commit 15f24f0fe5ca4b0743b8dc251e1cfeab4c9c72b9
author vfdev <vfdev.5@gmail.com> Mon Oct 04 18:45:24 2021 +0200
committer Jon Janzen <jonjanzen@fb.com> Thu Jul 21 13:41:06 2022 -0700
tree 055d96189c6f1c54a3ee60129ba5647d40c6bbbf
parent a0df7823fb3ed783a37fbb1ca099a1344c5c6b8c

[functorch] Update README.md (pytorch/functorch#176)

Readded missed `grad`

functorch/README.md

diff --git a/functorch/README.md b/functorch/README.md
index 62e3c33..874fbc4 100644
--- a/functorch/README.md
+++ b/functorch/README.md
@@ -264,7 +264,7 @@
     preds = func_model(params, data)
     return torch.mean((preds - targets) ** 2)
 
-per_sample_grads = vmap(compute_loss, (None, 0, 0))(params, data, targets)
+per_sample_grads = vmap(grad(compute_loss), (None, 0, 0))(params, data, targets)
 ```
 
 If you're making an ensemble of models, you may find