Traffic violations detection using Faster R-CNN with Intel® DevCloud
Project work based on deep learning algorithm and data preprocessing
What is Intel® DevCloud?
The DevCloud is a cluster of Intel® Xeon® Scalable Processors that will assist you with your machine learning and deep learning training and inference compute needs. It provides access to precompiled software optimized for Intel® architecture on Intel Xeon Scalable Processors. It includes:
- Intel® Software Optimization for neon™
- TensorFlow* on Intel® Architecture
- Intel® Optimizations for MXNet*
- Intel® Distribution for Caffe*
- Intel® Distribution for Python* 2.7 and 3.6 including NumPy, SciPy, pandas, scikit-learn, Jupyter, matplotlib, and mpi4py
- Intel® Software Optimization for Keras*
- Intel® Software Optimization for Theano*
- Intel Nervana AI platforms and technologies that become available in the future
When you gain access to the DevCloud, you will log into a Linux-based head node of a batch farm. There you can stage your code and data, compile, and submit jobs to a queue. Once the queued job completes, your results will be in your home folder.
- Jobs are scheduled on Intel® Xeon® Scalable Processors.
- Each processor has 24 cores with 2-way hyperthreading.
- Each processor has access to 96 GB of on-platform RAM (DDR4)
- Only one job will run on any processor at a time.
- You will get 200 GB of file storage quota.
- Your home directory is not visible to other users.
- Once your access period expires, your home directory on the cluster will be deleted.
This is so much computing power! Now let's solve a real-time problem…
In 2015, there were about five lakh road accidents in India, which killed about 1.5 lakh people and injured about five lakh people causing annual monetary loss of millions.
…with the help of computer vision and deep learning frameworks such as TensorFlow 2.0 and Keras.
DevCloud provides Jupyter Notebooks using high performing intel processors. Our team used video extracted image data and annotated using the Intel annotator tool. Annotated data is given to a faster RCNN algorithm where we split the date and train the model for several iterations!
The motivation behind using Faster RCNN was as traffic data is real-time data and consisting of images and videos. The results were pretty impressive and the development is being continuously done further with the help of the image segmentation to differentiate various modules of traffic violations! ✌️
For setting up & accessing Intel DevCloud follow this tutorial…
https://devmesh.intel.com/users/ajinkya-jawale/groups
Here is some help from Intel resources!
Follow the Intel DevCloud community! LOVE CODING ! MAKE PEACE! ❤️
Intel DevMesh & Intel DevCloud Thanks! :)
Resources:
- Ajinkya Jawale - https://devmesh.intel.com/users/ajinkya-jawale/groups
Find more and more knowledgeable resources related to #ai #machinelearning #deeplearning #python…https://twitter.com/Ajinkya_Tweets
Ajinkya Jawale, https://www.linkedin.com/in/ajinkya-jawale-b3421a12a/
https://angel.co/ajinkya-jawale
Reach me here, ajinkyajawale14499@gmail.com
gracies!