From Research to Production: Deploying Deep Learning on Embedded Hardware
Practical lessons from deploying TensorFlow and PyTorch models to TensorRT on Jetson AGX Xavier - quantisation, latency trade-offs, and ONNX conversion.
Practical lessons from deploying TensorFlow and PyTorch models to TensorRT on Jetson AGX Xavier - quantisation, latency trade-offs, and ONNX conversion.