From 3256967119b100231dd11b181431bad0e2e46201 Mon Sep 17 00:00:00 2001 From: Alexey Date: Mon, 10 Dec 2018 01:37:40 +0300 Subject: [PATCH] Update Readme.md --- README.md | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index d621f9d8..5765acd6 100644 --- a/README.md +++ b/README.md @@ -251,11 +251,9 @@ 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. For 4xGPUs - increase 4x times `burn_in =` and `max_batches =` in your cfg-file. I.e. use `burn_in = 4000` instead of `1000`. +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` -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` - -Only for small datasets sometimes better to decrease learning rate, for 4 GPUs set `learning_rate = 0.00025` (i.e. learning_rate = 0.001 / GPUs). +Only for small datasets sometimes better to decrease learning rate, for 4 GPUs set `learning_rate = 0.00025` (i.e. learning_rate = 0.001 / GPUs). In this case also increase 4x times `burn_in =` and `max_batches =` in your cfg-file. I.e. use `burn_in = 4000` instead of `1000`. https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