资源算法VAE-Mnist-CoordConv

VAE-Mnist-CoordConv

2020-02-19 | |  68 |   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

  • DuReader_QANet_BiDAF

    Machine Reading Comprehension on DuReader Usin...

  • ETD_cataloguing_a...

    ETD catalouging project using allennlp

  • allennlp_extras

    allennlp_extras Some utilities build on top of...

  • allennlp-dureader

    An Apache 2.0 NLP research library, built on Py...

  • honk-honk-motherf...

    honk-honk-motherfucker