资源分类
》 资源 》算法》Convolutional Neural Fabrics

Convolutional Neural Fabrics

2019-09-19 | |  135 |   0 |   0

PyTorch implementation of Convolutional Neural Fabrics arxiv:1606.02492 There are some minor differences: - The raw image is first convolved, to obtain #channels feature maps. - The upsampling is followed by a convolution, and the result is then summed with the other inputs. In the paper, they first sum and then convolve on the result. - These can be easily changed in the UpSample, DownSample, SameRes class definitions inside neural_fabrics.py. Feel free to implement your own procedure and experiment.

To run on CIFAR-10:

python neural_fabric.py --dataset cifar10 --save fabric_cifar10

Test set error: 7.2%, with rotation and translation augmented training data.

上一篇：variational-autoencoder

下一篇：NonLocal+SENet

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...