From 5f38c0d8f524225e78e36d3eeba90e4c6d3a0421 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 28 Mar 2018 20:30:53 +0000
Subject: [PATCH] Minor
---
README.md | 16 +++++++++-------
1 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/README.md b/README.md
index 4e4cbb8..89d2a6b 100644
--- a/README.md
+++ b/README.md
@@ -92,8 +92,8 @@
* 186 MB Yolo9000 - image: `darknet.exe detector test cfg/combine9k.data yolo9000.cfg yolo9000.weights`
* 186 MB Yolo9000 - video: `darknet.exe detector demo cfg/combine9k.data yolo9000.cfg yolo9000.weights test.mp4`
* Remeber to put data/9k.tree and data/coco9k.map under the same folder of your app if you use the cpp api to build an app
-* To process a list of images `image_list.txt` and save results of detection to `result.txt` use:
- `darknet.exe detector test data/voc.data yolo-voc.cfg yolo-voc.weights < image_list.txt > result.txt`
+* To process a list of images `data/train.txt` and save results of detection to `result.txt` use:
+ `darknet.exe detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt`
You can comment this line so that each image does not require pressing the button ESC: https://github.com/AlexeyAB/darknet/blob/6ccb41808caf753feea58ca9df79d6367dedc434/src/detector.c#L509
##### For using network video-camera mjpeg-stream with any Android smartphone:
@@ -126,9 +126,9 @@
### How to compile on Windows:
-1. If you have **MSVS 2015, CUDA 9.1 and OpenCV 3.0** (with paths: `C:\opencv_3.0\opencv\build\include` & `C:\opencv_3.0\opencv\build\x64\vc14\lib`), then start MSVS, open `build\darknet\darknet.sln`, set **x64** and **Release**, and do the: Build -> Build darknet
+1. If you have **MSVS 2015, CUDA 9.1 and OpenCV 3.0** (with paths: `C:\opencv_3.0\opencv\build\include` & `C:\opencv_3.0\opencv\build\x64\vc14\lib`), then start MSVS, open `build\darknet\darknet.sln`, set **x64** and **Release**, and do the: Build -> Build darknet. **NOTE:** If installing OpenCV, use OpenCV 3.4.0 or earlier. This is a bug in OpenCV 3.4.1 in the C API (see [#500](https://github.com/AlexeyAB/darknet/issues/500)).
- 1.1. Find files `opencv_world320.dll` and `opencv_ffmpeg320_64.dll` in `C:\opencv_3.0\opencv\build\x64\vc14\bin` and put it near with `darknet.exe`
+ 1.1. Find files `opencv_world320.dll` and `opencv_ffmpeg320_64.dll` (or `opencv_world340.dll` and `opencv_ffmpeg340_64.dll`) in `C:\opencv_3.0\opencv\build\x64\vc14\bin` and put it near with `darknet.exe`
2. If you have other version of **CUDA (not 9.1)** then open `build\darknet\darknet.vcxproj` by using Notepad, find 2 places with "CUDA 9.1" and change it to your CUDA-version, then do step 1
@@ -143,6 +143,8 @@
5. If you want to build with CUDNN to speed up then:
* download and install **cuDNN 7.0 for CUDA 9.1**: https://developer.nvidia.com/cudnn
+
+ * Check that there are `bin` and `include` folders in the `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.1` if aren't, then copy them to this folder from the path where is CUDA installed
* add Windows system variable `cudnn` with path to CUDNN: https://hsto.org/files/a49/3dc/fc4/a493dcfc4bd34a1295fd15e0e2e01f26.jpg
@@ -370,13 +372,13 @@
1. Before training:
* set flag `random=1` in your `.cfg`-file - it will increase precision by training Yolo for different resolutions: [link]https://github.com/AlexeyAB/darknet/blob/master/cfg/yolo-voc.2.0.cfg#L244)
-
+
+ * increase network resolution in your `.cfg`-file (`height=608`, `width=608` or any value multiple of 32) - it will increase precision
+
* 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
* to speedup training (with decreasing detection accuracy) do Fine-Tuning instead of Transfer-Learning, set param `stopbackward=1` in one of the penultimate convolutional layers, for example here: https://github.com/AlexeyAB/darknet/blob/cad4d1618fee74471d335314cb77070fee951a42/cfg/yolo-voc.2.0.cfg#L202
--
Gitblit v1.10.0