# deconv_vis

**Repository Path**: martbox/deconv_vis

## Basic Information

- **Project Name**: deconv_vis
- **Description**: Visualization of deep convolutional networks with deconvolution
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-01-27
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# deconv_vis

Visualizing the VGG16 image classification deep neural networks convolutional layers using deconvolution as proposed by Matt Zeiler and Rob Fergus in their paper in 2014. https://arxiv.org/abs/1311.2901
(no "switch" unpooling implemented yet)

Weights from:
https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_tf_dim_ordering_tf_kernels.h5