added files

app.py

@@ -0,0 +1,74 @@
+import gradio as gr
+import cv2
+import torch
+import numpy as np
+from torchvision import transforms
+
+title = "Background Remover"
+description = "Automatically remove the image background from a profile photo."
+article = "<p style='text-align: center'><a href='https://news.machinelearning.sg/posts/beautiful_profile_pics_remove_background_image_with_deeplabv3/'>Blog</a> | <a href='https://github.com/eugenesiow/practical-ml'>Github Repo</a></p>"
+
+
+def make_transparent_foreground(pic, mask):
+    # split the image into channels
+    b, g, r = cv2.split(np.array(pic).astype('uint8'))
+    # add an alpha channel with and fill all with transparent pixels (max 255)
+    a = np.ones(mask.shape, dtype='uint8') * 255
+    # merge the alpha channel back
+    alpha_im = cv2.merge([b, g, r, a], 4)
+    # create a transparent background
+    bg = np.zeros(alpha_im.shape)
+    # setup the new mask
+    new_mask = np.stack([mask, mask, mask, mask], axis=2)
+    # copy only the foreground color pixels from the original image where mask is set
+    foreground = np.where(new_mask, alpha_im, bg).astype(np.uint8)
+
+    return foreground
+
+
+def remove_background(input_image):
+    preprocess = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+    ])
+
+    input_tensor = preprocess(input_image)
+    input_batch = input_tensor.unsqueeze(0)  # create a mini-batch as expected by the model
+
+    # move the input and model to GPU for speed if available
+    if torch.cuda.is_available():
+        input_batch = input_batch.to('cuda')
+        model.to('cuda')
+
+    with torch.no_grad():
+        output = model(input_batch)['out'][0]
+    output_predictions = output.argmax(0)
+
+    # create a binary (black and white) mask of the profile foreground
+    mask = output_predictions.byte().cpu().numpy()
+    background = np.zeros(mask.shape)
+    bin_mask = np.where(mask, 255, background).astype(np.uint8)
+
+    foreground = make_transparent_foreground(input_image, bin_mask)
+
+    return foreground, bin_mask
+
+
+def inference(img):
+    foreground, _ = remove_background(img)
+    return foreground
+
+
+model = torch.hub.load('pytorch/vision:v0.6.0', 'deeplabv3_resnet101', pretrained=True)
+model.eval()
+
+gr.Interface(
+    inference,
+    gr.inputs.Image(type="pil", label="Input"),
+    gr.outputs.Image(type="pil", label="Output"),
+    title=title,
+    description=description,
+    article=article,
+    examples=[['woman.jpg'], ['man,jpg']],
+    enable_queue=True
+).launch(debug=False)

packages.txt

@@ -0,0 +1,4 @@
+python3-opencv
+ffmpeg
+libsm6
+libxext6

requirements.txt

@@ -0,0 +1,3 @@
+opencv-python==4.5.4.58
+torch==1.10.0
+torchvision==0.11.1