Python TensorProto.FLOAT属性代码示例

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def test_broadcast():
    """Test for broadcasting in onnx operators."""
    input1 = np.random.rand(1, 3, 4, 5).astype("float32")
    input2 = np.random.rand(1, 5).astype("float32")
    inputs = [helper.make_tensor_value_info("input1", TensorProto.FLOAT, shape=(1, 3, 4, 5)),
              helper.make_tensor_value_info("input2", TensorProto.FLOAT, shape=(1, 5))]

    outputs = [helper.make_tensor_value_info("output", TensorProto.FLOAT, shape=(1, 3, 4, 5))]

    nodes = [helper.make_node("Add", ["input1", "input2"], ["output"])]

    graph = helper.make_graph(nodes,
                              "bcast_test",
                              inputs,
                              outputs)

    bcast_model = helper.make_model(graph)
    
    bkd_rep = mxnet_backend.prepare(bcast_model)
    numpy_op = input1 + input2
    output = bkd_rep.run([input1, input2])
    npt.assert_almost_equal(output[0], numpy_op) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def test_greater():
    """Test for logical greater in onnx operators."""
    input1 = np.random.rand(1, 3, 4, 5).astype("float32")
    input2 = np.random.rand(1, 5).astype("float32")
    inputs = [helper.make_tensor_value_info("input1", TensorProto.FLOAT, shape=(1, 3, 4, 5)),
              helper.make_tensor_value_info("input2", TensorProto.FLOAT, shape=(1, 5))]

    outputs = [helper.make_tensor_value_info("output", TensorProto.FLOAT, shape=(1, 3, 4, 5))]

    nodes = [helper.make_node("Greater", ["input1", "input2"], ["output"])]

    graph = helper.make_graph(nodes,
                              "greater_test",
                              inputs,
                              outputs)

    greater_model = helper.make_model(graph)
    
    bkd_rep = mxnet_backend.prepare(greater_model)
    numpy_op = np.greater(input1, input2).astype(np.float32)
    output = bkd_rep.run([input1, input2])
    npt.assert_almost_equal(output[0], numpy_op) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def test_lesser():
    """Test for logical greater in onnx operators."""
    input1 = np.random.rand(1, 3, 4, 5).astype("float32")
    input2 = np.random.rand(1, 5).astype("float32")
    inputs = [helper.make_tensor_value_info("input1", TensorProto.FLOAT, shape=(1, 3, 4, 5)),
              helper.make_tensor_value_info("input2", TensorProto.FLOAT, shape=(1, 5))]

    outputs = [helper.make_tensor_value_info("output", TensorProto.FLOAT, shape=(1, 3, 4, 5))]

    nodes = [helper.make_node("Less", ["input1", "input2"], ["output"])]

    graph = helper.make_graph(nodes,
                              "lesser_test",
                              inputs,
                              outputs)

    greater_model = helper.make_model(graph)
    
    bkd_rep = mxnet_backend.prepare(greater_model)
    numpy_op = np.less(input1, input2).astype(np.float32)
    output = bkd_rep.run([input1, input2])
    npt.assert_almost_equal(output[0], numpy_op) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def test_equal():
    """Test for logical greater in onnx operators."""
    input1 = np.random.rand(1, 3, 4, 5).astype("float32")
    input2 = np.random.rand(1, 5).astype("float32")
    inputs = [helper.make_tensor_value_info("input1", TensorProto.FLOAT, shape=(1, 3, 4, 5)),
              helper.make_tensor_value_info("input2", TensorProto.FLOAT, shape=(1, 5))]

    outputs = [helper.make_tensor_value_info("output", TensorProto.FLOAT, shape=(1, 3, 4, 5))]

    nodes = [helper.make_node("Equal", ["input1", "input2"], ["output"])]

    graph = helper.make_graph(nodes,
                              "equal_test",
                              inputs,
                              outputs)

    greater_model = helper.make_model(graph)
    
    bkd_rep = mxnet_backend.prepare(greater_model)
    numpy_op = np.equal(input1, input2).astype(np.float32)
    output = bkd_rep.run([input1, input2])
    npt.assert_almost_equal(output[0], numpy_op) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def _create_param_tensors(self, conv_params, param_category, suffix):
        """Creates the initializers with weights from the weights file together with
        the input tensors.

