I tried to run this model against a data set containing about 40k items. With current rate, it may take more than 200 days. Is there any support available for multi threading/multi processing, the goal is to reduce the time taken for each prediction.
I tried few basic things and CUDA ran out of memory in between. Any help is much appreciated.
I tried to run this model against a data set containing about 40k items. With current rate, it may take more than 200 days. Is there any support available for multi threading/multi processing, the goal is to reduce the time taken for each prediction.
I tried few basic things and CUDA ran out of memory in between. Any help is much appreciated.