FlowNets

最新推荐文章于 2024-08-04 17:34:10 发布

访风景于崇阿

最新推荐文章于 2024-08-04 17:34:10 发布

阅读量68

点赞数

文章标签：深度学习 pytorch python

本文链接：https://blog.csdn.net/starlight1231/article/details/130724669

版权

本文介绍FlowNets在深度学习中的应用，主要关注如何使用Python和PyTorch实现光流估计。通过util.py和model.py两个关键文件，详细探讨了相关算法和代码实现。

摘要由CSDN通过智能技术生成

util.py

import torch.nn as nn
import torch.nn.functional as F

def conv(batchNorm, in_planes, out_planes, kernel_size=3, stride=1):
    if batchNorm:
        return nn.Sequential(
            nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=(kernel_size-1)//2, bias=False),
            nn.BatchNorm2d(out_planes),
            nn.LeakyReLU(0.1,inplace=True)
        )
    else:
        return nn.Sequential(
            nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=(kernel_size-1)//2, bias=True),
            nn.LeakyReLU(0.1,inplace=True)
        )


def predict_flow(in_planes):
    return nn.Conv2d(in_planes,2,kernel_size=3,stride=1,padding=1,bias=False)


def deconv(in_planes, out_planes):
    return nn.Sequential(
        nn.ConvTranspose2d(in_planes, out_planes, kernel_size=4, stride=2, padding=1, bias=False),
        nn.LeakyReLU(0.1,inplace=True)
    )

"""
# used for FlowNetC
def correlate(input1, input2):
    out_corr = spatial_correlation_sample(input1,
                                          input2,
                                          kernel_size=1,