File size: 1,694 Bytes
a72119e |
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 |
import gradio as gr
from gradio_imageslider import ImageSlider
from loadimg import load_img
import spaces
from transformers import AutoModelForImageSegmentation
import torch
from torchvision import transforms
torch.set_float32_matmul_precision(["high", "highest"][0])
birefnet = AutoModelForImageSegmentation.from_pretrained(
"ZhengPeng7/BiRefNet", trust_remote_code=True
)
birefnet.to("cuda")
transform_image = transforms.Compose(
[
transforms.Resize((1024, 1024)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
]
)
def fn(vid):
# TODO
# loop over video and extract images and process each one
im = load_img(vid, output_type="pil")
im = im.convert("RGB")
image = process(im)
return image
@spaces.GPU
def process(image):
image_size = image.size
input_images = transform_image(image).unsqueeze(0).to("cuda")
# Prediction
with torch.no_grad():
preds = birefnet(input_images)[-1].sigmoid().cpu()
pred = preds[0].squeeze()
pred_pil = transforms.ToPILImage()(pred)
mask = pred_pil.resize(image_size)
image.putalpha(mask)
return image
def process_file(f):
name_path = f.rsplit(".",1)[0]+".png"
im = load_img(f, output_type="pil")
im = im.convert("RGB")
transparent = process(im)
transparent.save(name_path)
return name_path
in_video = gr.Video(label="birefnet")
out_video = gr.Video()
url = "https://hips.hearstapps.com/hmg-prod/images/gettyimages-1229892983-square.jpg"
demo = gr.Interface(
fn, inputs=in_video, outputs=out_video, api_name="image"
)
if __name__ == "__main__":
demo.launch(show_error=True) |