From dbdd31ee211fe8b1ac7e93ceadf7b34b8d304f34 Mon Sep 17 00:00:00 2001
From: Roland Singer <roland.singer@desertbit.com>
Date: Wed, 22 Aug 2018 11:56:41 +0000
Subject: [PATCH] updated README to include information about learning rate adjustment for multiple GPUs
---
README.md | 14 +++++++++++---
1 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/README.md b/README.md
index b02da01..18d3f15 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,5 @@
# Yolo-v3 and Yolo-v2 for Windows and Linux
-### (neural network for object detection)
+### (neural network for object detection) - Tensor Cores can be used on [Linux](https://github.com/AlexeyAB/darknet#how-to-compile-on-linux) and [Windows](https://github.com/AlexeyAB/darknet#how-to-compile-on-windows)
[](https://circleci.com/gh/AlexeyAB/darknet)
@@ -20,6 +20,7 @@
|  |  mAP (AP50) https://pjreddie.com/media/files/papers/YOLOv3.pdf |
|---|---|
+* YOLOv3-spp (is not indicated) better than YOLOv3 - mAP = 60.6%, FPS = 20: https://pjreddie.com/darknet/yolo/
* Yolo v3 source chart for the RetinaNet on MS COCO got from Table 1 (e): https://arxiv.org/pdf/1708.02002.pdf
* Yolo v2 on Pascal VOC 2007: https://hsto.org/files/a24/21e/068/a2421e0689fb43f08584de9d44c2215f.jpg
* Yolo v2 on Pascal VOC 2012 (comp4): https://hsto.org/files/3a6/fdf/b53/3a6fdfb533f34cee9b52bdd9bb0b19d9.jpg
@@ -49,6 +50,7 @@
* **GPU with CC >= 3.0**: https://en.wikipedia.org/wiki/CUDA#GPUs_supported
##### Pre-trained models for different cfg-files can be downloaded from (smaller -> faster & lower quality):
+* `yolov3-spp.cfg` (240 MB COCO **Yolo v3**) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov3-spp.weights
* `yolov3.cfg` (236 MB COCO **Yolo v3**) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov3.weights
* `yolov3-tiny.cfg` (34 MB COCO **Yolo v3 tiny**) - requires 1 GB GPU-RAM: https://pjreddie.com/media/files/yolov3-tiny.weights
* `yolov2.cfg` (194 MB COCO Yolo v2) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov2.weights
@@ -225,7 +227,9 @@
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`
-2. Then stop and by using partially-trained model `/backup/yolov3-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolov3-voc_1000.weights -gpus 0,1,2,3`
+2. Adjust the learning rate (`cfg/yolov3-voc.cfg`) to fit the amount of GPUs. The learning rate should be equal to `0.001`, regardless of how many GPUs are used for training. So `learning_rate * GPUs = 0.001`. For 4 GPUs adjust the value to `learning_rate = 0.00025`.
+
+3. Then stop and by using partially-trained model `/backup/yolov3-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolov3-voc_1000.weights -gpus 0,1,2,3`
https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ
@@ -428,11 +432,13 @@
* 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 with a large number of objects in each image, add the parameter `max=200` or higher value in the last `[yolo]`-layer or `[region]`-layer in your cfg-file (the global maximum number of objects that can be detected by YoloV3 is `0,0615234375*(width*height)` where are width and height are parameters from `[net]` section in 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
+ * If you train the model to distinguish Left and Right objects as separate classes (left/right hand, left/right-turn on road signs, ...) then for disabling flip data augmentation - add `flip=0` here: https://github.com/AlexeyAB/darknet/blob/3d2d0a7c98dbc8923d9ff705b81ff4f7940ea6ff/cfg/yolov3.cfg#L17
+
* 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`
@@ -484,6 +490,8 @@
2. To use Yolo as DLL-file in your C++ console application - open in MSVS2015 file `build\darknet\yolo_console_dll.sln`, set **x64** and **Release**, and do the: Build -> Build yolo_console_dll
* you can run your console application from Windows Explorer `build\darknet\x64\yolo_console_dll.exe`
+ **use this command**: `yolo_console_dll.exe data/coco.names yolov3.cfg yolov3.weights test.mp4`
+
* or you can run from MSVS2015 (before this - you should copy 2 files `yolo-voc.cfg` and `yolo-voc.weights` to the directory `build\darknet\` )
* after launching your console application and entering the image file name - you will see info for each object:
`<obj_id> <left_x> <top_y> <width> <height> <probability>`
--
Gitblit v1.10.0