Closed euivmar closed 5 years ago
@euivmar Hi,
We are training with synthetic data extracted from a renderized photorealistic 3D model
This is very good approach.
Do you have any advice to training the yolo network? Is it necessary to freeze yolo layers? How can we do it?
No, you shouldn't freeze layers to get the highest accuracy.
Currently, we are testing with: darknet.exe detector train data/obj.data yolo-obj.cfg yolov3.conv.81
This is correct.
Just if you want to achieve higher mAP@0.5 then base your cfg-file on yolov3-spp.cfg
instead of yolov3.cfg
If you want to achieve higher mAP@0.75 or mAP@0.5...0.95 then base on `yolov3-spp.cfg
and add to each of 3
[yolo]` layers these 2 lines
iou_normalizer=0.5
iou_loss=giou
Also disable CUDNN_HALF.
CUDNN_HALF;
Thanks so much for your quick answer @AlexeyAB! I am going to try your suggestions.
@AlexeyAB
If you want to achieve higher mAP@0.75 or mAP@0.5...0.95 then base on
`yolov3-spp.cfg
and add to each of 3
[yolo]` layers these 2 linesiou_normalizer=0.5 iou_loss=giou
Does a lower iou_normalizer favor high mAP@0.75?
Why do I feel it's the opposite because higher iou_normalizer
will pay more attention to the bounding box?
Thanks.
Dear @AlexeyAB
We are training with synthetic data extracted from a renderized photorealistic 3D model (3D motor engine) with random backgrounds (Vocimages) and from multiple scales and view points replicating the work of Hinterstoisser et al 2017. The procedure is syntethized in this image from the paper .
We have random light and several image augmentations like gaussian noise, flip, rotation... We are working with about 20.000 images for only one class. Do you have any advice to training the yolo network? Is it necessary to freeze yolo layers? How can we do it? Currently, we are testing with:
darknet.exe detector train data/obj.data yolo-obj.cfg yolov3.conv.81