From dbdd31ee211fe8b1ac7e93ceadf7b34b8d304f34 Mon Sep 17 00:00:00 2001 From: Roland Singer Date: Wed, 22 Aug 2018 13:56:41 +0200 Subject: [PATCH] updated README to include information about learning rate adjustment for multiple GPUs --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 963c401b..18d3f153 100644 --- a/README.md +++ b/README.md @@ -227,7 +227,9 @@ More information about training by the link: http://pjreddie.com/darknet/yolo/#t 1. Train it first on 1 GPU for like 1000 iterations: `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg darknet53.conv.74` -2. Then stop and by using partially-trained model `/backup/yolov3-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolov3-voc_1000.weights -gpus 0,1,2,3` +2. Adjust the learning rate (`cfg/yolov3-voc.cfg`) to fit the amount of GPUs. The learning rate should be equal to `0.001`, regardless of how many GPUs are used for training. So `learning_rate * GPUs = 0.001`. For 4 GPUs adjust the value to `learning_rate = 0.00025`. + +3. Then stop and by using partially-trained model `/backup/yolov3-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolov3-voc_1000.weights -gpus 0,1,2,3` https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