Model compression: OpenCV Object Detection and Framing
$50 USD
Cancelled
Posted about 5 years ago
$50 USD
Paid on delivery
I have a Mobile SSD algorithm to do people detection and framing, the model size is 22mb, I want to compress it to 1.5mb without losing too much accuracy. You can use methods like channel-pruning, changing the model, and transform the float number to int.
What I need: source code to modify the large model, not only for this project.
The introduction of the algorithm:
I placed a camera on top of my TV covering my whole living room. It can detect people (one or multiple) in the room, frame them, and count the number in real time.
We use Mobile net + SSD to realize this.
Hi there,
I have many years of experiences in Machine Learning & Deep Learning fields with some related to compress model in Tensorflow. Through my skills, i will bring to you high quality results with reasonable price. If you interest on me, please feel free to ping me via chat for sharing details about your project. Best regards !!
As you know that machine learning is a trial and error method with educated guessing, I cannot tell you the exact process of how I will do the work before starting, but having worked with mobile net and ssd and having worked in production environment I am experienced in optimizing code and I am pretty sure I can do the work as expected. I am new to this freelancing market but I am experienced in the field of ML and I have my own startup. I will complete the project in 5 days aand show you a prototype and within 10 days I will deliver the completed code.