Predict

Prediction functions for ndarrays of device geometries.

predict_array(device_array, model, model_type, binarize)

Predict the nanofabrication outcome of a device array using a specified model.

This function sends the device array to a serverless prediction service, which uses a specified machine learning model to predict the outcome of the nanofabrication process.

Parameters:

Name	Type	Description	Default
device_array	ndarray	A 2D array representing the planar geometry of the device. This array undergoes various transformations to predict the nanofabrication process.	required
model	Model	The model to use for prediction, representing a specific fabrication process and dataset. This model encapsulates details about the fabrication foundry, process, material, technology, thickness, and sidewall presence, as defined in models.py. Each model is associated with a version and dataset that detail its creation and the data it was trained on, ensuring the prediction is tailored to specific fabrication parameters.	required
model_type	str	The type of model to use (e.g., 'p' for prediction, 'c' for correction, or 's' for SEMulate, 'b' for segmentation).	required
binarize	bool	If True, the predicted device geometry will be binarized using a threshold method. This is useful for converting probabilistic predictions into binary geometries.	required

Returns:

Type	Description
ndarray	The predicted output array. For single-level predictions, returns shape (h, w, 1). For multi-level predictions, returns shape (h, w, n) where n is the number of levels.

Raises:

Type	Description
RuntimeError	If the request to the prediction service fails.
ValueError	If the server returns an error or invalid response.

Source code in prefab/predict.py

def predict_array(
    device_array: np.ndarray,
    model: Model,
    model_type: str,
    binarize: bool,
) -> np.ndarray:
    """
    Predict the nanofabrication outcome of a device array using a specified model.

    This function sends the device array to a serverless prediction service, which uses
    a specified machine learning model to predict the outcome of the nanofabrication
    process.

    Parameters
    ----------
    device_array : np.ndarray
        A 2D array representing the planar geometry of the device. This array undergoes
        various transformations to predict the nanofabrication process.
    model : Model
        The model to use for prediction, representing a specific fabrication process and
        dataset. This model encapsulates details about the fabrication foundry, process,
        material, technology, thickness, and sidewall presence, as defined in
        `models.py`. Each model is associated with a version and dataset that detail its
        creation and the data it was trained on, ensuring the prediction is tailored to
        specific fabrication parameters.
    model_type : str
        The type of model to use (e.g., 'p' for prediction, 'c' for correction, or 's'
        for SEMulate, 'b' for segmentation).
    binarize : bool
        If True, the predicted device geometry will be binarized using a threshold
        method. This is useful for converting probabilistic predictions into binary
        geometries.

    Returns
    -------
    np.ndarray
        The predicted output array. For single-level predictions, returns shape
        (h, w, 1). For multi-level predictions, returns shape (h, w, n) where n is the
        number of levels.

    Raises
    ------
    RuntimeError
        If the request to the prediction service fails.
    ValueError
        If the server returns an error or invalid response.
    """
    endpoint_url = f"{BASE_ENDPOINT_URL}-v{ENDPOINT_VERSION}.modal.run"
    predict_data = {
        "device_array": _encode_array(np.squeeze(device_array)),
        "model": model.to_json(),
        "model_type": model_type,
    }
    headers = _prepare_headers()

    try:
        response = requests.post(
            url=endpoint_url, data=json.dumps(predict_data), headers=headers
        )
        response.raise_for_status()

        if not response.content:
            raise ValueError("Empty response received from server")

        response_data = response.json()

        if "error" in response_data:
            raise ValueError(f"Prediction error: {response_data['error']}")

        results = response_data["results"]
        result_arrays = [
            _decode_array(results[key])
            for key in sorted(results.keys())
            if key.startswith("result")
        ]

        prediction_array = np.stack(result_arrays, axis=-1)

        if binarize:
            prediction_array = binarize_hard(prediction_array)

        return prediction_array

    except requests.exceptions.RequestException as e:
        raise RuntimeError(f"Request failed: {e}") from e
    except json.JSONDecodeError as e:
        raise ValueError(f"JSON decode error: {e}") from e

predict_array_with_grad(device_array, model)

Predict the nanofabrication outcome of a device array and compute its gradient.

This function predicts the outcome of the nanofabrication process for a given device array using a specified model. It also computes the gradient of the prediction with respect to the input device array, making it suitable for use in automatic differentiation applications (e.g., autograd).

Parameters:

Name	Type	Description	Default
device_array	ndarray	A 2D array representing the planar geometry of the device.	required
model	Model	The model to use for prediction, representing a specific fabrication process.	required

Returns:

Type	Description
ndarray	The predicted output array.

Raises:

Type	Description
RuntimeError	If the request to the prediction service fails.
ValueError	If the server returns an error or invalid response.

Source code in prefab/predict.py

@primitive
def predict_array_with_grad(device_array: np.ndarray, model: Model) -> np.ndarray:
    """
    Predict the nanofabrication outcome of a device array and compute its gradient.

    This function predicts the outcome of the nanofabrication process for a given
    device array using a specified model. It also computes the gradient of the
    prediction with respect to the input device array, making it suitable for use in
    automatic differentiation applications (e.g., autograd).

