self-driving-car-sim | A self-driving car simulator built with Unity | Learning library
kandi X-RAY | self-driving-car-sim Summary
kandi X-RAY | self-driving-car-sim Summary
This simulator was built for Udacity's Self-Driving Car Nanodegree, to teach students how to train cars how to navigate road courses using deep learning. See more project details here. All the assets in this repository require Unity. Please follow the instructions below for the full setup.
Support
Quality
Security
License
Reuse
Top functions reviewed by kandi - BETA
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of self-driving-car-sim
self-driving-car-sim Key Features
self-driving-car-sim Examples and Code Snippets
Community Discussions
Trending Discussions on self-driving-car-sim
QUESTION
How to prevent a lazy Convolutional Neural Network? I end with a ‘lazy CNN’ after training it with KERAS. Whatever the input is, the output is constant. What do you think the problem is?
I try to repeat an experiment of NVIDIA’s End to End Learning for Self-Driving Cars the paper. Absolutely, I do not have a real car but a Udacity’s simulator . The simulator generates figures about the foreground of a car.
A CNN receives the figure, and it gives the steering angle to keep the car in the track. The rule of the game is to keep the simulated car runs in the track safely. It is not very difficult.
The strange thing is sometimes I end with a lazy CNN after training it with KERAS, which gives constant steering angles. The simulated car will go off the trick, but the output of the CNN has no change. Especially the layer gets deeper, e.g. the CNN in the paper.
If I use a CNN like this, I can get a useful model after training.
...ANSWER
Answered 2017-Dec-22 at 15:12I can't run your model, because neither the question not the GitHub repo contains the data. That's why I am 90% sure of my answer.
But I think the main problem of your network is the sigmoid
activation function after dense layers. I assume, it will train well when there's just two of them, but four is too much.
Unfortunately, NVidia's End to End Learning for Self-Driving Cars paper doesn't specify it explicitly, but these days the default activation is no longer sigmoid
(as it once was), but relu
. See this discussion if you're interested why that is so. So the solution I'm proposing is try this model:
Community Discussions, Code Snippets contain sources that include Stack Exchange Network
Vulnerabilities
No vulnerabilities reported
Install self-driving-car-sim
Support
Reuse Trending Solutions
Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items
Find more librariesStay Updated
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page