Quantizing the model - 2.5 English

• Prepare dataset. For tf_resnet50 model, download the calibration images from Imagenet_calib.tar.gz, and copy into Vitis-AI folder (Full dataset is from ImageNet).
• Launch the docker image

  [Host]$ ./docker_run.sh xilinx/vitis-ai-cpu:latest

• Quantize the model
  Set CALIB_BATCH_SIZE in the tf_resnetv1_50_imagenet_224_224_6.97G_2.5/code/quantize/config.ini to 5. Then run

  
  [Docker]$ conda activate vitis-ai-tensorflow
  [Docker]$ tar -xzvf Imagenet_calib.tar.gz -C tf_resnetv1_50_imagenet_224_224_6.97G_2.5/data
  [Docker]$ cd tf_resnetv1_50_imagenet_224_224_6.97G_2.5/code/quantize
  [Docker]$ bash quantize.sh

After running quantize.sh, the quantized model are available in tf_resnetv1_50_imagenet_224_224_6.97G_2.5/quantized