Hi there!
Does anybody have implementation of Mask R-CNN in PyTorch that has ability to fine-tuning on own dataset?
Hi there!
Does anybody have implementation of Mask R-CNN in PyTorch that has ability to fine-tuning on own dataset?
Hi, Oktai,
For inference only, please refer to the below implementation (reproduce).
https://github.com/ignacio-rocco/detectorch
For training/fine-tuning, you can refer to this implementation, but no benchmark performance has been reported, meaning that it might has risks in reproducing paper’s results.
https://github.com/roytseng-tw/mask-rcnn.pytorch
Best
Not yet, I just saw a guy I stared follow the second implementation.
The author of the second implementation posts benchmark evaluation results, seems reasonable.
From the Facebook Research team, just released, support for training on own dataset.