Running Deep Learning Models on Mobile with optimised speed
summary
Shows how to deploy task-specific deep learning models on iOS and Android with a focus on performance and memory footprint. Covers techniques for speeding up mobile inference and reducing model size, and discusses practical difficulties and how to build custom mobile libraries (rather than relying on slow, memory-heavy wrappers).
AI-written summary · about
chapters (5)
- 0:00Start
- 5:01Applications
- 12:17Server based approach problems
- 16:52Complaints on performance
- 25:15Quality of results after quantization
related talks
46mFire Up Your Smartphone Neurons with On-Device Deep Learning
39mAI/ML on mobile/android with TensorFlow
41mWarm Up Your Smartphone's Neurons with Deep Learning
39mCreating smaller, faster, production-worthy mobile machine learning models for Android
15mSimplified Machine Learning on mobile, browsers, and edge devices with on-device ML
41mTensorFlow Neural Networks on iOS
40mDeep Learning on iOS
47mMachine Learning on Android Demystified