ONNX tutorial with TensorFlow

Install necessary libraries

    !pip install -U tensorflow tf2onnx onnx==1.14.1 scikit-learn

PyTorch - Standard Model Training

The following blocks of code define a standard tensorflow training code. This is completely independent of TurboML.

    import pandas as pd
    import tf2onnx.convert
    import matplotlib.pyplot as plt
    import tensorflow as tf
    from tensorflow.keras.models import Sequential
    from tensorflow.keras.layers import Dense

    transactions = pd.read_csv("data/transactions.csv").reset_index()
    labels = pd.read_csv("data/labels.csv").reset_index()

    joined_df = pd.merge(transactions, labels, on="index", how="right")
    joined_df

    X = joined_df.drop("is_fraud", axis=1)
    numerical_fields = [
        "transactionAmount",
        "localHour",
        "isProxyIP",
        "digitalItemCount",
        "physicalItemCount",
    ]
    
    feats = X[numerical_fields]
    targets = joined_df["is_fraud"].astype(int)

    from sklearn.model_selection import train_test_split
    
    X_train, X_test, y_train, y_test = train_test_split(
        feats, targets, test_size=0.2, random_state=42
    )

    model = Sequential()
    model.add(Dense(64, activation="relu", input_shape=(X_train.shape[1],)))
    model.add(Dense(64, activation="relu"))
    model.add(Dense(2, activation="softmax"))

    model.summary()

    model.compile(
        optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
    )
    
    num_epochs = 10
    model.fit(X_train, y_train, epochs=num_epochs, batch_size=64, verbose=1)

    _, accuracy = model.evaluate(X_test, y_test)
    print("Accuracy:", accuracy)

Export model to ONNX format

Exporting a model to ONNX format depends on the framework. Tutorials for different frameworks can be found at https://github.com/onnx/tutorials#converting-to-onnx-format (opens in a new tab)

    onnx_model_path = "tensorflow_model.onnx"
    input_signature = [
        tf.TensorSpec([1, len(numerical_fields)], tf.float32, name="keras_tensor")
    ]
    model.output_names = ["output"]
    onnx_model, _ = tf2onnx.convert.from_keras(model, input_signature, opset=13)
    
    onnx_model_bytes = onnx_model.SerializeToString()

Create an ONNX model with TurboML

Now that we've converted the model to ONNX format, we can deploy it with TurboML.

    import turboml as tb

    transactions = tb.PandasDataset(
        dataset_name="transactions_onxx_tf",
        key_field="index",
        dataframe=transactions,
        upload=True,
    )
    labels = tb.PandasDataset(
        dataset_name="labels", key_field="index", dataframe=labels, upload=True
    )
    features = transactions.get_input_fields(numerical_fields=numerical_fields)
    label = labels.get_label_field(label_field="is_fraud")

    tb.set_onnx_model("tensorflowmodel", onnx_model_bytes)
    onnx_model = tb.ONNX(model_save_name="tensorflowmodel")

    deployed_model = onnx_model.deploy("onnx_model_tf", input=features, labels=label)

    deployed_model.add_metric("WindowedAUC")

    model_auc_scores = deployed_model.get_evaluation("WindowedAUC")
    plt.plot([model_auc_score.metric for model_auc_score in model_auc_scores])

ONNX - Scikit-Learn TF-IDF Example