def main(model_uri, data_path):
print("Options:")
for k, v in locals().items():
print(f" {k}: {v}")
data = utils.get_prediction_data(data_path)
print("data.type:", type(data))
print("data.shape:", data.shape)
print("\n**** mlflow.keras.load_model\n")
model = mlflow.keras.load_model(model_uri)
print("model:", type(model))
print("\n== model.predict")
predictions = model.predict(data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
#print("predictions:", predictions)
utils.display_predictions(predictions)
print("\n== model.predict_classes")
predictions = model.predict_classes(data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
utils.display_predictions(predictions)
utils.predict_pyfunc(model_uri, data)
def main(model_uri):
model = mlflow.pyfunc.load_model(model_uri)
print("model:", model)
ndarray = utils.get_prediction_data()
data = pd.DataFrame(ndarray)
print("data.shape:", data.shape)
predictions = model.predict(data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
print("predictions:", predictions)
def main(model_uri, data_path):
print("Options:")
for k,v in locals().items(): print(f" {k}: {v}")
model = mlflow.pyfunc.load_model(model_uri)
print("model:", model)
ndarray = utils.get_prediction_data(data_path)
data = pd.DataFrame(ndarray)
print("data.shape:", data.shape)
predictions = model.predict(data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
print("predictions:", predictions)
def main(model_uri):
print("model_uri:", model_uri)
data = utils.get_prediction_data()
print("\n**** mlflow.onnx.load_model\n")
model = mlflow.onnx.load_model(model_uri)
print("model.type:", type(model))
predictions = onnx_utils.score_model(model, data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
print("predictions:", predictions)
utils.predict_pyfunc(model_uri, data)
print("\n**** mlflow.pyfunc.load_model\n")
model = mlflow.pyfunc.load_model(model_uri)
print("model.type:", type(model))
data = pd.DataFrame(data)
predictions = model.predict(data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
print("predictions:", predictions)
dest="rows",
help="Number of rows",
default=None,
type=int)
parser.add_argument("--base_name",
dest="base_name",
help="Base name",
default="mnist",
type=str)
parser.add_argument("--output_dir",
dest="output_dir",
help="Output directory",
default=".")
args = parser.parse_args()
print("Arguments:")
for arg in vars(args):
print(f" {arg}: {getattr(args, arg)}")
x_test = utils.get_prediction_data()
print("x_test.type:", type(x_test))
print("x_test.shape:", x_test.shape)
if args.rows:
x_test = x_test[:args.rows]
print("x_test.shape:", x_test.shape)
to_json_mlflow(
x_test, os.path.join(args.output_dir, f"{args.base_name}-mlflow.json"))
to_json_tensorflow_serving(
x_test,
os.path.join(args.output_dir, f"{args.base_name}-tf_serving.json"))