From d502dea9a451c290f602ba18bc61f4f79c51be0c Mon Sep 17 00:00:00 2001 From: Alexey Date: Mon, 4 Jun 2018 13:55:27 +0300 Subject: [PATCH] Update Readme.md --- README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/README.md b/README.md index e56efa8c..40289e9e 100644 --- a/README.md +++ b/README.md @@ -421,6 +421,11 @@ 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 layer [region] in your cfg-file + * General rule - you should keep relative size of objects in the Training and Testing datasets 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: