adaptive_avg_pool2d — PyTorch 2.7 documentation (original) (raw)

class torch.ao.nn.quantized.functional.adaptive_avg_pool2d(input, output_size)[source][source]¶

Applies a 2D adaptive average pooling over a quantized input signal composed of several quantized input planes.

Note

The input quantization parameters propagate to the output.

See AdaptiveAvgPool2d for details and output shape.

Parameters

output_size (None) – the target output size (single integer or double-integer tuple)

Return type

Tensor