From 16862ea846c1ed49310cec4a22b0035fb66b6a3c Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Mon, 30 Mar 2020 21:21:45 -0700
Subject: [PATCH] update 'reproduce our results'

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 539373b5..7bbcbf86 100755
--- a/README.md
+++ b/README.md
@@ -177,9 +177,9 @@ Speed: 21.3/3.0/24.4 ms inference/NMS/total per 640x640 image at batch-size 16
 
 This command trains `yolov3-spp.cfg` from scratch to our mAP above. Training takes about one week on a 2080Ti.
 ```bash
-$ python3 train.py --weights '' --cfg yolov3-spp.cfg --epochs 273 --batch 16 --accum 4 --multi
+$ python3 train.py --weights '' --cfg yolov3-spp.cfg --epochs 300 --batch 16 --accum 4 --multi
 ```
-<img src="https://user-images.githubusercontent.com/26833433/74633793-4f9cdf80-5117-11ea-9cd4-be4860640831.png" width="900">
+<img src="https://user-images.githubusercontent.com/26833433/77986559-408b7e80-72cc-11ea-9c4f-5d7820840a98.png" width="900">
 
 # Reproduce Our Environment