This project is from a kaggle competition in 2016, we use mobileNet V2 to achieve classification recognition based on pytorch.
The implementation of the [State Farm Distracted Driver Detection] competition in kaggle.
Classify a picture of driver behavior, a total of 10 categories
The 10 classes to predict are:
c0: safe driving
c1: texting - right
c2: talking on the phone - right
c3: texting - left
c4: talking on the phone - left
c5: operating the radio
c6: drinking
c7: reaching behind
c8: hair and makeup
c9: talking to passenger
Training and identification with MobileNet V2
https://www.kaggle.com/c/state-farm-distracted-driver-detection/data
1: Download the repository to the local;
2: In this directory, create a folder as follows, and download the train dataset to the data folder:
---data
------train
pytorch1.0.1
easydict
torchvision
PIL
python-opencv
pip install --upgrade git+https://github.com/Lyken17/pytorch-OpCounter.git
2、3、1 training
- python train.py
2、3、2 testing
- Select the model to load, write it to test.py, then python test.py