File size: 3,022 Bytes
5395ccf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e761b96
5395ccf
 
 
 
900e3ff
5395ccf
ffb9fb5
5395ccf
bb15987
e761b96
5395ccf
 
 
 
 
 
 
 
84ef148
 
 
 
 
 
 
4579715
6b8f616
 
5395ccf
 
6b8f616
5395ccf
 
 
 
 
 
ea9dbee
37b5606
b63cf58
5395ccf
 
 
 
 
 
 
 
 
e324aa4
 
c0ca1d8
e4e47d6
5395ccf
c0ca1d8
 
 
 
5395ccf
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
#try:
#    import detectron2
#except:
import os 
os.system('pip install git+https://github.com/SysCV/transfiner.git')

from matplotlib.pyplot import axis
import gradio as gr
import requests
import numpy as np
from torch import nn
import requests

import torch

from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog


model_name='./configs/transfiner/mask_rcnn_R_101_FPN_3x_deform.yaml'


cfg = get_cfg()
# add project-specific config (e.g., TensorMask) here if you're not running a model in detectron2's core library
cfg.merge_from_file(model_name)
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
cfg.VIS_PERIOD = 100
# Find a model from detectron2's model zoo. You can use the https://dl.fbaipublicfiles... url as w ell
#cfg.MODEL.WEIGHTS = './output_3x_transfiner_r50.pth'
cfg.MODEL.WEIGHTS = './output_3x_transfiner_r101_deform.pth'

if not torch.cuda.is_available():
    cfg.MODEL.DEVICE='cpu'

predictor = DefaultPredictor(cfg)


def inference(image):
    width, height = image.size
    if width > 1300:
        ratio = float(height) / float(width)
        width = 1300
        height = int(ratio * width)
        image = image.resize((width, height))

    img = np.asarray(image)

    #img = np.array(image)
    outputs = predictor(img)

    v = Visualizer(img, MetadataCatalog.get(cfg.DATASETS.TRAIN[0]))
    out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
    
    return out.get_image()



title = "Mask Transfiner [CVPR, 2022]"
description = "Demo for <a target='_blank' href='https://arxiv.org/abs/2111.13673'>Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022</a> based on R50-FPN. To use it, simply upload your image, or click one of the examples to load them. Note that it runs in the <b>CPU environment</b> provided by Hugging Face so the processing speed may be slow."
article = "<p style='text-align: center'><a target='_blank' href='https://arxiv.org/abs/2111.13673'>Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022</a> | <a target='_blank' href='https://github.com/SysCV/transfiner'>Mask Transfiner Github Code</a></p>"

gr.Interface(
    inference, 
    [gr.inputs.Image(type="pil", label="Input")], 
    gr.outputs.Image(type="numpy", label="Output"),
    title=title,
    description=description,
    article=article,
    examples=[
            ["demo/sample_imgs/000000131444.jpg"],
            ["demo/sample_imgs/000000157365.jpg"],
            ["demo/sample_imgs/000000176037.jpg"],
            ["demo/sample_imgs/000000018737.jpg"],
            ["demo/sample_imgs/000000224200.jpg"],
            ["demo/sample_imgs/000000558073.jpg"],
            ["demo/sample_imgs/000000404922.jpg"],
            ["demo/sample_imgs/000000252776.jpg"],
            ["demo/sample_imgs/000000482477.jpg"],
            ["demo/sample_imgs/000000344909.jpg"]
        ]).launch()