diff --git a/README.md b/README.md
index b5d5acf..6b27310 100755
--- a/README.md
+++ b/README.md
@@ -120,7 +120,7 @@ python global_recon/run_dataset.py --dataset 3dpw --cfg glamr_3dpw --out_dir out
 ```
 Next, evaluate the results generated by GLAMR:
 ```
-python eval/eval.py --dataset 3dpw --results_dir out/3dpw
+python global_recon/eval_dataset.py --dataset 3dpw --results_dir out/3dpw
 ```
 Similarly, to evaluate on Dynamic Human3.6M, you can replace the `3dpw` to `h36m` for the dataset and config.