From a0dc4d717ab2d95e5e90f5b7b6344e8074b81606 Mon Sep 17 00:00:00 2001 From: Alexey Date: Fri, 30 Mar 2018 18:34:28 +0300 Subject: [PATCH] Update Readme.md --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 0830e120..343db79b 100644 --- a/README.md +++ b/README.md @@ -219,7 +219,7 @@ 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/yolo-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolo-voc_1000.weights -gpus 0,1,2,3` +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` https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ @@ -305,6 +305,8 @@ https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ * 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. + ### 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: