Merge remote-tracking branch 'upstream/3.4' into merge-3.4

Author: alalek

testdata/dnn/onnx/data/input_div_test_1x1_0.npy

@@ -92,6 +92,23 @@ def save_data_and_onnx_model(name, input_np, output_np, onnx_model):
     with open(models_files, 'wb') as file:
         file.write(model_def.SerializeToString())
 
+def save_data_and_onnx_model_multy_inputs(name, input_list, output_np, onnx_model):
+    for index in range(len(input_list)):
+        print(name + " input  "+str(index)+" has sizes",  input_list[index].shape)
+        input_files = os.path.join("data", "input_" + name + "_" + str(index))
+        np.save(input_files, input_list[index])
+
+    print(name + " output has sizes", output_np.shape)
+    print()
+    output_files =  os.path.join("data", "output_" + name)
+    np.save(output_files, np.ascontiguousarray(output_np.data))
+
+    models_files = os.path.join("models", name + ".onnx")
+
+    onnx_model_pb = onnx._serialize(onnx_model)
+    model_def = assertONNXExpected(onnx_model_pb)
+    with open(models_files, 'wb') as file:
+        file.write(model_def.SerializeToString())
 
 def simplify(name, rename=False, **kwargs):
     model, check = onnxsim.simplify(name, **kwargs)
@@ -2091,3 +2108,23 @@ def gemm_reference_implementation(A: np.ndarray, B: np.ndarray, C: Optional[np.n
 
 output_np = np.sum(input_np, axis=1, keepdims=1)
 save_data_and_onnx_model("reduce_sum_axis_dynamic_batch", input_np, output_np, onnx_model)
+
+
+# ########################## DivBroadcast ##########################
+input_np = np.random.rand(1, 4).astype("float32")
+input2_np = np.random.rand(1, 1).astype(np.float32)
+inputs = [onnx.helper.make_tensor_value_info("input1", onnx.mapping.NP_TYPE_TO_TENSOR_TYPE[input_np.dtype], shape=input_np.shape), \
+    onnx.helper.make_tensor_value_info("input2", onnx.mapping.NP_TYPE_TO_TENSOR_TYPE[input2_np.dtype], shape=input2_np.shape)]
+
+outputs = [onnx.helper.make_tensor_value_info("output", onnx.TensorProto.FLOAT, shape=(1, 4))]
+
+nodes = [onnx.helper.make_node("Div", ["input1", "input2"], ["output"])]
+
+graph = onnx.helper.make_graph(nodes,
+                            "div_test",
+                            inputs,
+                            outputs)
+onnx_model = onnx.helper.make_model(graph)
+
+output_np = input_np/input2_np
+save_data_and_onnx_model_multy_inputs("div_test_1x1", [input_np, input2_np], output_np, onnx_model)

testdata/dnn/onnx/data/input_div_test_1x1_1.npy

@@ -0,0 +1,16 @@
+:w
+
+input1
+input2output"Divdiv_testZ
+input1
+

+

+Z
+input2
+

+

+
b
+output
+

+

+B