def test_custom_pipeline_scaler(self):
digits = datasets.load_digits(n_class=6)
Xd = digits.data[:20]
yd = digits.target[:20]
n_samples, n_features = Xd.shape
ptsne_knn = PredictableTSNE()
ptsne_knn.fit(Xd, yd)
update_registered_converter(
PredictableTSNE,
"CustomPredictableTSNE",
predictable_tsne_shape_calculator,
predictable_tsne_converter,
)
model_onnx = convert_sklearn(
ptsne_knn,
"predictable_tsne",
[("input", FloatTensorType([None, Xd.shape[1]]))],
target_opset=TARGET_OPSET)
dump_data_and_model(Xd.astype(numpy.float32)[:7],
ptsne_knn,
model_onnx,
basename="CustomTransformerTSNEkNN-OneOffArray")
trace_line = []
def my_parser(scope, model, inputs, custom_parsers=None):
trace_line.append(model)
return _parse_sklearn_simple_model(scope, model, inputs,
custom_parsers)
model_onnx = convert_sklearn(
ptsne_knn,
"predictable_tsne",
[("input", FloatTensorType([None, Xd.shape[1]]))],
custom_parsers={PredictableTSNE: my_parser},
target_opset=TARGET_OPSET)
assert len(trace_line) == 1
dump_data_and_model(
Xd.astype(numpy.float32)[:7],
ptsne_knn,
model_onnx,
basename="CustomTransformerTSNEkNNCustomParser-OneOffArray")
update_registered_parser(PredictableTSNE, my_parser)
model_onnx = convert_sklearn(
ptsne_knn,
"predictable_tsne",
[("input", FloatTensorType([None, Xd.shape[1]]))],
target_opset=TARGET_OPSET)
assert len(trace_line) == 2
def test_custom_pipeline_scaler(self):
digits = datasets.load_digits(n_class=6)
Xd = digits.data[:20]
yd = digits.target[:20]
n_samples, n_features = Xd.shape
ptsne_knn = PredictableTSNE()
ptsne_knn.fit(Xd, yd)
update_registered_converter(PredictableTSNE, 'CustomPredictableTSNE',
predictable_tsne_shape_calculator,
predictable_tsne_converter)
model_onnx = convert_sklearn(
ptsne_knn, 'predictable_tsne',
[('input', FloatTensorType([1, Xd.shape[1]]))])
dump_data_and_model(Xd.astype(numpy.float32)[:7],
ptsne_knn,
model_onnx,
basename="CustomTransformerTSNEkNN-OneOffArray",
allow_failure="StrictVersion(onnx.__version__) "
"== StrictVersion('1.4.1')")
trace_line = []
def my_parser(scope, model, inputs, custom_parsers=None):
trace_line.append(model)
return _parse_sklearn_simple_model(scope, model, inputs,
custom_parsers)
model_onnx = convert_sklearn(
ptsne_knn,
'predictable_tsne', [('input', FloatTensorType([1, Xd.shape[1]]))],
custom_parsers={PredictableTSNE: my_parser})
assert len(trace_line) == 1
dump_data_and_model(
Xd.astype(numpy.float32)[:7],
ptsne_knn,
model_onnx,
basename="CustomTransformerTSNEkNNCustomParser-OneOffArray",
allow_failure="StrictVersion(onnx.__version__) "
"== StrictVersion('1.4.1')")
update_registered_parser(PredictableTSNE, my_parser)
model_onnx = convert_sklearn(
ptsne_knn, 'predictable_tsne',
[('input', FloatTensorType([1, Xd.shape[1]]))])
assert len(trace_line) == 2