Merge pull request #980 from WanliZhong:issue_22015

* Add a model for testing clip with min and max initializers

* Add models for testing clip with min or max initializers

Author: WanliZhong

testdata/dnn/onnx/data/input_clip_init_max.npy

@@ -593,6 +593,66 @@ def forward(self, x):
 input = Variable(torch.rand(1, 10, 2, 2))
 save_data_and_model('clip', input, model)
 
+########### clip_init ###########
+
+operation = "Clip"
+min = -0.5
+max = 0.5
+
+input = np.random.randn(3, 4, 5).astype(np.float32)
+output = np.clip(input, min, max)
+
+X = onnx.helper.make_tensor_value_info('input', onnx.TensorProto.FLOAT, [3, 4, 5])
+MIN = onnx.helper.make_tensor_value_info('min', onnx.TensorProto.FLOAT, [1])
+MAX = onnx.helper.make_tensor_value_info('max', onnx.TensorProto.FLOAT, [1])
+Y = onnx.helper.make_tensor_value_info('output', onnx.TensorProto.FLOAT, [3, 4, 5])
+MIN_INIT = onnx.helper.make_tensor("min", onnx.TensorProto.FLOAT, [1], np.array([min]))
+MAX_INIT = onnx.helper.make_tensor("max", onnx.TensorProto.FLOAT, [1], np.array([max]))
+
+name = "clip_init_min_max"
+input = np.random.randn(3, 4, 5).astype(np.float32)
+output = np.clip(input, min, max)
+
+input_files = os.path.join("data", "input_" + name)
+np.save(input_files, input.data)
+output_files = os.path.join("data", "output_" + name)
+np.save(output_files, np.ascontiguousarray(output.data))
+
+node = onnx.helper.make_node(operation, inputs=['input', "min", "max"], outputs=['output'])
+graph = onnx.helper.make_graph([node], name, [X, MIN, MAX], [Y], [MIN_INIT, MAX_INIT])
+model = onnx.helper.make_model(graph, producer_name=name)
+onnx.save(model, os.path.join("models", name + ".onnx"))
+
+name = "clip_init_min"
+input = np.random.randn(3, 4, 5).astype(np.float32)
+output = np.clip(input, min, None)
+
+input_files = os.path.join("data", "input_" + name)
+np.save(input_files, input.data)
+output_files = os.path.join("data", "output_" + name)
+np.save(output_files, np.ascontiguousarray(output.data))
+
+node = onnx.helper.make_node(operation, inputs=['input', "min", ""], outputs=['output'])
+graph = onnx.helper.make_graph([node], name, [X, MIN], [Y], [MIN_INIT])
+model = onnx.helper.make_model(graph, producer_name=name)
+onnx.save(model, os.path.join("models", name + ".onnx"))
+
+name = "clip_init_max"
+input = np.random.randn(3, 4, 5).astype(np.float32)
+output = np.clip(input, None, max)
+
+input_files = os.path.join("data", "input_" + name)
+np.save(input_files, input.data)
+output_files = os.path.join("data", "output_" + name)
+np.save(output_files, np.ascontiguousarray(output.data))
+
+node = onnx.helper.make_node(operation, inputs=['input', "", "max"], outputs=['output'])
+graph = onnx.helper.make_graph([node], name, [X, MAX], [Y], [MAX_INIT])
+model = onnx.helper.make_model(graph, producer_name=name)
+onnx.save(model, os.path.join("models", name + ".onnx"))
+
+#################################
+
 input = Variable(torch.randn(1, 3, 6, 6, 6))
 deconv = nn.ConvTranspose3d(3, 3, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(0, 0, 0), bias=False)
 save_data_and_model("deconv3d", input, deconv)
@@ -1444,14 +1504,14 @@ def forward(self, x):
 save_data_and_model("reduce_max", x, model)
 
 class ReduceMax(nn.Module):
-      def __init__(self, axes):
-    super(ReduceMax, self).__init__()
-    self.axes = axes
+    def __init__(self, axes):
+        super(ReduceMax, self).__init__()
+        self.axes = axes
 
-  def forward(self, x):
-    # torch.return_types.max(values, indices)
-    out = torch.max(x, dim=self.axes, keepdim=False)[0]
-    return out
+    def forward(self, x):
+        # torch.return_types.max(values, indices)
+        out = torch.max(x, dim=self.axes, keepdim=False)[0]
+        return out
 
 x = Variable(torch.randn(1, 3, 2, 2))