From d8bafc728478e5cba9cf41eca01d66a38800eddd Mon Sep 17 00:00:00 2001 From: Alexey <AlexeyAB@users.noreply.github.com> Date: Fri, 28 Apr 2017 11:04:56 +0000 Subject: [PATCH] Update Readme.md --- README.md | 12 +++++++----- 1 files changed, 7 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 85ef0c3..85b25d5 100644 --- a/README.md +++ b/README.md @@ -187,12 +187,12 @@ ## How to train (to detect your custom objects): -1. Create file `yolo-obj.cfg` with the same content as in `yolo-voc.cfg` (or copy `yolo-voc.cfg` to `yolo-obj.cfg)` and: +1. Create file `yolo-obj.cfg` with the same content as in `yolo-voc.2.0.cfg` (or copy `yolo-voc.2.0.cfg` to `yolo-obj.cfg)` and: * change line batch to [`batch=64`](https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x64/yolo-voc.cfg#L3) * change line subdivisions to [`subdivisions=8`](https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x64/yolo-voc.cfg#L4) * change line `classes=20` to your number of objects - * change line #224 from [`filters=125`](https://github.com/AlexeyAB/darknet/blob/master/cfg/yolo-voc.cfg#L224) to `filters=(classes + 5)*5` (generally this depends on the `num` and `coords`, i.e. equal to `(classes + coords + 1)*num`) + * change line #237 from [`filters=125`](https://github.com/AlexeyAB/darknet/blob/master/cfg/yolo-voc.cfg#L237) to `filters=(classes + 5)*5` (generally this depends on the `num` and `coords`, i.e. equal to `(classes + coords + 1)*num`) For example, for 2 objects, your file `yolo-obj.cfg` should differ from `yolo-voc.cfg` in such lines: @@ -267,7 +267,7 @@ * **9002** - iteration number (number of batch) * **0.060730 avg** - average loss (error) - **the lower, the better** - When you see that average loss **0.060730 avg** enough low at many iterations and no longer decreases then you should stop training. + When you see that average loss **0.xxxxxx avg** no longer decreases at many iterations then you should stop training. 2. Once training is stopped, you should take some of last `.weights`-files from `darknet\build\darknet\x64\backup` and choose the best of them: @@ -275,7 +275,7 @@  - 2.1. At first, you should put filenames of validation images to file `data\voc.2007.test` (format as in `train.txt`) or if you haven't validation images - simply copy `data\train.txt` to `data\voc.2007.test`. + 2.1. At first, in your file `obj.data` you must specify the path to the validation dataset `valid = valid.txt` (format of `valid.txt` as in `train.txt`), and if you haven't validation images, just copy `data\train.txt` to `data\valid.txt`. 2.2 If training is stopped after 9000 iterations, to validate some of previous weights use this commands: @@ -288,7 +288,7 @@ > 7586 7612 7689 RPs/Img: 68.23 **IOU: 77.86%** Recall:99.00% * **IOU** - the bigger, the better (says about accuracy) - **better to use** -* **Recall** - the bigger, the better (says about accuracy) +* **Recall** - the bigger, the better (says about accuracy) - actually Yolo calculates true positives, so it shouldn't be used For example, **bigger IUO** gives weights `yolo-obj_8000.weights` - then **use this weights for detection**. @@ -306,6 +306,8 @@ 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/47409529d0eb935fa7bafbe2b3484431117269f5/cfg/yolo-voc.cfg#L244) + + * desirable that your training dataset include images with objects at diffrent: scales, rotations, lightings, from different sides 2. After training - for detection: -- Gitblit v1.10.0