From c83865bb61ffa3dbdfdceddfc7b46d93859d89d3 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Mon, 02 Apr 2018 11:13:10 +0000
Subject: [PATCH] Fixed partial.cmd for new tiny weights
---
README.md | 23 ++++++++++++++++-------
1 files changed, 16 insertions(+), 7 deletions(-)
diff --git a/README.md b/README.md
index d576a1e..e6b576a 100644
--- a/README.md
+++ b/README.md
@@ -17,9 +17,10 @@
-|  |  https://pjreddie.com/media/files/papers/YOLOv3.pdf |
+|  |  mAP (AP50) https://pjreddie.com/media/files/papers/YOLOv3.pdf |
|---|---|
+* 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
@@ -188,7 +189,7 @@
## How to train (Pascal VOC Data):
-1. Download pre-trained weights for the convolutional layers (76 MB): http://pjreddie.com/media/files/darknet53.conv.74 and put to the directory `build\darknet\x64`
+1. Download pre-trained weights for the convolutional layers (154 MB): http://pjreddie.com/media/files/darknet53.conv.74 and put to the directory `build\darknet\x64`
2. Download The Pascal VOC Data and unpack it to directory `build\darknet\x64\data\voc` will be created dir `build\darknet\x64\data\voc\VOCdevkit\`:
* http://pjreddie.com/media/files/VOCtrainval_11-May-2012.tar
@@ -219,11 +220,12 @@
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/yolo-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolo-voc_1000.weights -gpus 0,1,2,3`
+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`
https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ
## How to train (to detect your custom objects):
+Training Yolo v3
1. Create file `yolo-obj.cfg` with the same content as in `yolov3.cfg` (or copy `yolov3.cfg` to `yolo-obj.cfg)` and:
@@ -238,8 +240,10 @@
* https://github.com/AlexeyAB/darknet/blob/0039fd26786ab5f71d5af725fc18b3f521e7acfd/cfg/yolov3.cfg#L689
* https://github.com/AlexeyAB/darknet/blob/0039fd26786ab5f71d5af725fc18b3f521e7acfd/cfg/yolov3.cfg#L776
- So if `classes=1` then should be `filters=18`. If `classes=2` then write `filters=31`.
+ So if `classes=1` then should be `filters=18`. If `classes=2` then write `filters=21`.
+
**(Do not write in the cfg-file: filters=(classes + 5)x3)**
+
(Generally `filters` depends on the `classes`, `coords` and number of `mask`s, i.e. filters=`(classes + coords + 1)*<number of mask>`, where `mask` is indices of anchors. If `mask` is absence, then filters=`(classes + coords + 1)*num`)
So for example, for 2 objects, your file `yolo-obj.cfg` should differ from `yolov3.cfg` in such lines in each of **3** [yolo]-layers:
@@ -266,15 +270,17 @@
4. Put image-files (.jpg) of your objects in the directory `build\darknet\x64\data\obj\`
-5. Create `.txt`-file for each `.jpg`-image-file - in the same directory and with the same name, but with `.txt`-extension, and put to file: object number and object coordinates on this image, for each object in new line: `<object-class> <x> <y> <width> <height>`
+5. You should label each object on images from your dataset. Use this visual GUI-software for marking bounded boxes of objects and generating annotation files for Yolo v2 & v3: https://github.com/AlexeyAB/Yolo_mark
+
+It will create `.txt`-file for each `.jpg`-image-file - in the same directory and with the same name, but with `.txt`-extension, and put to file: object number and object coordinates on this image, for each object in new line: `<object-class> <x> <y> <width> <height>`
Where:
* `<object-class>` - integer number of object from `0` to `(classes-1)`
- * `<x> <y> <width> <height>` - float values relative to width and height of image, it can be equal from 0.0 to 1.0
+ * `<x> <y> <width> <height>` - float values relative to width and height of image, it can be equal from (0.0 to 1.0]
* for example: `<x> = <absolute_x> / <image_width>` or `<height> = <absolute_height> / <image_height>`
* atention: `<x> <y>` - are center of rectangle (are not top-left corner)
- For example for `img1.jpg` you should create `img1.txt` containing:
+ For example for `img1.jpg` you will be created `img1.txt` containing:
```
1 0.716797 0.395833 0.216406 0.147222
@@ -303,6 +309,8 @@
* Also you can get result earlier than all 45000 iterations.
+ **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 tiny-yolo (to detect your custom objects):
Do all the same steps as for the full yolo model as described above. With the exception of:
@@ -361,6 +369,7 @@
* **mAP** (mean average precision) - mean value of `average precisions` for each class, where `average precision` is average value of 11 points on PR-curve for each possible threshold (each probability of detection) for the same class (Precision-Recall in terms of PascalVOC, where Precision=TP/(TP+FP) and Recall=TP/(TP+FN) ), page-11: http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc09.pdf
+**mAP** is default metric of precision in the PascalVOC competition, **this is the same as AP50** metric in the MS COCO competition.
In terms of Wiki, indicators Precision and Recall have a slightly different meaning than in the PascalVOC competition, but **IoU always has the same meaning**.
--
Gitblit v1.10.0