then set the same 9 `anchors` in each of 3 `[yolo]`-layers in your cfg-file
(also you can change indexes of anchors `masks=` for each [yolo]-layer, so that 1st-[yolo]-layer has anchors larger than 60x60, 2nd larger than 30x30, 3rd remaining)
* 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
* 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
@ -488,7 +483,7 @@ Example of custom object detection: `darknet.exe detector test data/obj.data yol
* 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 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
* for training for small objects (smaller than 16x16 after the image is resized to 416x416) - 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
and set `stride=4` instead of https://github.com/AlexeyAB/darknet/blob/6390a5a2ab61a0bdf6f1a9a6b4a739c16b36e0d7/cfg/yolov3.cfg#L717
* for training for both small and large objects use modified models:
* for training for both small and large objects use modified models:
@ -515,6 +510,10 @@ Example of custom object detection: `darknet.exe detector test data/obj.data yol
* The more different objects you want to detect, the more complex network model should be used. But each: `model of object, side, illimination, scale, each 30 grad` of the turn and inclination angles - these are different objects from a neural network perspective.
* The more different objects you want to detect, the more complex network model should be used. But each: `model of object, side, illimination, scale, each 30 grad` of the turn and inclination angles - these are different objects from a neural network perspective.
* recalculate anchors for your dataset for `width` and `height` from cfg-file:
then set the same 9 `anchors` in each of 3 `[yolo]`-layers in your cfg-file. But you should change indexes of anchors `masks=` for each [yolo]-layer, so that 1st-[yolo]-layer has anchors larger than 60x60, 2nd larger than 30x30, 3rd remaining. If many of the calculated anchors do not fit under the appropriate layers - then just try using all the default anchors.
Alexey
6 years ago
committed by
GitHub