August 2019
Intermediate to advanced
242 pages
5h 45m
English
We can do the same for the GPU build of the executable. This allows us to compare how long an epoch takes to train through the model. As our model is not complex, we don't expect to see that much of a difference:
2018/07/21 23:54:31 Using CUDA build2018/07/21 23:54:32 Batches 6002018/07/21 23:54:56 Epoch 0 | cost -0.69148070963577072018/07/21 23:55:19 Epoch 1 | cost -0.69174708713560432018/07/21 23:55:42 Epoch 2 | cost -0.69183437392579662018/07/21 23:56:05 Epoch 3 | cost -0.69187772920806052018/07/21 23:56:29 Epoch 4 | cost -0.69190364643621682018/07/21 23:56:52 Epoch 5 | cost -0.691920883357462018/07/21 23:57:15 Epoch 6 | cost -0.69193317497497632018/07/21 23:57:39 Epoch 7 | cost -0.6919423825458852018/07/21 23:58:02 Epoch 8 ...
Read now
Unlock full access