Model Evaluation

Introduction

Evaluate mode is used to test the performance of the model on the reserved test set for the specified task. Similar to training, the routine can be customized via CLI configuration file or by setting the parameters directly in the code. The evaluation process involves testing the model’s performance on the test data to measure its accuracy, precision, recall, and F1 score. A number of results and metrics will be generated and saved to the job_dir.

1. Load the configuration data (e.g. configuration.json)
2. Load the desired datasets (e.g. PtbxlDataset)
3. Load the corresponding task dataloaders (e.g. PtbxlDataLoader)
4. Load the trained model (e.g. model.keras)
5. Define the metrics (e.g. accuracy)
6. Evaluate the model (e.g. model.evaluate)
7. Generate evaluation report (e.g. report.json)

Example configuration

modes-evaluate-1.json150 lines · JSONDownload

Show full exampleCollapse example

modes-evaluate-1.json

{
    "name": "arr-2-eff-sm",
    "project": "hk-rhythm-2",
    "job_dir": "./results/arr-2-eff-sm",
    "verbose": 2,
    "datasets": [
        {
            "name": "ptbxl",
            "params": {
                "path": "./datasets/ptbxl"
            }
        }
    ],
    "num_classes": 2,
    "class_map": {
        "0": 0,
        "7": 1,
        "8": 1
    },
    "class_names": [
        "NORMAL",
        "AFIB/AFL"
    ],
    "class_weights": "balanced",
    "sampling_rate": 100,
    "frame_size": 512,
    "samples_per_patient": [
        10,
        10
    ],
    "val_samples_per_patient": [
        5,
        5
    ],
    "test_samples_per_patient": [
        5,
        5
    ],
    "val_patients": 0.2,
    "val_size": 20000,
    "test_size": 20000,
    "batch_size": 256,
    "buffer_size": 20000,
    "epochs": 100,
    "steps_per_epoch": 50,
    "val_metric": "loss",
    "lr_rate": 0.001,
    "lr_cycles": 1,
    "threshold": 0.75,
    "val_metric_threshold": 0.98,
    "tflm_var_name": "g_rhythm_model",
    "tflm_file": "rhythm_model_buffer.h",
    "backend": "pc",
    "demo_size": 896,
    "display_report": true,
    "quantization": {
        "qat": false,
        "format": "INT8",
        "io_type": "int8",
        "conversion": "CONCRETE",
        "debug": false
    },
    "preprocesses": [
        {
            "name": "layer_norm",
            "params": {
                "epsilon": 0.01,
                "name": "znorm"
            }
        }
    ],
    "augmentations": [],
    "model_file": "model.keras",
    "use_logits": false,
    "architecture": {
        "name": "efficientnetv2",
        "params": {
            "input_filters": 16,
            "input_kernel_size": [
                1,
                9
            ],
            "input_strides": [
                1,
                2
            ],
            "blocks": [
                {
                    "filters": 24,
                    "depth": 2,
                    "kernel_size": [
                        1,
                        9
                    ],
                    "strides": [
                        1,
                        2
                    ],
                    "ex_ratio": 1,
                    "se_ratio": 2
                },
                {
                    "filters": 32,
                    "depth": 2,
                    "kernel_size": [
                        1,
                        9
                    ],
                    "strides": [
                        1,
                        2
                    ],
                    "ex_ratio": 1,
                    "se_ratio": 2
                },
                {
                    "filters": 40,
                    "depth": 2,
                    "kernel_size": [
                        1,
                        9
                    ],
                    "strides": [
                        1,
                        2
                    ],
                    "ex_ratio": 1,
                    "se_ratio": 2
                },
                {
                    "filters": 48,
                    "depth": 1,
                    "kernel_size": [
                        1,
                        9
                    ],
                    "strides": [
                        1,
                        2
                    ],
                    "ex_ratio": 1,
                    "se_ratio": 2
                }
            ],
            "output_filters": 0,
            "include_top": true,
            "use_logits": true
        }
    }
}

{
    "name": "arr-2-eff-sm",
    "project": "hk-rhythm-2",
    "job_dir": "./results/arr-2-eff-sm",
    "verbose": 2,
    "datasets": [
        {
            "name": "ptbxl",

… 142 more lines

---

Usage

CLI

The following command will evaluate a rhythm model using the reference configuration.

Terminal

heartkit --task rhythm --mode evaluate --config ./configuration.json

Python

The model can be evaluated using the following snippet:

Python example

task = hk.TaskFactory.get("rhythm")

params = hk.HKTaskParams(...)

task.evaluate(params)

Example configuration

modes-evaluate-4.py82 lines · PYTHONDownload

Show full exampleCollapse example

modes-evaluate-4.py

hk.HKTaskParams(
    name="arr-2-eff-sm",
    project="hk-rhythm-2",
    job_dir="./results/arr-2-eff-sm",
    verbose=2,
    datasets=[hk.NamedParams(
        name="ptbxl",
        params=dict(
            path="./datasets/ptbxl"
        )
    )],
    num_classes=2,
    class_map={
        "0": 0,
        "7": 1,
        "8": 1
    },
    class_names=[
        "NORMAL", "AFIB/AFL"
    ],
    class_weights="balanced",
    sampling_rate=100,
    frame_size=512,
    samples_per_patient=[10, 10],
    val_samples_per_patient=[5, 5],
    test_samples_per_patient=[5, 5],
    val_patients=0.20,
    val_size=20000,
    test_size=20000,
    batch_size=256,
    buffer_size=20000,
    epochs=100,
    steps_per_epoch=50,
    val_metric="loss",
    lr_rate=1e-3,
    lr_cycles=1,
    threshold=0.75,
    val_metric_threshold=0.98,
    tflm_var_name="g_rhythm_model",
    tflm_file="rhythm_model_buffer.h",
    backend="pc",
    demo_size=896,
    display_report=True,
    quantization=hk.QuantizationParams(
        qat=False,
        format="INT8",
        io_type="int8",
        conversion="CONCRETE",
        debug=False
    ),
    preprocesses=[
        hk.NamedParams(
            name="layer_norm",
            params=dict(
                epsilon=0.01,
                name="znorm"
            )
        )
    ],
    augmentations=[
    ],
    model_file="model.keras",
    use_logits=False,
    architecture=hk.NamedParams(
        name="efficientnetv2",
        params=dict(
            input_filters=16,
            input_kernel_size=[1, 9],
            input_strides=[1, 2],
            blocks=[
                {"filters": 24, "depth": 2, "kernel_size": [1, 9], "strides": [1, 2], "ex_ratio": 1,  "se_ratio": 2},
                {"filters": 32, "depth": 2, "kernel_size": [1, 9], "strides": [1, 2], "ex_ratio": 1,  "se_ratio": 2},
                {"filters": 40, "depth": 2, "kernel_size": [1, 9], "strides": [1, 2], "ex_ratio": 1,  "se_ratio": 2},
                {"filters": 48, "depth": 1, "kernel_size": [1, 9], "strides": [1, 2], "ex_ratio": 1,  "se_ratio": 2}
            ],
            output_filters=0,
            include_top=True,
            use_logits=True
        )
    }
)

hk.HKTaskParams(
    name="arr-2-eff-sm",
    project="hk-rhythm-2",
    job_dir="./results/arr-2-eff-sm",
    verbose=2,
    datasets=[hk.NamedParams(
        name="ptbxl",

… 74 more lines

---

Arguments

Please refer to HKTaskParams for the list of arguments that can be used with the evaluate command.