how to use GPU train?

[xinsuinizhuan]

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2020 NVIDIA Corporation
Built on Wed_Jul_22_19:09:35_Pacific_Daylight_Time_2020
Cuda compilation tools, release 11.0, V11.0.221
Build cuda_11.0_bu.relgpu_drvr445TC445_37.28845127_0

VS2019 i set:
auto make_lstm_network() {
return bc::nn::neuralnetwork(
bc::nn::lstm(bc::device_tag(), 96 * 10, 1536, bc::nn::adam),
bc::nn::lstm(bc::device_tag(), 1536, 768, bc::nn::adam),
bc::nn::lstm(bc::device_tag(), 768, 384, bc::nn::adam),
bc::nn::feedforward(bc::device_tag(), 384, 192),
bc::nn::logistic(bc::device_tag(), 192),
bc::nn::logging_output_layer(bc::device_tag(), 192, bc::nn::RMSE).skip_every(100)
);
}
using network_type = decltype(make_lstm_network());
but many compile errors: