From c8ad33ceba05cbb60c5197e4db4d3bdef28edd6d Mon Sep 17 00:00:00 2001
From: Alexey <AlexeyAB@users.noreply.github.com>
Date: Mon, 04 Jun 2018 12:57:13 +0000
Subject: [PATCH] Update Readme.md
---
README.md | 26 ++++++++++++++++++--------
1 files changed, 18 insertions(+), 8 deletions(-)
diff --git a/README.md b/README.md
index 0dc6230..7cf0b77 100644
--- a/README.md
+++ b/README.md
@@ -99,7 +99,7 @@
* 186 MB Yolo9000 - image: `darknet.exe detector test cfg/combine9k.data yolo9000.cfg yolo9000.weights`
* 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 `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`
+ `darknet.exe detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show -ext_output < 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:
@@ -218,7 +218,7 @@
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.
+ **Note:** If during training you see `nan` values for `avg` (loss) field - then training goes wrong, but if `nan` is in some other lines - then training goes well.
## How to train with multi-GPU:
@@ -317,15 +317,15 @@
* 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.
+ **Note:** If during training you see `nan` values for `avg` (loss) field - then training goes wrong, but if `nan` is in some other lines - then training goes well.
### 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:
-* Download default weights file for yolov2-tiny-voc: http://pjreddie.com/media/files/yolov2-tiny-voc.weights
-* Get pre-trained weights yolov2-tiny-voc.conv.13 using command: `darknet.exe partial cfg/yolov2-tiny-voc.cfg yolov2-tiny-voc.weights yolov2-tiny-voc.conv.13 13`
-* Make your custom model `yolov2-tiny-obj.cfg` based on `cfg/yolov2-tiny-voc.cfg` instead of `yolov3.cfg`
-* Start training: `darknet.exe detector train data/obj.data yolov2-tiny-obj.cfg yolov2-tiny-voc.conv.13`
+* Download default weights file for yolov3-tiny: https://pjreddie.com/media/files/yolov3-tiny.weights
+* Get pre-trained weights `yolov3-tiny.conv.15` using command: `darknet.exe partial cfg/yolov3-tiny.cfg yolov3-tiny.weights yolov3-tiny.conv.15 15`
+* Make your custom model `yolov3-tiny-obj.cfg` based on `cfg/yolov3-tiny_obj.cfg` instead of `yolov3.cfg`
+* Start training: `darknet.exe detector train data/obj.data yolov3-tiny-obj.cfg yolov3-tiny.conv.15`
For training Yolo based on other models ([DenseNet201-Yolo](https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x64/densenet201_yolo.cfg) or [ResNet50-Yolo](https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x64/resnet50_yolo.cfg)), you can download and get pre-trained weights as showed in this file: https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x64/partial.cmd
If you made you custom model that isn't based on other models, then you can train it without pre-trained weights, then will be used random initial weights.
@@ -349,7 +349,7 @@
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:
-For example, you stopped training after 9000 iterations, but the best result can give one of previous weights (7000, 8000, 9000). It can happen due to overfitting. **Overfitting** - is case when you can detect objects on images from training-dataset, but can't detect ojbects on any others images. You should get weights from **Early Stopping Point**:
+For example, you stopped training after 9000 iterations, but the best result can give one of previous weights (7000, 8000, 9000). It can happen due to overfitting. **Overfitting** - is case when you can detect objects on images from training-dataset, but can't detect objects on any others images. You should get weights from **Early Stopping Point**:
@@ -415,12 +415,22 @@
`darknet.exe detector calc_anchors data/obj.data -num_of_clusters 9 -width 416 -height 416`
then set the same 9 `anchors` in each of 3 `[yolo]`-layers in your cfg-file
+ * check that each object are mandatory labeled in your dataset - no one object in your data set should not be without label. In the most training issues - there are wrong labels in your dataset (got labels by using some conversion script, marked with a third-party tool, ...). Always check your dataset by using: https://github.com/AlexeyAB/Yolo_mark
+
* 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 non-labeled objects that you do not want to detect - negative samples without bounded box (empty `.txt` files)
* 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 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
+
+ * General rule - you should keep relative size of objects in the Training and Testing datasets roughly the same:
+
+ * `train_network_width * train_obj_width / train_image_width ~= detection_network_width * detection_obj_width / detection_image_width`
+ * `train_network_height * train_obj_height / train_image_height ~= detection_network_height * detection_obj_height / detection_image_height`
+
* 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 before the 1-st `[yolo]`-layer, for example here: https://github.com/AlexeyAB/darknet/blob/0039fd26786ab5f71d5af725fc18b3f521e7acfd/cfg/yolov3.cfg#L598
2. After training - for detection:
--
Gitblit v1.10.0