Vitis AI Quantizer#

Note

The Vitis AI Quantizer has been deprecated as of the Ryzen AI 1.3 release. AMD strongly recommends using the new AMD Quark Quantizer instead (please refer to the main documentation about Model Quantization).

Vitis AI Quantizer for ONNX#

Vitis AI Quantizer for ONNX: Provides an easy-to-use Post Training Quantization (PTQ) flow on the pre-trained model saved in the ONNX format. It generates a quantized ONNX model ready to be deployed with the Ryzen AI Software.

For more details, refer to the Vitis AI Quantizer for ONNX section of this documentation.

Vitis AI Quantizer for PyTorch#

Vitis AI Quantizer for PyTorch: Allows quantizing models through the PyTorch framework. This flow supports both post-training quantization (PTQ) and quantization-aware training (QAT) to improve model accuracy.

For more details, refer to the Vitis AI Quantizer for PyTorch section of this documentation.

Vitis AI Quantizer for TensorFlow 2#

Vitis AI Quantizer for TensorFlow 2: Allows quantizing models through the TensorFlow framework. This flow supports both post-training quantization (PTQ) and quantization-aware training (QAT) to improve model accuracy.

For more details, refer to the Vitis AI Quantizer for TensorFlow section of this documentation.