Struct MaxPool1d 

pub struct MaxPool1d { /* private fields */ }

1D max pooling layer.

Applies max pooling over a 3D input tensor, selecting the maximum value in each sliding window along the temporal/sequence dimension. Equivalent to PyTorch’s nn.MaxPool1d.

• Input shape: [N, C, L_in]
• Output shape: [N, C, L_out]

Output size formula:

L_out = floor((L_in + 2*padding - dilation*(kernel_size-1) - 1) / stride + 1)

Example

let pool = MaxPool1d::new(2);            // kernel_size=2, stride=2
let pool = MaxPool1d::with_stride(3, 1)  // kernel_size=3, stride=1
    .padding(1);
let y = pool.forward(&x)?;

Implementations

impl MaxPool1d

pub fn new(kernel_size: i64) -> Self

Create a MaxPool1d with the given kernel size.

Stride defaults to kernel_size (non-overlapping windows). Padding defaults to 0, dilation to 1.

pub fn with_stride(kernel_size: i64, stride: i64) -> Self

Create with explicit kernel size and stride.

pub fn padding(self, padding: i64) -> Self

Set padding added to both sides of the input sequence.

Trait Implementations

impl Module for MaxPool1d

fn name(&self) -> &str

Human-readable type name used as node ID prefix in graph visualization. Override to return a lowercase identifier (e.g., “linear”, “gelu”).

fn forward(&self, input: &Variable) -> Result<Variable>

Run the forward pass on input and return the result.

fn parameters(&self) -> Vec<Parameter>

Return this module’s learnable parameters. Default: recursively collects from sub_modules() with pointer dedup.

fn buffers(&self) -> Vec<Buffer>

Return this module’s non-learnable persistent buffers (e.g., running stats). Default: recursively collects from sub_modules() with pointer dedup. Leaf modules should override to return their own buffers.

fn sub_modules(&self) -> Vec<Rc<dyn Module>>

Return direct child modules for recursive tree walks. Override in composite modules (loops, switches, gates).

fn move_to_device(&self, device: Device)

Move all parameters and buffers to the given device.

fn set_training(&self, _training: bool)

Set training/eval mode. Affects Dropout, BatchNorm, etc. Override in modules with mode-dependent behavior.

fn train(&self)

Set training mode. Shorthand for set_training(true).

fn eval(&self)

Set eval mode. Shorthand for set_training(false).

fn trace(&self) -> Option<Variable>

Return per-iteration side output for loop tracing. Override in loop body modules that capture trajectory data (e.g., attention fixation points). Returns None by default. When Some, the loop executor collects traces accessible via Graph::traces().

fn as_named_input(&self) -> Option<&dyn NamedInputModule>

Upcast to NamedInputModule for multi-input graphs. Override in types that implement NamedInputModule to enable receiving additional named inputs via graph using().

fn as_loop_body(&self) -> Option<&dyn LoopBody>

Upcast to LoopBody for loop bodies that publish named per-iteration traces. Override in types that implement LoopBody to enable multi-output trace publishing via TraceEmit::publish. Default returns None, in which case the loop runner falls back to the legacy Module::trace path.

fn as_any(&self) -> Option<&dyn Any>

Opt-in identity hook for framework downcasts.

fn structural_hash(&self) -> Option<String>

SHA-256 hex hash of module architecture for checkpoint validation. Override in composite modules (Graph) that compute a deterministic hash from their topology and parameter shapes.

fn reset(&self)

Reset internal state (e.g. recurrent hidden state) between sequences. Called by loops before iterating to clear stale tensors whose grad_fns may reference freed saved tensors. Override in stateful modules.

fn detach_state(&self)

Detach internal state from the computation graph (for truncated BPTT). Called between training steps to break gradient chains on state carried across forward passes (e.g., recurrent hidden state). Override in stateful modules.

fn aggregated_metrics_slot(&self) -> Option<Arc<Mutex<Option<EpochMetrics>>>>

Hand the framework the model’s shared slot for coord-broadcast aggregated crate::metrics::EpochMetrics. The cluster- rank worker setup calls this at construction and stores the returned Arc clone alongside its own — both ends then point at the same Mutex, so the bridge thread’s writes are visible to the user’s main-thread reads (Graph::latest_metrics, Graph::aggregated_gpu_tabs — with Graph = flodl::graph::Graph).