        Keyword arguments:
        conv_params -- a ConvParams object
        param_category -- the category of parameters to be created ('bn' or 'conv')
        suffix -- a string determining the sub-type of above param_category (e.g.,
        'weights' or 'bias')
        """
        param_name, param_data, param_data_shape = self._load_one_param_type(
            conv_params, param_category, suffix)

        initializer_tensor = helper.make_tensor(
            param_name, TensorProto.FLOAT, param_data_shape, param_data)
        input_tensor = helper.make_tensor_value_info(
            param_name, TensorProto.FLOAT, param_data_shape)
        return initializer_tensor, input_tensor 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def _make_input_tensor(self, layer_name, layer_dict):
        """Create an ONNX input tensor from a 'net' layer and store the batch size.

        Keyword arguments:
        layer_name -- the layer's name (also the corresponding key in layer_configs)
        layer_dict -- a layer parameter dictionary (one element of layer_configs)
        """
        batch_size = layer_dict['batch']
        channels = layer_dict['channels']
        height = layer_dict['height']
        width = layer_dict['width']
        self.batch_size = batch_size
        input_tensor = helper.make_tensor_value_info(
            str(layer_name), TensorProto.FLOAT, [
                batch_size, channels, height, width])
        self.input_tensor = input_tensor
        return layer_name, channels 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def load_resize_scales(self, resize_params):
        """Returns the initializers with the value of the scale input
        tensor given by resize_params.

        Keyword argument:
        resize_params -- a ResizeParams object
        """
        initializer = list()
        inputs = list()
        name = resize_params.generate_param_name()
        shape = resize_params.value.shape
        data = resize_params.value
        scale_init = helper.make_tensor(
            name, TensorProto.FLOAT, shape, data)
        scale_input = helper.make_tensor_value_info(
            name, TensorProto.FLOAT, shape)
        initializer.append(scale_init)
        inputs.append(scale_input)
        return initializer, inputs 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def __init__(self, ch):
        super(Link_Linear, self).__init__(lambda x, n_batch_axes=1: x)

        if ch.b is None:
            self.n_out = 'output_size'
            self.nobias = True
        else:
            self.n_out = ch.b.shape[0]
            self.nobias = False

        if not(ch.W.data is None):
            self.n_in = ch.W.shape[1]
        else:
            self.n_in = None

        self.W = helper.make_tensor_value_info(
            '/W', TensorProto.FLOAT,
            [self.n_out, ('input_size' if (self.n_in is None) else self.n_in)])

        if not self.nobias:
            self.b = helper.make_tensor_value_info(
                '/b', TensorProto.FLOAT, [self.n_out]) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def generate_graph(self, name: 'str', isMain=False):

        input_tensor_and_initializer = self.input_tensor.copy()

        # TODO(take-cheeze): Remove this workaround
        for i in input_tensor_and_initializer:
            t = i.type.tensor_type
            if t is not None and t.elem_type is TensorProto.UNDEFINED:
                t.elem_type = TensorProto.FLOAT

        initializers = []

        # add initializers
        if isMain:
            for v in self.generator.initializers.values():
                initializers.append(v.tensor)

                if v.tensor_value in self.input_tensor:
                    continue

                input_tensor_and_initializer.append(v.tensor_value)

        return oh.make_graph(self.nodes, name, input_tensor_and_initializer, self.output_tensor, initializer=initializers) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def __call__(self, graph):  # type: (Graph) -> Graph
        input_names = [str(input_[0]) for input_ in graph.inputs]
        output_names = [str(output_[0]) for output_ in graph.outputs]
        for node in graph.nodes:
            if str(node.op_type) == 'LSTM':
                input_h = node.inputs[5] if len(node.inputs) > 5 else node.inputs[0] + '_h_input'
                input_c = node.inputs[6] if len(node.inputs) > 6 else node.inputs[0] + '_c_input'
                output_h = node.outputs[1] if len(node.outputs) > 1 else node.outputs[0] + '_h_output'
                output_c = node.outputs[2] if len(node.outputs) > 2 else node.outputs[0] + '_c_output'
                h = node.attrs["hidden_size"]
                for input_ in [str(input_h), str(input_c)]:
                    if input_ not in input_names:
                        graph.inputs.append(tuple((input_, TensorProto.FLOAT, (h,))))  #type: ignore
                    if input_ not in graph.blob_to_op_type:
                        graph.blob_to_op_type[input_] = ['LSTM']
                for output_ in [str(output_h), str(output_c)]:
                    if output_ not in output_names:
                        graph.outputs.append(tuple((output_, TensorProto.FLOAT, (h,))))  #type: ignore
                    graph.blob_from_op_type[output_] = 'LSTM'
        return graph 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def _onnx_create_single_node_model(op_type,  # type: Text
                                   input_shapes,  # type: Sequence[Tuple[int, ...]]
                                   output_shapes,  # type: Sequence[Tuple[int, ...]]
                                   initializer=[],  # type: Sequence[TensorProto]
                                   **kwargs  # type: Any
                                   ):
    # type: (...) -> ModelProto
    inputs = [
        ("input{}".format(i,), input_shapes[i])
        for i in range(len(input_shapes))
    ]
    outputs = [
        ("output{}".format(i,), output_shapes[i], TensorProto.FLOAT)
        for i in range(len(output_shapes))
    ]

