Fine-tune Mask-RCNN on a customized beagle dataset
There is a total number of 100 beagle images in the dataset which I scraped from Google Image. 75 images are used for training and 25 images are used for validation.
I used VGG Image Annotator (VIA) to annotate the training and validation images.
Feel free to use the dataset and modify the code. The original code is adopted from mattport's Mask-RCNN repo.