Cut(prototxt) - 1.2 English

The auto_cut_deploy.prototxt generated in the previous step, has complete information to run inference. For example:

Notebook execution

There are two example notebooks (image detection and image classification) that can be accessed from $VAI_ALVEO_ROOT/notebooks to understand these steps in detail.

Script execution

There is a python script that can be used to run the models with default settings. It can be run using the following commands:

PreparePhase

Python

$VAI_ALVEO_ROOT/examples/caffe/run.py --prototxt <example prototxt> --caffemodel <example caffemodel> --prepare

prototxt

Path to model’s prototxt

caffemodel

Path to models caffemodel

output_dir

Path to save the quantization, compiler and subgraph_cut files

qtest_iter

Number of iterations to test the quantization

qcalib_iter

Number of iterations to calibration used for quantization

Validate Phase

Python

$VAI_ALVEO_ROOT/examples/caffe/run.py –validate

output_dir

If output_dir is given in the prepare phase, give the same argument and value to use the files generated in prepare phase.

numBatches

Number of batches which can be used to test the inference.