[fbsync] Updated classification README to refer to torch.cuda.amp (#4570)

Reviewed By: NicolasHug

Differential Revision: D31505553

fbshipit-source-id: 2bd5dcfd0d0ab9cdb6454c004eb40a52d252fc28

Author: prabhat00155

references/classification/README.md

@@ -110,13 +110,13 @@ torchrun --nproc_per_node=8 train.py\
 Here `$MODEL` is one of `regnet_x_32gf`, `regnet_y_16gf` and `regnet_y_32gf`.
 
 ## Mixed precision training
-Automatic Mixed Precision (AMP) training on GPU for Pytorch can be enabled with the [NVIDIA Apex extension](https://github.com/NVIDIA/apex).
+Automatic Mixed Precision (AMP) training on GPU for Pytorch can be enabled with the [torch.cuda.amp](https://pytorch.org/docs/stable/amp.html?highlight=amp#module-torch.cuda.amp).
 
-Mixed precision training makes use of both FP32 and FP16 precisions where appropriate. FP16 operations can leverage the Tensor cores on NVIDIA GPUs (Volta, Turing or newer architectures) for improved throughput, generally without loss in model accuracy. Mixed precision training also often allows larger batch sizes. GPU automatic mixed precision training for Pytorch Vision can be enabled via the flag value `--apex=True`.
+Mixed precision training makes use of both FP32 and FP16 precisions where appropriate. FP16 operations can leverage the Tensor cores on NVIDIA GPUs (Volta, Turing or newer architectures) for improved throughput, generally without loss in model accuracy. Mixed precision training also often allows larger batch sizes. GPU automatic mixed precision training for Pytorch Vision can be enabled via the flag value `--amp=True`.
 
 ```
 torchrun --nproc_per_node=8 train.py\
-    --model resnext50_32x4d --epochs 100 --apex
+    --model resnext50_32x4d --epochs 100 --amp
 ```
 
 ## Quantized