# TensorFlow Deployment
## TF.js
- Browser-based models
## TF Lite
- Mobile/edge inference, quantization
## Data Pipelines
- TF Data Services
## Optimization
- Pruning, distillation, topology transforms
TensorFlow: Data and Deployment Specialization
4 Courses
- Browser-based Models with TensorFlow.js
- Device-based Models with TensorFlow Lite
- Data Pipelines with TensorFlow Data Services
- Advanced Deployment Scenarios with TensorFlow
TF Lite Benefits
- Lightweight + low-latency + privacy
- Improved power consumption
- Efficient model ready to use
Optimization Techniques
- Quantization (all CPU platforms, reduced latency, low memory)
- Weight pruning
- Model topology transforms
- Tensor decomposition
- Distillation
#TensorFlow #EdgeAI #MobileML #FarshidPirahansiah