keras-salient-object-visualisation
所属分类：其他
开发工具：Python
文件大小：16497KB
下载次数：0
上传日期：2020-10-28 13:14:23
上 传 者：
韩国的使者
说明： 基于端到端控制方法实现的自动驾驶，深度模型通过识别道路和路旁的哪些特征做出驾驶决策！
(Based on the end-to-end control method for automatic driving, the depth model makes driving decisions by identifying which features of the road and roadside.)
文件列表:
keras-salient-object-visualisation (0, 2019-06-10)
keras-salient-object-visualisation\.ipynb_checkpoints (0, 2019-06-10)
keras-salient-object-visualisation\.ipynb_checkpoints\keras-salient-object-visualisation-checkpoint.ipynb (1456741, 2019-06-10)
keras-salient-object-visualisation\LICENSE (11357, 2019-06-10)
... ...
# keras-salient-object-visualization
[](https://youtu.be/bgGEonerPiw "Donkey car network visualization based on Nvidia paper")
Keras implementation of nvidia paper 'Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car'.
The goal of the visualization is to explain what Donkey Car (https://github.com/wroscoe/donkey) learns and how it makes its decisions. The central idea in discerning the salient objects is finding parts of the image that correspond to
locations where the feature maps of CNN layers have the greatest activations.
Original paper: https://arxiv.org/pdf/1704.07911.pdf
近期下载者：
相关文件：
收藏者：