From f39160f6e8f4465e9325e235e18f0d9413d1f672 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Sun, 04 Mar 2018 00:09:40 +0000
Subject: [PATCH] Added: calc_anchors

---
 README.md |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/README.md b/README.md
index 2f75fb3..7e3fd65 100644
--- a/README.md
+++ b/README.md
@@ -372,6 +372,8 @@
   
   * desirable that your training dataset include images with objects at diffrent: scales, rotations, lightings, from different sides
 
+  * desirable that your training dataset include images with objects (without labels) that you do not want to detect - negative samples
+
   * for training on small objects, add the parameter `small_object=1` in the last layer [region] in your cfg-file
 
   * for training with a large number of objects in each image, add the parameter `max=200` or higher value in the last layer [region] in your cfg-file

--
Gitblit v1.10.0