    Parameters
    ----------
    device_array : np.ndarray
        A 2D array representing the planar geometry of the device.
    model : Model
        The model to use for prediction, representing a specific fabrication process.

    Returns
    -------
    np.ndarray
        The predicted output array.

    Raises
    ------
    RuntimeError
        If the request to the prediction service fails.
    ValueError
        If the server returns an error or invalid response.
    """
    prediction_array, gradient_array = _predict_array_with_grad(
        device_array=device_array, model=model
    )
    predict_array_with_grad.gradient_array = gradient_array  # type: ignore
    return prediction_array

predict_array_with_grad_vjp(ans, device_array, *args)

Define the vector-Jacobian product (VJP) for the prediction function.

Parameters:

Name	Type	Description	Default
ans	ndarray	The output of the predict_array_with_grad function.	required
device_array	ndarray	The input device array for which the gradient is computed.	required
*args		Additional arguments that aren't used in the VJP computation.	()

Returns:

Type	Description
function	A function that computes the VJP given an upstream gradient g.

Source code in prefab/predict.py

def predict_array_with_grad_vjp(ans: np.ndarray, device_array: np.ndarray, *args):
    """
    Define the vector-Jacobian product (VJP) for the prediction function.

    Parameters
    ----------
    ans : np.ndarray
        The output of the `predict_array_with_grad` function.
    device_array : np.ndarray
        The input device array for which the gradient is computed.
    *args :
        Additional arguments that aren't used in the VJP computation.

    Returns
    -------
    function
        A function that computes the VJP given an upstream gradient `g`.
    """
    grad_x = predict_array_with_grad.gradient_array  # type: ignore

    def vjp(g: np.ndarray) -> np.ndarray:
        return g * grad_x

    return vjp

predict_gds(gds_path, cell_name, model, model_type, gds_layer=(1, 0), eta=0.5, output_path=None)

Predict the nanofabrication outcome for a GDS file and cell.

This function loads a GDS file, extracts the specified cell, and predicts the nanofabrication outcome using the specified model. The predicted cell is automatically added to the original GDS library and the file is written to the specified output path (or overwrites the original if no output path is provided).

Parameters:

Name	Type	Description	Default
gds_path	str	The file path to the GDS file.	required
cell_name	str	The name of the cell within the GDS file to predict.	required
model	Model	The model to use for prediction, representing a specific fabrication process and dataset. This model encapsulates details about the fabrication foundry, process, material, technology, thickness, and sidewall presence, as defined in models.py. Each model is associated with a version and dataset that detail its creation and the data it was trained on, ensuring the prediction is tailored to specific fabrication parameters.	required
model_type	str	The type of model to use ('p' for prediction, 'c' for correction).	required
gds_layer	tuple[int, int]	The layer and datatype to use within the GDS file. Defaults to (1, 0).	(1, 0)
eta	float	The threshold value for binarization. Defaults to 0.5. Because intermediate values cannot be preserved in the polygon data, the predicted polygons are binarized using a threshold value of eta.	0.5
output_path	str	The file path where the updated GDS file will be written. If None, the original file will be overwritten. Defaults to None.	None

Raises:

Type	Description
RuntimeError	If the request to the prediction service fails.
ValueError	If the GDS file cannot be read, the specified cell is not found, or the server returns an error or invalid response.

Source code in prefab/predict.py

def predict_gds(
    gds_path: str,
    cell_name: str,
    model: Model,
    model_type: str,
    gds_layer: tuple[int, int] = (1, 0),
    eta: float = 0.5,
    output_path: str = None,
) -> None:
    """
    Predict the nanofabrication outcome for a GDS file and cell.

    This function loads a GDS file, extracts the specified cell, and predicts the
    nanofabrication outcome using the specified model. The predicted cell is
    automatically added to the original GDS library and the file is written to the
    specified output path (or overwrites the original if no output path is provided).

    Parameters
    ----------
    gds_path : str
        The file path to the GDS file.
    cell_name : str
        The name of the cell within the GDS file to predict.
    model : Model
        The model to use for prediction, representing a specific fabrication process and
        dataset. This model encapsulates details about the fabrication foundry, process,
        material, technology, thickness, and sidewall presence, as defined in
        `models.py`. Each model is associated with a version and dataset that detail its
        creation and the data it was trained on, ensuring the prediction is tailored to
        specific fabrication parameters.
    model_type : str
        The type of model to use ('p' for prediction, 'c' for correction).
    gds_layer : tuple[int, int]
        The layer and datatype to use within the GDS file. Defaults to (1, 0).
    eta : float
        The threshold value for binarization. Defaults to 0.5. Because intermediate
        values cannot be preserved in the polygon data, the predicted polygons are
        binarized using a threshold value of eta.
    output_path : str, optional
        The file path where the updated GDS file will be written. If None, the
        original file will be overwritten. Defaults to None.

