From d723d2cfd0838fae2c34d3f19eb7cceda0a3fa44 Mon Sep 17 00:00:00 2001 From: HagegeR Date: Sun, 24 Nov 2019 19:49:03 +0200 Subject: [PATCH] added gaussian documentation I wasn't sure how to add the distinction without breaking the explanation flow, I hope I did ok... --- README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 13a13167..23969c10 100644 --- a/README.md +++ b/README.md @@ -377,7 +377,11 @@ Training Yolo v3: * https://github.com/AlexeyAB/darknet/blob/0039fd26786ab5f71d5af725fc18b3f521e7acfd/cfg/yolov3.cfg#L603 * https://github.com/AlexeyAB/darknet/blob/0039fd26786ab5f71d5af725fc18b3f521e7acfd/cfg/yolov3.cfg#L689 * https://github.com/AlexeyAB/darknet/blob/0039fd26786ab5f71d5af725fc18b3f521e7acfd/cfg/yolov3.cfg#L776 - + * when using [[`gaussian_yolo`]](https://github.com/AlexeyAB/darknet/blob/6e5bdf1282ad6b06ed0e962c3f5be67cf63d96dc/cfg/Gaussian_yolov3_BDD.cfg#L608) layers, change [`filters=57`] filters=(classes + 9)x3 in the 3 `[convolutional]` before each `[gaussian_yolo]` layer + * https://github.com/AlexeyAB/darknet/blob/6e5bdf1282ad6b06ed0e962c3f5be67cf63d96dc/cfg/Gaussian_yolov3_BDD.cfg#L604 + * https://github.com/AlexeyAB/darknet/blob/6e5bdf1282ad6b06ed0e962c3f5be67cf63d96dc/cfg/Gaussian_yolov3_BDD.cfg#L696 + * https://github.com/AlexeyAB/darknet/blob/6e5bdf1282ad6b06ed0e962c3f5be67cf63d96dc/cfg/Gaussian_yolov3_BDD.cfg#L789 + 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)**