    node = helper.make_node(
        op_type,
        inputs=[i[0] for i in inputs] + [t.name for t in initializer],
        outputs=[o[0] for o in outputs],
        **kwargs
    )
    return _onnx_create_model([node], inputs, outputs, initializer) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def _make_model_acos_exp_topk(): # type: (...) -> ModelProto
  '''
  make a very simple model for testing: input->clip->exp->topk->2 outputs
  '''
  inputs = [('input0', (10,), TensorProto.FLOAT), ('K', (1,), TensorProto.INT64)]
  outputs = [('output_values', (3,), TensorProto.FLOAT), ('output_indices', (3,), TensorProto.INT64)]
  acos = helper.make_node("Acos",
                          inputs=[inputs[0][0]],
                          outputs=['acos_out'])
  exp = helper.make_node("Exp",
                        inputs=[acos.output[0]],
                        outputs=['exp_out'])
  topk = helper.make_node("TopK",
                        inputs=[exp.output[0], inputs[1][0]],
                        outputs=[outputs[0][0], outputs[1][0]],
                        axis=0)
  return _onnx_create_model([acos, exp, topk], inputs, outputs) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def test_relu_node_inplace(self):
    X = np.random.randn(3, 2).astype(np.float32)
    Y_ref = np.clip(X, 0, np.inf)

    node_def = helper.make_node("Relu", ["X"], ["X1"])

    graph_def = helper.make_graph(
        [node_def],
        name="test",
        inputs=[helper.make_tensor_value_info("X", TensorProto.FLOAT, [3, 2])],
        outputs=[
            helper.make_tensor_value_info("X1", TensorProto.FLOAT, [3, 2])
        ])
    tf_rep = prepare(helper.make_model(graph_def))
    output = tf_rep.run({"X": X})
    np.testing.assert_almost_equal(output.X1, Y_ref) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def test_eye_like(self):
    if legacy_opset_pre_ver(9):
      raise unittest.SkipTest("ONNX version {} doesn't support EyeLike.".format(
          defs.onnx_opset_version()))
    shape = [6, 10]
    off_diagonal_offset = -3
    x = self._get_rnd_int(0, 100, shape=shape)
    y = np.eye(shape[0], shape[1], k=off_diagonal_offset, dtype=np.float32)
    node_def = helper.make_node("EyeLike", ["x"], ["y"],
                                dtype=TensorProto.FLOAT,
                                k=off_diagonal_offset)
    graph_def = helper.make_graph(
        [node_def],
        name="test_unknown_shape",
        inputs=[
            helper.make_tensor_value_info("x", TensorProto.INT32, [None, None])
        ],
        outputs=[
            helper.make_tensor_value_info("y", TensorProto.FLOAT, [None, None])
        ])
    tf_rep = onnx_graph_to_tensorflow_rep(graph_def)
    output = tf_rep.run({"x": x})
    np.testing.assert_equal(output["y"], y) 

# 需要导入模块: from onnx import TensorProto [as 别名]
# 或者: from onnx.TensorProto import FLOAT [as 别名]
def test_flatten(self):
    shape = [2, 3, 4]
    x = self._get_rnd_float32(shape=shape)
    axis = 1
    node_def = helper.make_node("Flatten", ["X"], ["Y"], axis=axis)
    graph_def = helper.make_graph(
        [node_def],
        name="test_unknown_shape",
        inputs=[
            helper.make_tensor_value_info("X", TensorProto.FLOAT,
                                          [None, None, None])
        ],
        outputs=[helper.make_tensor_value_info("Y", TensorProto.FLOAT, [None])])
    tf_rep = onnx_graph_to_tensorflow_rep(graph_def)
    output = tf_rep.run({"X": x})
    new_shape = (np.prod(shape[0:axis]).astype(int), -1)
    np.testing.assert_almost_equal(output["Y"], np.reshape(x, new_shape))