Update app.py

app.py

@@ -1,88 +1,57 @@
-import glob
+import os
+import subprocess
 import gradio as gr
-import matplotlib
-import numpy as np
+from gradio_imageslider import ImageSlider
 from PIL import Image
-import torch
+import glob
 import tempfile
-from gradio_imageslider import ImageSlider
-
-from depth_anything_v2.dpt import DepthAnythingV2
-
-css = """
-#img-display-container {
-    max-height: 100vh;
-}
-#img-display-input {
-    max-height: 80vh;
-}
-#img-display-output {
-    max-height: 80vh;
-}
-#download {
-    height: 62px;
-}
-"""
-DEVICE = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu'
-model_configs = {
-    'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384]},
-    'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768]},
-    'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024]},
-    'vitg': {'encoder': 'vitg', 'features': 384, 'out_channels': [1536, 1536, 1536, 1536]}
-}
-encoder = 'vitl'
-model = DepthAnythingV2(**model_configs[encoder])
-state_dict = torch.load(f'checkpoints/depth_anything_v2_{encoder}.pth', map_location="cpu")
-model.load_state_dict(state_dict)
-model = model.to(DEVICE).eval()
-
-title = "# Depth Anything V2"
-description = """Official demo for **Depth Anything V2**.
-Please refer to our [paper](https://arxiv.org/abs/2406.09414), [project page](https://depth-anything-v2.github.io), or [github](https://github.com/DepthAnything/Depth-Anything-V2) for more details."""
-
-def predict_depth(image):
-    return model.infer_image(image)
-
-with gr.Blocks(css=css) as demo:
-    gr.Markdown(title)
-    gr.Markdown(description)
-    gr.Markdown("### Depth Prediction demo")
-
-    with gr.Row():
-        input_image = gr.Image(label="Input Image", type='numpy', elem_id='img-display-input')
-        depth_image_slider = ImageSlider(label="Depth Map with Slider View", elem_id='img-display-output', position=0.5)
-    submit = gr.Button(value="Compute Depth")
-    gray_depth_file = gr.File(label="Grayscale depth map", elem_id="download",)
-    raw_file = gr.File(label="16-bit raw output (can be considered as disparity)", elem_id="download",)
-
-    cmap = matplotlib.colormaps.get_cmap('Spectral_r')
-
-    def on_submit(image):
-        original_image = image.copy()
-
-        h, w = image.shape[:2]
-
-        depth = predict_depth(image[:, :, ::-1])
-
-        raw_depth = Image.fromarray(depth.astype('uint16'))
-        tmp_raw_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
-        raw_depth.save(tmp_raw_depth.name)
-
-        depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
-        depth = depth.astype(np.uint8)
-        colored_depth = (cmap(depth)[:, :, :3] * 255).astype(np.uint8)
-
-        gray_depth = Image.fromarray(depth)
-        tmp_gray_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
-        gray_depth.save(tmp_gray_depth.name)
-
-        return [(original_image, colored_depth), tmp_gray_depth.name, tmp_raw_depth.name]
-
-    submit.click(on_submit, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file])
-
-    example_files = glob.glob('assets/examples/*')
-    examples = gr.Examples(examples=example_files, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file], fn=on_submit)
-
 
-if __name__ == '__main__':
+# Output folder
+OUTPUT_DIR = "output"
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+def process_video(video_file):
+    """
+    Run DepthAnythingV2 run_video.py CLI to process the uploaded MP4 video
+    and return both a slider view (per-frame depth map) and the output video.
+    """
+    video_path = video_file.name
+
+    # Call run_video.py using subprocess
+    cmd = [
+        "python", "run_video.py",
+        "--encoder", "vitb",
+        "--video-path", video_path,
+        "--outdir", OUTPUT_DIR,
+        "--grayscale",
+        "--pred-only"
+    ]
+    subprocess.run(cmd, check=True)
+
+    # run_video.py output video filename: <input>_depth.mp4
+    base_name = os.path.basename(video_path)
+    output_video = os.path.join(OUTPUT_DIR, base_name.replace(".mp4", "_depth.mp4"))
+
+    # Prepare slider images for per-frame preview
+    # Assume run_video.py saves frames as PNG in output folder
+    slider_images = []
+    frame_files = sorted(glob.glob(os.path.join(OUTPUT_DIR, "*.png")))
+    for f in frame_files:
+        slider_images.append(Image.open(f))
+
+    return slider_images, output_video
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# Depth Anything V2 - Video Demo")
+    gr.Markdown("Upload an MP4 video, and the system will automatically generate a DepthMap video.")
+
+    video_input = gr.File(label="Upload MP4", file_types=['.mp4'])
+    depth_slider = ImageSlider(label="Depth Map Slider")  # Slider view of frames
+    video_output = gr.Video(label="DepthMap Video")
+    submit = gr.Button("Render DepthMap")
+
+    submit.click(fn=process_video, inputs=[video_input], outputs=[depth_slider, video_output])
+
+if __name__ == "__main__":
     demo.queue().launch()