Join GitHub today
GitHub is home to over 28 million developers working together to host and review code, manage projects, and build software together.Sign up
Add device mode for Predictor interface? #724
One of the best things about Caffe was that it was extremely easy to load a pre-trained model in Python, set CPU/GPU and get output for an image.
It seems like the Predictor interface, which is meant for such ease-of-use, does not have any way to set GPU. It always runs the network in CPU mode. This is a big pain point as seen in #323 and #503 .
Could a simple device mode be added for Predictor for folks who just want to load a model on a device and run?