资源算法mpl.pytorch

mpl.pytorch

2019-10-09 | |  147 |   0 |   0

Max-Pooling Loss

Loss Max-Pooling for Semantic Image Segmentation

Installation

Requirements

To install PyTorch, please refer to https://github.com/pytorch/pytorch#installation.

Compiling

Some parts of Max-Pooling Loss have a native C++ implementation, which must be compiled with the following commands:

cd mpl
python build.py

Using

import mplimport torch

max_pooling_loss = mpl.MaxPoolingLoss(ratio=0.3, p=1.7, reduce=True)
loss = torch.Tensor(1, 3, 3, 3).uniform_(0, 1)
loss = max_pooling_loss(loss)


上一篇:pytorch-summary

下一篇:apex

用户评价
全部评价

热门资源

  • TensorFlow-Course

    This repository aims to provide simple and read...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • mxnet_VanillaCNN

    This is a mxnet implementation of the Vanilla C...

  • vsepp_tensorflow

    Improving Visual-Semantic Embeddings with Hard ...

  • DuReader_QANet_BiDAF

    Machine Reading Comprehension on DuReader Usin...