PyTorch torch.quantized_max_pool1d Function
Pytorch torch Reference Manual
torch.quantized_max_pool1dThis is a function in PyTorch used to perform one-dimensional max pooling operations on quantized tensors. This function is used for downsampling in quantized convolutional neural networks.
Function Definition
torch.quantized_max_pool1d(input, kernel_size, stride, padding, dilation)
Parameter Description
input: The input quantized tensor (3D: batch x channel x length)kernel_size: Pooling window sizestride: Stride (optional)padding: Padding (optional)dilation: Dilation (optional)
Usage Example
Example
import torch
# Create quantized input tensor (batch=1, channel=1, length=10)
input = torch.quantize_per_tensor(torch.randn(1, 1, 10), scale=0.1, zero_point=0, dtype=torch.quint8)
# Perform quantized max pooling
output = torch.quantized_max_pool1d(input, kernel_size=3, stride=2, padding=1)
print("Input shape:", input.shape)
print("Output shape:", output.shape)
# Create quantized input tensor (batch=1, channel=1, length=10)
input = torch.quantize_per_tensor(torch.randn(1, 1, 10), scale=0.1, zero_point=0, dtype=torch.quint8)
# Perform quantized max pooling
output = torch.quantized_max_pool1d(input, kernel_size=3, stride=2, padding=1)
print("Input shape:", input.shape)
print("Output shape:", output.shape)
The output result is:
输入形状: torch.Size([1, 1, 10]) 输出形状: torch.Size([1, 1, 5])
Other Extensions