Closed ghost closed 3 years ago
There's no silver bullet; you need to experiment on various parameter settings and compare their results. Anyway, here are some suggestions:-
Also try out heavier models like deeplab, bisnet, boundary-aware network etc. if speed is not an issue...
Thanks, I probably won't be able to do it, I'll try to figure it out.
How can I for example use resnet18 or vgg16 to train the model?
I would suggest you to look at the working of basic encoder decoder networks and how to use popular networks like mobilenet or resnet as backbone for segmentaion tasks.
Thanks, i use DeeplabV3Plus now
Hi, thank you very much for your previous help. How can I significantly increase segmentation accuracy of the slim512 network, speed is not important in principle, I need a very high segmentation accuracy and the ability to convert the model to TFLite.