resnet_ptq_cpu.json

{
    "input_model":{
        "type": "PyTorchModel",
        "config": {
            "model_path": "models/resnet_trained_for_cifar10.pt",
            "io_config": {
                "input_names": ["input"],
                "input_shapes": [[1, 3, 32, 32]],
                "output_names": ["output"],
                "dynamic_axes": {
                    "input": {"0": "batch_size"},
                    "output": {"0": "batch_size"}
                }
            }
        }
    },
    "evaluators": {
        "common_evaluator":{
            "metrics":[
                {
                    "name": "accuracy",
                    "type": "custom",
                    "sub_types": [
                        {
                            "name": "accuracy_custom",
                            "priority": 1, "higher_is_better": true,
                            "goal": {"type": "max-degradation", "value": 0.01}
                        }
                    ],
                    "user_config":{
                        "user_script": "user_script.py",
                        "data_dir": "data",
                        "evaluate_func": "eval_accuracy",
                        "batch_size": 16
                    }
                },
                {
                    "name": "latency",
                    "type": "latency",
                    "sub_types": [
                        {
                            "name": "avg",
                            "priority": 2,
                            "goal": {"type": "percent-min-improvement", "value": 20}
                        }
                    ],
                    "user_config":{
                        "user_script": "user_script.py",
                        "data_dir": "data",
                        "dataloader_func": "create_dataloader",
                        "batch_size": 16
                    }
                }
            ]
        }
    },
    "passes": {
        "onnx_conversion": {
            "type": "OnnxConversion",
            "config": {
                "target_opset": 13
            }
        },
        "onnx_quantization": {
            "type": "OnnxQuantization",
            "config": {
                "user_script": "user_script.py",
                "data_dir": "data",
                "dataloader_func": "resnet_calibration_reader",
                "weight_type": "QUInt8",
                "activation_type": "QUInt8",
                "quant_preprocess": true
            }
        },
        "perf_tuning": {
            "type": "OrtPerfTuning",
            "config": {
                "user_script": "user_script.py",
                "dataloader_func": "create_dataloader",
                "batch_size": 16,
                "data_dir": "data"
            }
        }
    },
    "engine": {
        "search_strategy": {
            "execution_order": "joint",
            "search_algorithm": "exhaustive"
        },
        "evaluator": "common_evaluator",
        "execution_providers": ["CPUExecutionProvider"],
        "cache_dir": "cache",
        "output_dir": "models/resnet_ptq_cpu"
    }
}