Upload folder using huggingface_hub

app.py

@@ -6,58 +6,48 @@ from ormbg import ORMBG
 from PIL import Image
 
 
-def preprocess_image(im: np.ndarray, model_input_size: list) -> torch.Tensor:
-    if len(im.shape) < 3:
-        im = im[:, :, np.newaxis]
-    im_tensor = torch.tensor(im, dtype=torch.float32).permute(2, 0, 1)
-    im_tensor = F.interpolate(
-        torch.unsqueeze(im_tensor, 0), size=model_input_size, mode="bilinear"
-    ).type(torch.uint8)
-    image = torch.divide(im_tensor, 255.0)
-    return image
-
+model_path = "ormbg.pth"
 
-def postprocess_image(result: torch.Tensor, im_size: list) -> np.ndarray:
-    result = torch.squeeze(F.interpolate(result, size=im_size, mode="bilinear"), 0)
-    ma = torch.max(result)
-    mi = torch.min(result)
-    result = (result - mi) / (ma - mi)
-    im_array = (result * 255).permute(1, 2, 0).cpu().data.numpy().astype(np.uint8)
-    im_array = np.squeeze(im_array)
-    return im_array
+net = ORMBG()
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+net.to(device)
 
 
-def inference(image):
+def resize_image(image):
+    image = image.convert("RGB")
+    model_input_size = (1024, 1024)
+    image = image.resize(model_input_size, Image.BILINEAR)
+    return image
 
-    model_path = "ormbg.pth"
 
-    net = ORMBG()
-    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+def inference(image):
 
+    # prepare input
     orig_image = Image.fromarray(image)
-
+    w, h = 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)
     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()
-
-    model_input_size = [1024, 1024]
-    orig_im_size = orig_image.size
-    processed_image = preprocess_image(orig_image, model_input_size).to(device)
-
-    result = net(processed_image)
+        im_tensor = im_tensor.cuda()
 
+    # inference
+    result = net(im_tensor)
     # post process
-    result_image = postprocess_image(result[0][0], orig_im_size)
-
-    # save result
-    pil_im = Image.fromarray(result_image)
-    no_bg_image = Image.new("RGBA", pil_im.size, (0, 0, 0, 0))
-    no_bg_image.paste(orig_image, mask=pil_im)
-
-    return no_bg_image
+    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)
+
+    return new_im
 
 
 gr.Markdown("## Open Remove Background Model (ormbg)")