Update README.md

exorevan · Apr 25, 2022 · b364910 · b364910
1 parent 4c31e16
commit b364910
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -75,6 +75,8 @@ For faster convergence and better results, a large batch size (more than 16) is
 
 ***We recommend training more than 400K iterations (batch size is 16), 600K~800K will be better, more iterations will not be recommended.***
 
+VGGFace2 is not a toy dataset like Cifar or Minist that takes a lot of time to learn.
+
 ```
 python train.py --name simswap224_test --batchSize 8  --gpu_ids 0 --dataset /path/to/VGGFace2HQ --Gdeep False
 ```