Training a deep learning model on a GPU
The Graphical processing unit (GPU) is hardware used for rendering images using a lot of cores. Pascal is the latest GPU micro architecture released by NVIDIA. The presence of hundreds of cores in GPU helps enhance the computation. This section provides the recipe for running a deep learning model using GPU.
Getting ready
This section provides dependencies required to run GPU and CPU:
- The experiment performed in this recipe uses GPU hardware such as GTX 1070.
- Install
mxnet
for GPU. To installmxnet
for GPU for a specified machine, follow the installation instruction frommxnet.io
. Select the requirement as shown in the screenshot, and follow the instructions:
Steps to get installation instruction for MXNet
How to do it...
Here is how you train a deep learning model on a GPU:
- The Inception-BN-transferred learning recipe discussed in the previous section can be made to run on the GPU installed and the configured machine by changing the device settings as shown...