Qualcomm® Neural Processing SDK
v2.39.0
Overview
Setup
Tutorials and Examples
Network Models
Supported Network Layers
Supported ONNX Ops
Quantized vs Non-Quantized Models
User-defined Operations
Model Conversion
TensorFlow Model Conversion
Tensorflow Graph Compatibility
TFLite Model Conversion
PyTorch Model Conversion
ONNX Model Conversion
Quantizing a Model
Offline Graph Caching for DSP Runtime on HTP
Qairt Converter
Qairt Quantizer
Model Tips
Using MobilenetSSD
Using DeepLabv3
Input Data and Preprocessing
Benchmarking and Accuracy
Tools
Debug Tools
API
Limitations
Revision History
References
Qualcomm® Neural Processing SDK
»
Network Models
»
Model Conversion
»
Model Tips
Model Tips
¶
MobilenetSSD
DeepLabv3