Update Readme.md

This commit is contained in:
Alexey
2018-09-14 15:29:52 +03:00
committed by GitHub
parent ca43bbdaae
commit b829fee30b

View File

@ -229,7 +229,9 @@ More information about training by the link: http://pjreddie.com/darknet/yolo/#t
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`
3. For 4xGPUs - increase 4x times `burn_in =` and `max_batches =` in your cfg-file. I.e. use `burn_in = 4000` instead of `1000`.
4. 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