Major refactor, small fixes

sthalles · Jan 18, 2021 · ca4016f · ca4016f
1 parent d16b226
commit ca4016f
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -26,6 +26,8 @@ $ python run.py -data ./datasets --dataset-name stl10 --log-every-n-steps 100 --
 
 If you want to run it on CPU (for debugging purposes) use the ```--disable-cuda``` option.
 
+For 16-bit precision GPU training, make sure to install [!NVIDIA apex](https://github.com/NVIDIA/apex) and used the ```--fp16_precision``` flag.
+
 ## Feature Evaluation
 
 Feature evaluation is done using a linear model protocol.