Skip to main content
Version: v2509

Tutorial

This is a tutorial on accelerating the inference speed of image classification with ResNet50 using AcuiRT.

Introduction​

  • Please refer to the Setup to install AcuiRT.

1. Prepare the dataset​

  • Prepare a subset of ImageNet.

    git clone https://github.com/EliSchwartz/imagenet-sample-images

2. Execute the conversion​

  • Run faib/intelligence/components/acuirt/example/image_classification_resnet50.py. This sample converts ResNet50 to a TensorRT model with int8 quantization to accelerate inference.

    python faib/intelligence/components/acuirt/example/image_classificatoin_resnet50.py

  • The Top-1 accuracy and inference time are displayed for both the PyTorch model inference and the TensorRT model conversion.

  • Example output

    PyTorch: Top-1 Accuracy: 887/1000 (88.70%), Average Inference Time: 1618.08μs
    AcuiRT: Top-1 Accuracy: 882/1000 (88.20%), Average Inference Time: 415.05μs