search

josephjaspers / blackcat_tensors

Matrix-Vector Library Designed for Neural Network Construction. cuda (gpu) support, openmp (multithreaded cpu) support, partial support of BLAS, expression template based implementation PTX code generation identical to hand written kernels, and support for auto-differentiation
12 stars 4 forks source link

when i use the load net to forcast, the performance is so bad! #47

Open xinsuinizhuan opened 4 years ago

josephjaspers commented 4 years ago

Sorry for the late response, what is the model and layers of the neural-network you are using?

xinsuinizhuan commented 4 years ago

Sorry for the late response, what is the model and layers of the neural-network you are using?

this: auto make_lstm_network() { return BC::nn::neuralnetwork( BC::nn::lstm(BC::host_tag(), 96 * 10, 1024), BC::nn::lstm(BC::host_tag(), 1024, 512), BC::nn::lstm(BC::host_tag(), 512, 216), BC::nn::feedforward(BC::host_tag(), 216, 192), BC::nn::logistic(BC::host_tag(), 192), BC::nn::logging_output_layer(BC::host_tag(), 192, BC::nn::RMSE).skip_every(100) ); } using network_type = decltype(make_lstm_network());