From b7ac446d62d275fa8f4377a4ba65988eb8e55a19 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Wed, 17 Jun 2020 12:56:47 -0700
Subject: [PATCH] update README.md

---
 README.md | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 7e39727..35fbee6 100755
--- a/README.md
+++ b/README.md
@@ -74,9 +74,12 @@ Results saved to /content/yolov5/inference/output
 
 ## Reproduce Our Training
 
-Run command below. Training times for yolov5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster).
+Download [COCO](https://github.com/ultralytics/yolov5/blob/master/data/get_coco2017.sh), install [Apex](https://github.com/NVIDIA/apex) and run command below. Training times for yolov5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster). Use the largest `--batch-size` your GPU allows (batch sizes shown for 16 GB devices).
 ```bash
-$ python train.py --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 16                                      
+$ python train.py --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 64
+                                         yolov5m                                48
+                                         yolov5l                                32
+                                         yolov5x                                16
 ```
 <img src="https://user-images.githubusercontent.com/26833433/84186698-c4d54d00-aa45-11ea-9bde-c632c1230ccd.png" width="900">