Accuracy

Accuracy

Framework	Version	Architecture	Archive	HTML	XLSX	Comments
Intel® Distribution of OpenVINO™ Toolkit	2023.3	x86	ZIP TAR.GZ	HTML	XLSX	—
TFLite	2.14	RISC-V	ZIP TAR.GZ	—	XLSX	Parameters: Models downloaded and converted to .tflite by script convert_models_to_tflite.sh Accuracy calculated on the first 1000 images of the ImageNet validation dataset
Apache TVM	0.15	RISC-V	ZIP TAR.GZ	—	XLSX	Parameters: Models downloaded and converted to .json by script convert_models_to_tvm.sh and compiled to .tar by script compile_tvm_models.sh opt_level=2 Accuracy calculated on the first 1000 images of the ImageNet validation dataset
OpenVINO™ toolkit	2023.3.0	RISC-V	ZIP TAR.GZ	—	XLSX	Guide to build the OpenVINO toolkit is available here Accuracy calculated on the first 1000 images of the ImageNet validation dataset
Apache TVM	0.14	x86	ZIP TAR.GZ	—	XLSX	Parameters: Models downloaded and converted to .json by script: convert_models_to_tvm.sh opt_level=2
Apache TVM	0.14.dev264	x86	ZIP TAR.GZ	—	XLSX	Parameters: Models downloaded and converted to .json by script: convert_models_to_tvm.sh opt_level=0
Intel® Distribution of OpenVINO™ Toolkit	2022.3	x86	ZIP TAR.GZ	HTML	XLSX	—
Intel® Distribution of OpenVINO™ Toolkit	2022.2	x86	ZIP TAR.GZ	HTML	XLSX	—
Intel® Distribution of OpenVINO™ Toolkit	2022.1	x86	ZIP TAR.GZ	HTML	XLSX	—
Intel® Distribution of OpenVINO™ Toolkit	2021.4	x86	ZIP TAR.GZ	HTML	XLSX	—