Windows.md

Using Intel® Model Zoo on Windows Systems

Prerequisites for running on bare metal

Basic requirements for running all TensorFlow models on Windows include:

• Install Python 3.7+ 64-bit release for Windows, and add it to your system %PATH% environment variable.
• Download and Install Microsoft Visual C++ 2022 Redistributable.
• MSYS2. If MSYS2 is installed to C:\msys64, add C:\msys64\usr\bin to your %PATH% environment variable. Add MSYS64_BASH=C:\msys64\usr\bin\bash.exe environment variable to your system. Then, using cmd.exe, run:

   pacman -S git patch unzip

• Install intel-tensorflow
• Install the common models dependencies:
  • python-tk
  • libsm6
  • libxext6
  • requests

Individual models may have additional dependencies that need to be installed before running it. Please follow the instructions in each model documentation.

Run TensorFlow models

The following list of models are tested on Windows, please check each model instructions from the Run from the Model Zoo repository column based on the available precisions.

Note that on Windows systems all of the system cores will be used. For users of Windows desktop/laptops, it is strongly encouraged to instead use the batch file provided here to open a Windows command prompt pre-configured with optimized settings to achieve high AI workload performance on Intel hardware (e.g. TigerLake & AlderLake) for image recognition models.

Use Case	Model	Mode	Run from the Model Zoo repository
Image Recognition	DenseNet169	Inference	FP32
Image Recognition	Inception V3	Inference	Int8 FP32
Image Recognition	Inception V4	Inference	Int8 FP32
Image Recognition	MobileNet V1*	Inference	Int8 FP32
Image Recognition	ResNet 101	Inference	Int8 FP32
Image Recognition	ResNet 50	Inference	Int8 FP32
Image Recognition	ResNet 50v1.5	Inference	Int8 FP32
Image Segmentation	3D U-Net MLPerf	Inference	FP32
Language Modeling	BERT	Inference	FP32
Language Translation	BERT	Inference	FP32
Language Translation	Transformer_LT_Official	Inference	FP32
Object Detection	R-FCN	Inference	Int8 FP32
Object Detection	SSD-MobileNet*	Inference	Int8 FP32
Object Detection	SSD-ResNet34*	Inference	Int8 FP32
Recommendation	DIEN	Inference	FP32
Recommendation	Wide & Deep	Inference	FP32