深度学习-识别红绿灯-交通信号排

识别红绿灯比赛：

博客：

https://medium.freecodecamp.org/recognizing-traffic-lights-with-deep-learning-23dae23287cc

Software and hardware

I used Caffe to train the models. The main reason I chose Caffe was because of the large variety of pre-trained models.

Python, NumPy & Jupyter Notebook were used for analyzing results, data exploration and ad-hoc scripts.

Amazon’s GPU instances (g2.2xlarge) were used to train the models. My AWS bill ended up being $263 (!). Not cheap. ?

The code and files I used to train and run the model are on GitHub.

github地址：

https://github.com/davidbrai/deep-learning-traffic-lights

SqueezeNet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.

Since the competition rewards solutions that use small models, early on I decided to look for a compact network with as few parameters as possible that can still produce good results. Most of the recently published networks are very deep and have a lot of parameters. SqueezeNet seemed to be a very good fit, and it also had a pre-trained model trained on ImageNet available in Caffe’s Model Zoo which came in handy.

鲸鱼识别比赛：

https://deepsense.ai/deep-learning-right-whale-recognition-kaggle/

SqueezeNet变种：

https://github.com/songhan/SqueezeNet-Residual

https://github.com/songhan/SqueezeNet-DSD-Training

识别交通信号牌：

https://hackernoon.com/traffic-signs-classification-with-deep-learning-b0cb03e23efb

github代码：

https://github.com/MehdiSv/TrafficSignsRecognition/ 

 

还有一个博客：

https://www.jianshu.com/p/39d1d8af7c57