The weight-sharing model will be repeatedly quantified

[AddSalt8227]

My model has two inputs, so I modify its quantization code as follows:

get_input_data_cv(imgs1_list[nums].c_str(), input1_data.data(), img1_c, img1_h, img1_w, mean, scale, sw_RGB, center_crop, letterbox_rows, letterbox_cols, focus);
get_input_data_cv(imgs2_list[nums].c_str(), input2_data.data(), img2_c, img2_h, img2_w, mean, scale, sw_RGB, center_crop, letterbox_rows, letterbox_cols, focus);

The weights are shared as follows：

output:

I think that the tensor224\225 is repeatedly quantized, we need check if(weight_tensor->data_type != TENGINE_DT_UINT8) then quantize it. After i do this, it works.