Build engine error when use pointnet-like structure and TensorRT 8.0.1.6

AI & Data Science Deep Learning (Training & Inference) TensorRT
6

the model is declared in that script:

def pointwise_fusion_bug(network, weights):
    # Configure the network layers based on the weights provided.
    input_tensor = network.add_input(name=ModelData.INPUT_NAME, dtype=ModelData.DTYPE, shape=ModelData.INPUT_SHAPE)
    conv1_w = trt.Weights(weights['conv1.weight'])
    conv1_b = trt.Weights()
    conv1 = network.add_convolution(input=input_tensor, num_output_maps=32, kernel_shape=(1, 1), kernel=conv1_w, bias=conv1_b)
    conv2 = network.add_convolution(input=input_tensor, num_output_maps=32, kernel_shape=(1, 1), kernel=conv1_w, bias=conv1_b)
    add1 = network.add_elementwise(conv1.get_output(0), conv2.get_output(0), trt.ElementWiseOperation.SUM)
    network.mark_output(tensor=add1.get_output(0))

what are you talking about???