From 3a33d00d22ef55247fe379b8e6c53850f43a32a8 Mon Sep 17 00:00:00 2001
From: Alexey <AlexeyAB@users.noreply.github.com>
Date: Tue, 19 Jun 2018 22:29:59 +0000
Subject: [PATCH] Update Readme.md
---
README.md | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md
index b40d531..d43d797 100644
--- a/README.md
+++ b/README.md
@@ -422,14 +422,14 @@
* desirable that your training dataset include images with objects at diffrent: scales, rotations, lightings, from different sides, on different backgrounds - you should preferably have 2000 images for each class or more
- * desirable that your training dataset include images with non-labeled objects that you do not want to detect - negative samples without bounded box (empty `.txt` files)
+ * desirable that your training dataset include images with non-labeled objects that you do not want to detect - negative samples without bounded box (empty `.txt` files) - use as many images of negative samples as there are images with objects
* 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
* for training for small objects - set `layers = -1, 11` instead of https://github.com/AlexeyAB/darknet/blob/6390a5a2ab61a0bdf6f1a9a6b4a739c16b36e0d7/cfg/yolov3.cfg#L720
and set `stride=4` instead of https://github.com/AlexeyAB/darknet/blob/6390a5a2ab61a0bdf6f1a9a6b4a739c16b36e0d7/cfg/yolov3.cfg#L717
- * General rule - your training dataset should include such a set of relative sizes of objects that you want to detect - differing by no more than 2 times:
+ * General rule - your training dataset should include such a set of relative sizes of objects that you want to detect:
* `train_network_width * train_obj_width / train_image_width ~= detection_network_width * detection_obj_width / detection_image_width`
* `train_network_height * train_obj_height / train_image_height ~= detection_network_height * detection_obj_height / detection_image_height`
--
Gitblit v1.10.0