feat: init app

app.py

@@ -0,0 +1,56 @@
+import depth_pro
+import gradio as gr
+import matplotlib.cm as cm
+import numpy as np
+from depth_pro.depth_pro import DepthProConfig
+from PIL import Image
+
+
+def run(input_image_path):
+    config = DepthProConfig(
+        patch_encoder_preset="dinov2l16_384",
+        image_encoder_preset="dinov2l16_384",
+        checkpoint_uri="./depth_pro.pt",
+        decoder_features=256,
+        use_fov_head=True,
+        fov_encoder_preset="dinov2l16_384",
+    )
+
+    # Load model and preprocessing transform
+    model, transform = depth_pro.create_model_and_transforms(config=config)
+    model.eval()
+
+    # Load and preprocess an image
+    image, _, f_px = depth_pro.load_rgb(input_image_path)
+    image = transform(image)
+
+    # Run inference
+    prediction = model.infer(image, f_px=f_px)
+
+    depth_map = prediction["depth"].squeeze().cpu().numpy()
+    focallength_px = prediction["focallength_px"]
+
+    depth_map = (depth_map - depth_map.min()) / (depth_map.max() - depth_map.min())
+    colormap = cm.get_cmap("viridis")
+    depth_map = colormap(depth_map)
+    depth_map = (depth_map[:, :, :3] * 255).astype(np.uint8)
+
+    depth_map = Image.fromarray(depth_map)
+
+    return depth_map, focallength_px.item()
+
+
+demo = gr.Interface(
+    fn=run,
+    inputs=gr.Image(label="Input Image", type="filepath"),
+    outputs=[
+        gr.Image(label="Depth Map"),
+        gr.Number(label="Focal Length"),
+    ],
+    description="""
+        <div align="center">
+            <h2><a href="https://arxiv.org/abs/2410.02073">Depth Pro: Sharp Monocular Metric Depth in Less Than a Second</a></h2>
+        </div>
+        """,
+)
+demo.launch()