torch命令总结

import torch.nn as nn
class Model(nn.Module){
	def __init__(self):
		super(Model).__init__()
		self.BN = nn.BatchNorm2d(self.inplanes, eps=2e-05, momentum=0.9)
		self.conv2d = nn.Conv2d(in_channel, out_channel, kernel_size=3, stride=1, padding=1,bias=False)
		self.avgpool = nn.AdaptiveAvgPool2d(self.kernal)
		self.downsample = downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion, stride),
                nn.BatchNorm2d(planes * block.expansion, eps=2e-05, momentum=0.9),
            )
	def forward(self){
		x = self.BN(x)
		x = self.conv2d(x)
		return x
	}
}

self.Leakyrelu = nn.LeakyReLU(0.1, inplace=True)
self.deconv = nn.ConvTranpose2d(in_channels=in_c, out_channels=out_c, kernel_size=4, stride=2, padding=1, bias=False)



import torch.nn.functional as F
m = F.interpolate(x, scale_factor=2, mode='bilinear', align_corners=True) # 双线性插值-上采样
"""
    参数:
    - input (Tensor): input tensor
    - size(None) (int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int]):输出的 spatial 尺寸.
    - scale_factor(None) (float or Tuple[float]): spatial 尺寸的缩放因子.
    - mode (string): 上采样算法:nearest, linear, bilinear, trilinear, area. 默认为 nearest.
    - align_corners (bool, optional): 如果 align_corners=True，则对齐 input 和 output 的角点像素(corner pixels)，保持在角点像素的值. 只会对 mode=linear, bilinear 和 trilinear 有作用. 默认是 False.
"""