nikunjkdtechnoland
add bg remover
e9d702e
import numpy as np
import torch
import torch.nn.functional as F
from torchvision.transforms.functional import normalize
from bgremove.bg_remove_cnn import BriaRMBG
from PIL import Image
net = BriaRMBG()
model_path = "./pretrained-model/bgremove.pth"
if torch.cuda.is_available():
net.load_state_dict(torch.load(model_path))
net = net.cuda()
else:
net.load_state_dict(torch.load(model_path, map_location="cpu"))
net.eval()
def resize_image(image):
image = image.convert('RGB')
model_input_size = (1024, 1024)
image = image.resize(model_input_size, Image.BILINEAR)
return image
def process(image):
# prepare input
orig_image = Image.fromarray(image)
w, h = orig_im_size = orig_image.size
image = resize_image(orig_image)
im_np = np.array(image)
im_tensor = torch.tensor(im_np, dtype=torch.float32).permute(2, 0, 1)
im_tensor = torch.unsqueeze(im_tensor, 0)
im_tensor = torch.divide(im_tensor, 255.0)
im_tensor = normalize(im_tensor, [0.5, 0.5, 0.5], [1.0, 1.0, 1.0])
if torch.cuda.is_available():
im_tensor = im_tensor.cuda()
# inference
result = net(im_tensor)
# post process
result = torch.squeeze(F.interpolate(result[0][0], size=(h, w), mode='bilinear'), 0)
ma = torch.max(result)
mi = torch.min(result)
result = (result - mi) / (ma - mi)
# image to pil
im_array = (result * 255).cpu().data.numpy().astype(np.uint8)
pil_im = Image.fromarray(np.squeeze(im_array))
# paste the mask on the original image
new_im = Image.new("RGBA", pil_im.size, (0, 0, 0, 0))
new_im.paste(orig_image, mask=pil_im)
# new_orig_image = orig_image.convert('RGBA')
return new_im