资源分类
》 资源 》算法》VAE-Mnist-CoordConv

VAE-Mnist-CoordConv

2020-02-19 | |  36 |   0 |   0

An intriguing failing of convolutional neural networks and the CoordConv solution

Implementation of the CoordConv (Convolution and Deconvolution) for a Variational Autoencoder applied to the MNIST dataset

1. Install dependencies:

pip install -r requirements.txt

2. Run training without coordConv layers

python trainVAE.py --useCoordConv False

3. Run training with coordConv layers

python trainVAE.py --useCoordConv True

4. Display Reconstructions on TensorBoard

tensorboard --logdir logdir

5. Compare reconstructions:

python compare_generated_images.py


上一篇：CoordConvExperiments

下一篇：optimize-coordconv

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...