From 2ce6460c79e06caa33eab3991ee3e7fd9f0909d6 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Tue, 10 Apr 2018 18:08:24 +0000
Subject: [PATCH] Remove truth only if smaller than 1x1 pix during training

---
 README.md |    8 +++++---
 1 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 346a4ef..78ba765 100644
--- a/README.md
+++ b/README.md
@@ -167,7 +167,7 @@
 
 `C:\opencv_3.0\opencv\build\include;..\..\3rdparty\include;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir);$(cudnn)\include`
 - (right click on project) -> Build dependecies -> Build Customizations -> set check on CUDA 9.1 or what version you have - for example as here: http://devblogs.nvidia.com/parallelforall/wp-content/uploads/2015/01/VS2013-R-5.jpg
-- add to project all .c & .cu files from `\src`
+- add to project all `.c` & `.cu` files and file `http_stream.cpp` from `\src`
 - (right click on project) -> properties  -> Linker -> General -> Additional Library Directories, put here: 
 
 `C:\opencv_3.0\opencv\build\x64\vc14\lib;$(CUDA_PATH)lib\$(PlatformName);$(cudnn)\lib\x64;%(AdditionalLibraryDirectories)`
@@ -216,6 +216,8 @@
 
 More information about training by the link: http://pjreddie.com/darknet/yolo/#train-voc
 
+ **Note:** If during training you see `nan` values in some lines then training goes well, but if `nan` are in all lines then training goes wrong.
+
 ## How to train with multi-GPU:
 
 1. Train it first on 1 GPU for like 1000 iterations: `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg darknet53.conv.74`
@@ -407,9 +409,9 @@
   `darknet.exe detector calc_anchors data/obj.data -num_of_clusters 9 -width 416 -heigh 416`
    then set the same 9 `anchors` in each of 3 `[yolo]`-layers in your cfg-file
 
-  * 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 at diffrent: scales, rotations, lightings, from different sides, on different backgrounds
 
-  * desirable that your training dataset include images with objects (without labels) that you do not want to detect - negative samples
+  * desirable that your training dataset include images with non-labeled objects that you do not want to detect - negative samples without bounded box
 
   * 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