This project utilizes UDACITY self driving car simulator. All training data was obtained by capturing images of moving car. About 3000 images were used for training CNN. It utilized opencv,numpy,panda,imgaug,keras,tensorflow,socketio,as major libraries. The neural network worked well on the first track. The model.h5 file stored the trained model. elu and softmax activation function were employed. It can work on work stations without GPU but takes a considerable amount of time. It is expected that any person uses his training data to get different results.
-
Notifications
You must be signed in to change notification settings - Fork 0
about three thousand images were used for training CNN.It utilized opencv,NumPy,panda,imaging,Keras, TensorFlow,socketio,as major libraries.the neural network worked well on the first track.the model file stored the trained model.elu and softmax activation functions were employed.It can work on workstations without GPU but takes a considerable a…
mayanksinghrathore/AI_Self_driving_car_using_CNN_-
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
about three thousand images were used for training CNN.It utilized opencv,NumPy,panda,imaging,Keras, TensorFlow,socketio,as major libraries.the neural network worked well on the first track.the model file stored the trained model.elu and softmax activation functions were employed.It can work on workstations without GPU but takes a considerable a…
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published