资源分类
》 资源 》算法》VGG16CAM-keras

VGG16CAM-keras

2020-02-07 | |  28 |   0 |   0

Implementation of the VGG-CAM model with keras

Source

Original matlab implementation and paper here.

Requirements

  • keras with theano backend (keras version 1.0.4 or later)

  • h5py

  • numpy

  • matplotlib

  • opencv3

External data

Download the keras vgg16 weights.

Usage

  1. Use the train_VGGCAM function to fine tune the VGG16 model on your data. You should write your own code to feed the data into the network.

  2. Use the plot_classmap function to then plot the class activation map on an image specified by its path.

The network is focusing on the cell phone the driver is holding, regardless of driver ID or hand position.

上一篇： py-faster-rcnn-dockerface

下一篇：cam_vgg

用户评价
全部评价

热门资源

  • 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 ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • shih-styletransfer

    shih-styletransfer Code from Style Transfer ...