zymk9 / yet-another-anime-segmenter Goto Github PK

Hi! I was wondering if it would be possible for you to upload the manually annotated data?

Hi, thanks for your work and I want to know how to delete the text boxes of output image.
I find that there is a text boxed on the leftup of image with info(tensor(0) 80%), how to delete it?Thanks!

It's very useful for my dataset. But I found that the confidence-threshold is not so good to estimate the confidence.

Like place the detection over a transparent/white background

Your model is the best one for Anime segmentation task that I have ever seen.

There is a new crowd-sourced dataset for danbooru. Hope it will help further improve the performance.

It would be even better if you could add more classes for the segmentation.

what's the potential applications Anime Segmentation?

Hi, your work is great and very interesting.
I'm wondering if I could segment only head and hairs of the anime character.
I want to train with my own dataset, but can it be realized by doing the way this link says? https://github.com/aim-uofa/AdelaiDet/tree/master/configs/SOLOv2#installation--quick-start
Or did you build your own model and trained with pretrained models? If so, can you teach me further details how to do these things?
I just started studying deeplearnings, so I apolgize if this is a dumb question.

assert torch.__version__.startswith("1.7")
!pip install detectron2 -f
https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.7/index.html
clear_output()

AssertionError Traceback (most recent call last)
in
3 # See https://detectron2.readthedocs.io/tutorials/install.html for instructions if you
4 # want to switch to an older version
----> 5 assert torch.version.startswith("1.7")
6 get_ipython().system('pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.7/index.html')
7 clear_output()

AssertionError:

I am getting this error in that code. What should i do to solve this problem?
I ran this in colab.

Hey, I'm kinda new to ai. I'm trying to use YAAS in my personal project and I'm stuck on this error. Do you have any idea what am I doing wrong?

class AnimeSegmentator:
    def __init__(self):
        config_path = "./YAAS/SOLOv2.yaml"
        model_path = "./YAAS/SOLOv2.pth"
        cfg = get_cfg()
        cfg.merge_from_file(config_path)
        cfg.MODEL.WEIGHTS = model_path
        cfg.MODEL.DEVICE = "cpu" #torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
        cfg.freeze()
        self.model = DefaultPredictor(cfg)
        self.model.score_threshold = 0.1
        self.model.mask_threshold = 0.5
    
    def run(self, image):
        preds = self.model(image)
        print(preds)
        return image