name for weights. If provided, weights are named {name}.weight and {name}.bias (if bias is enabled). If None, uses “weight” and “bias”.
has_bias (bool) – If true, adds a learnable bias vector to the layer. Defaults to False.
permute (bool) – If true, permutes weights from PyTorch format to MAX format. PyTorch order: (out_channels, in_channels / num_groups, kernel_size). MAX API order: (kernel_size, in_channels / num_groups, out_channels). Defaults to False.

`bias`

bias: Weight | None = None

source

The optional bias vector stored on CPU with shape (out_channels,). Model init moves the bias to device if present.

`device`

device: DeviceRef | None

source

The device where matrix operations are performed.

`dilation`

dilation: int

source

Controls the dilation rate.

`filter`

filter: Weight

source

The weight matrix stored on CPU with shape (kernel_size, in_channels / num_groups, out_channels). Model init moves the weight to device.

`num_groups`

num_groups: int

source

Number of blocked connections from input channels to output channels.

`padding`

padding: int | tuple[int, int]

source

Controls the amount of padding applied to the input.

If int: symmetric padding applied to both sides (pad_left = pad_right = padding). If tuple[int, int]: asymmetric padding as (pad_left, pad_right).

`permute`

permute: bool = False

source

bool controls whether self.filter is permuted from PyTorch order to max order. PyTorch order is: (out_channels, in_channels / num_groups, kernel_size) Max API order: (kernel_size, in_channels / num_groups, out_channels).

`stride`

stride: int

source

Controls the stride for the cross-correlation.

Conv1D​

bias​

device​

dilation​

filter​

num_groups​

padding​

permute​

stride​