Spaces:
Running
Running
File size: 2,360 Bytes
5f57808 c8f8b0e 5f57808 c8f8b0e 5f57808 c8f8b0e 5f57808 c8f8b0e 5f57808 c8f8b0e 5f57808 c8f8b0e 5f57808 c8f8b0e 5f57808 |
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 86 87 |
import os
from typing import List
import numpy as np
import pooch
from PIL import Image
from PIL.Image import Image as PILImage
from .base import BaseSession
class DisSession(BaseSession):
"""
This class represents a session for object detection.
"""
def predict(self, img: PILImage, *args, **kwargs) -> List[PILImage]:
"""
Use a pre-trained model to predict the object in the given image.
Parameters:
img (PILImage): The input image.
*args: Variable length argument list.
**kwargs: Arbitrary keyword arguments.
Returns:
List[PILImage]: A list of predicted mask images.
"""
ort_outs = self.inner_session.run(
None,
self.normalize(img, (0.485, 0.456, 0.406), (1.0, 1.0, 1.0), (1024, 1024)),
)
pred = ort_outs[0][:, 0, :, :]
ma = np.max(pred)
mi = np.min(pred)
pred = (pred - mi) / (ma - mi)
pred = np.squeeze(pred)
mask = Image.fromarray((pred * 255).astype("uint8"), mode="L")
mask = mask.resize(img.size, Image.Resampling.LANCZOS)
return [mask]
@classmethod
def download_models(cls, *args, **kwargs):
"""
Download the pre-trained models.
Parameters:
*args: Variable length argument list.
**kwargs: Arbitrary keyword arguments.
Returns:
str: The path of the downloaded model file.
"""
fname = f"{cls.name(*args, **kwargs)}.onnx"
pooch.retrieve(
"https://github.com/danielgatis/rembg/releases/download/v0.0.0/isnet-anime.onnx",
(
None
if cls.checksum_disabled(*args, **kwargs)
else "md5:6f184e756bb3bd901c8849220a83e38e"
),
fname=fname,
path=cls.u2net_home(*args, **kwargs),
progressbar=True,
)
return os.path.join(cls.u2net_home(*args, **kwargs), fname)
@classmethod
def name(cls, *args, **kwargs):
"""
Get the name of the pre-trained model.
Parameters:
*args: Variable length argument list.
**kwargs: Arbitrary keyword arguments.
Returns:
str: The name of the pre-trained model.
"""
return "isnet-anime"
|