mirror of
https://github.com/pjreddie/darknet.git
synced 2023-08-10 21:13:14 +03:00
Update Readme.md
This commit is contained in:
@ -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
|
||||
|
||||
|
Reference in New Issue
Block a user