    Raises
    ------
    RuntimeError
        If the request to the prediction service fails.
    ValueError
        If the GDS file cannot be read, the specified cell is not found, or the server
        returns an error or invalid response.
    """
    gdstk_library = gdstk.read_gds(gds_path)
    gdstk_cell = gdstk_library[cell_name]

    predicted_cell = predict_gdstk(
        gdstk_cell=gdstk_cell,
        model=model,
        model_type=model_type,
        gds_layer=gds_layer,
        eta=eta,
    )

    base_name = predicted_cell.name
    counter = 1
    while predicted_cell.name in [cell.name for cell in gdstk_library.cells]:
        predicted_cell.name = f"{base_name}_{counter}"
        counter += 1

    gdstk_library.add(predicted_cell)

    write_path = output_path if output_path is not None else gds_path
    gdstk_library.write_gds(write_path, max_points=8190)

predict_gdstk(gdstk_cell, model, model_type, gds_layer=(1, 0), eta=0.5)

Predict the nanofabrication outcome of a gdstk cell using a specified model.

This function extracts polygons from a gdstk cell, sends them to a serverless prediction service, and returns a new cell containing the predicted polygons.

Parameters:

Name	Type	Description	Default
gdstk_cell	Cell	The gdstk.Cell object containing polygons to predict.	required
model	Model	The model to use for prediction, representing a specific fabrication process and dataset. This model encapsulates details about the fabrication foundry, process, material, technology, thickness, and sidewall presence, as defined in models.py. Each model is associated with a version and dataset that detail its creation and the data it was trained on, ensuring the prediction is tailored to specific fabrication parameters.	required
model_type	str	The type of model to use ('p' for prediction, 'c' for correction).	required
gds_layer	tuple[int, int]	The layer and datatype to use within the GDSTK cell. Defaults to (1, 0).	(1, 0)
eta	float	The threshold value for binarization. Defaults to 0.5. Because intermediate values cannot be preserved in the polygon data, the predicted polygons are binarized using a threshold value of eta.	0.5

Returns:

Type	Description
Cell	A new gdstk cell containing the predicted polygons. For multi-level predictions, each level's polygons will be placed on a different layer: - Level 0: (layer, 99) - Level 1: (layer, 100)

Raises:

Type	Description
RuntimeError	If the request to the prediction service fails.
ValueError	If no polygons are found in the specified layer, or the server returns an error or invalid response.

Source code in prefab/predict.py

def predict_gdstk(
    gdstk_cell: gdstk.Cell,
    model: Model,
    model_type: str,
    gds_layer: tuple[int, int] = (1, 0),
    eta: float = 0.5,
) -> gdstk.Cell:
    """
    Predict the nanofabrication outcome of a gdstk cell using a specified model.

    This function extracts polygons from a gdstk cell, sends them to a serverless
    prediction service, and returns a new cell containing the predicted polygons.

    Parameters
    ----------
    gdstk_cell : gdstk.Cell
        The gdstk.Cell object containing polygons to predict.
    model : Model
        The model to use for prediction, representing a specific fabrication process and
        dataset. This model encapsulates details about the fabrication foundry, process,
        material, technology, thickness, and sidewall presence, as defined in
        `models.py`. Each model is associated with a version and dataset that detail its
        creation and the data it was trained on, ensuring the prediction is tailored to
        specific fabrication parameters.
    model_type : str
        The type of model to use ('p' for prediction, 'c' for correction).
    gds_layer : tuple[int, int]
        The layer and datatype to use within the GDSTK cell. Defaults to (1, 0).
    eta : float
        The threshold value for binarization. Defaults to 0.5. Because intermediate
        values cannot be preserved in the polygon data, the predicted polygons are
        binarized using a threshold value of eta.

    Returns
    -------
    gdstk.Cell
        A new gdstk cell containing the predicted polygons. For multi-level
        predictions, each level's polygons will be placed on a different layer:
        - Level 0: (layer, 99)
        - Level 1: (layer, 100)

    Raises
    ------
    RuntimeError
        If the request to the prediction service fails.
    ValueError
        If no polygons are found in the specified layer, or the server returns an error
        or invalid response.
    """
    polygons = gdstk_cell.get_polygons(layer=gds_layer[0], datatype=gds_layer[1])
    if not polygons:
        raise ValueError("No polygons found in the specified layer")

    polygon_points = [polygon.points.tolist() for polygon in polygons]

    predicted_polygon_data = _predict_poly(
        polygon_points=polygon_points,
        model=model,
        model_type=model_type,
        eta=eta,
    )

    result_cell = gdstk.Cell(f"{gdstk_cell.name}_predicted")

    polygons_by_channel = {}
    for polygon_data in predicted_polygon_data:
        channel = polygon_data.get("channel", 0)
        points = polygon_data.get("points", [])

        if channel not in polygons_by_channel:
            polygons_by_channel[channel] = []

        polygons_by_channel[channel].append(points)

    for channel, points_list in polygons_by_channel.items():
        layer = gds_layer[0]
        datatype = 99 + channel

        for points in points_list:
            points_array = np.array(points)
            polygon = gdstk.Polygon(points_array, layer=layer, datatype=datatype)
            result_cell.add(polygon)

    return result_cell