If you need help with anything quantization or ML related (e.g. debugging code) feel free to book a 30 minute consultation session! https://calendly.com/oscar-savolainen
I'm also available for long-term freelance work, e.g. for training / productionizing models, teaching AI concepts, etc.
Video Summary:
In this video we take a PyTorch (torchvision) ResNEt18 model and quantize it from scratch, using FX Graph Mode quantization.
We get used to the basic operations one has to do to FX quantize a model, and gain some familiarity with GraphModules. This is the 1st of 3 videos on FX Graph mode quantization, where in the later parts we will dive into more advanced aspects of FX Graph mode quantization (e.g. graph traversal and manipulation).
I can only apologize for the mic and webcam quality! Ubuntu just hates my microphone. Within a few videos I'll have an actual proper microphone and webcam!
Timestamps:
00:00 Intro
02:03 Setting up
04:15 Getting the ResNet model
06:10 Starting on main.py
07:35 Creating QConfigs
14:05 Creating QConfig Mapper
15:00 FX Graph Mode Quantization
17:30 Printing out the graph
21:07 Conclusion
Links:
See the code at:
https://github.com/OscarSavolainen/Qu...
Connect on LinkedIn: / oscar-savolainen-phd-b88277121
On this page of the site you can watch the video online How to do FX Graph Mode Quantization: FX Graph Mode Quantization Coding tutorial - Part 1/3 with a duration of hours minute second in good quality, which was uploaded by the user Oscar Savolainen 12 March 2024, share the link with friends and acquaintances, this video has already been watched 1,354 times on youtube and it was liked by 42 viewers. Enjoy your viewing!