Upload 2 files

app.py

@@ -1,102 +1,68 @@
 import gradio as gr
+import torch
+from PIL import Image
 import cv2
-import matplotlib
 import numpy as np
+from geobench.modeling.archs.dam.dam import DepthAnything
+from geobench.utils.image_util import colorize_depth_maps
+from geobench.midas.transforms import Resize, NormalizeImage, PrepareForNet
+from torchvision.transforms import Compose
 import os
-from PIL import Image
-import spaces
-import torch
-import tempfile
-from gradio_imageslider import ImageSlider
-from huggingface_hub import hf_hub_download
-
-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 '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]}
-}
-encoder2name = {
-    'vits': 'Small',
-    'vitb': 'Base',
-    'vitl': 'Large',
-    'vitg': 'Giant', # we are undergoing company review procedures to release our giant model checkpoint
-}
-encoder = 'vitl'
-model_name = encoder2name[encoder]
-model = DepthAnythingV2(**model_configs[encoder])
-filepath = hf_hub_download(repo_id=f"depth-anything/Depth-Anything-V2-{model_name}", filename=f"depth_anything_v2_{encoder}.pth", repo_type="model")
-state_dict = torch.load(filepath, 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), and [github](https://github.com/DepthAnything/Depth-Anything-V2) for more details."""
-
-@spaces.GPU
-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 = os.listdir('assets/examples')
-    example_files.sort()
-    example_files = [os.path.join('assets/examples', filename) for filename in example_files]
-    examples = gr.Examples(examples=example_files, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file], fn=on_submit)
-
 
-if __name__ == '__main__':
-    demo.queue().launch(share=True)
+# Helper function to load model (same as your original code)
+def load_model_by_name(arch_name, checkpoint_path, device):
+    if arch_name == 'depthanything':
+        if '.safetensors' in checkpoint_path:
+            model = DepthAnything.from_pretrained(os.path.dirname(checkpoint_path)).to(device)
+        else:
+            raise NotImplementedError("Model architecture not implemented.")
+    else:
+        raise NotImplementedError(f"Unknown architecture: {arch_name}")
+    return model
+
+# Image processing function (same as your original code, modified for Gradio)
+def process_image(image, model, device, mode='rel_depth'):
+    # Preprocess the image
+    image_np = np.array(image)[..., ::-1] / 255
+    transform = Compose([
+        Resize(512, 512, resize_target=None, keep_aspect_ratio=False, ensure_multiple_of=32, image_interpolation_method=cv2.INTER_CUBIC),
+        NormalizeImage(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
+        PrepareForNet()
+    ])
+    
+    image_tensor = transform({'image': image_np})['image']
+    image_tensor = torch.from_numpy(image_tensor).unsqueeze(0).to(device)
+    
+    with torch.no_grad():  # Disable autograd since we don't need gradients on CPU
+        pred_disp, _ = model(image_tensor)
+        pred_disp_np = pred_disp.cpu().detach().numpy()[0, :, :, :].transpose(1, 2, 0)
+        pred_disp = (pred_disp_np - pred_disp_np.min()) / (pred_disp_np.max() - pred_disp_np.min())
+
+    # Colorize depth map
+    cmap = "Spectral_r" if mode != 'metric' else 'Spectral_r'
+    depth_colored = colorize_depth_maps(pred_disp[None, ...], 0, 1, cmap=cmap).squeeze()
+    depth_colored = (depth_colored * 255).astype(np.uint8)
+    
+    depth_image = Image.fromarray(depth_colored)
+    return depth_image
+
+# Gradio interface function
+def gradio_interface(image, mode='rel_depth'):
+    # Set device to CPU explicitly
+    device = torch.device("cpu")  # Force using CPU
+    model = load_model_by_name("depthanything", "your_checkpoint_path_here", device)
+
+    # Process image and return output
+    return process_image(image, model, device, mode)
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[gr.Image(type="pil"), gr.Dropdown(choices=['rel_depth', 'metric_depth', 'disparity'], label="Mode")],
+    outputs=gr.Image(type="pil"),
+    title="Depth Estimation Demo",
+    description="Upload an image to see the depth estimation results."
+)
+
+# Launch the Gradio interface
+iface.launch()