Update app.py

app.py

@@ -1,163 +1,29 @@
-import os
-os.system("pip freeze")
-import spaces
-
 import gradio as gr
-import torch as torch
 from diffusers import MarigoldDepthPipeline, DDIMScheduler
-from gradio_dualvision import DualVisionApp
-from huggingface_hub import login
+import torch
 from PIL import Image
 
 CHECKPOINT = "developy/ApDepth"
 
-if "HF_TOKEN_LOGIN" in os.environ:
-    login(token=os.environ["HF_TOKEN_LOGIN"])
-
 device = "cpu"
-dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
+dtype = torch.float32
 
 pipe = MarigoldDepthPipeline.from_pretrained(CHECKPOINT)
 pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
 pipe = pipe.to(device=device, dtype=dtype)
-try:
-    import xformers
-    pipe.enable_xformers_memory_efficient_attention()
-except:
-    pass
-
-
-class MarigoldDepthApp(DualVisionApp):
-    DEFAULT_SEED = 2024
-    DEFAULT_ENSEMBLE_SIZE = 1
-    DEFAULT_DENOISE_STEPS = 1
-    DEFAULT_PROCESSING_RES = 768
-
-    def make_header(self):
-        gr.Markdown(
-            """
-            <h2><a href="https://huggingface.co/spaces/prs-eth/marigold" style="color: black;">Marigold Depth Estimation</a></h2>
-            """
-        )
-        with gr.Row(elem_classes="remove-elements"):
-            gr.Markdown(
-                f"""
-                <p align="center">
-                <a title="Website" href="https://marigoldcomputervision.github.io/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%E2%99%A5%20Project%20-Website-blue">
-                </a>
-                <a title="diffusers" href="https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%F0%9F%A7%A8%20Read_diffusers-Tutorial-yellow?labelColor=green">
-                </a>
-                <a title="arXiv" href="https://arxiv.org/abs/2505.09358" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%F0%9F%93%84%20Read%20-Paper-AF3436">
-                </a>
-                <a title="Github" href="https://github.com/prs-eth/marigold" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/github/stars/prs-eth/marigold?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="badge-github-stars">
-                </a>
-                <a title="Image Normals" href="https://huggingface.co/spaces/prs-eth/marigold-normals" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Image%20Normals%20-Demo-yellow" alt="imagedepth">
-                </a>
-                <a title="Image Intrinsics" href="https://huggingface.co/spaces/prs-eth/marigold-iid" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Image%20Intrinsics%20-Demo-yellow" alt="imagedepth">
-                </a>
-                <a title="LiDAR Depth" href="https://huggingface.co/spaces/prs-eth/marigold-dc" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20LiDAR%20Depth%20-Demo-yellow" alt="imagedepth">
-                </a>
-                <a title="Video Depth" href="https://huggingface.co/spaces/prs-eth/rollingdepth" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Video%20Depth%20-Demo-yellow" alt="videodepth">
-                </a>
-                <a title="Depth-to-3D" href="https://huggingface.co/spaces/prs-eth/depth-to-3d-print" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Depth--to--3D%20-Demo-yellow" alt="depthto3d">
-                </a>
-                <a title="Social" href="https://twitter.com/antonobukhov1" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
-                    <img src="https://shields.io/twitter/follow/:?label=Subscribe%20for%20updates!" alt="social">
-                </a>
-                </p>                    
-                <p align="center" style="margin-top: 0px;">
-                    Upload a photo or select an example below to compute depth maps in real time.
-                    Use the slider to reveal areas of interest.
-                    Use the radio-buttons to switch between modalities.
-                    Check our other demo badges above for new or relocated functionality.
-                </p>
-                """
-        )
-
-    def build_user_components(self):
-        with gr.Column():
-            ensemble_size = gr.Slider(
-                label="Ensemble size",
-                minimum=1,
-                maximum=10,
-                step=1,
-                value=self.DEFAULT_ENSEMBLE_SIZE,
-            )
-            denoise_steps = gr.Slider(
-                label="Number of denoising steps",
-                minimum=1,
-                maximum=20,
-                step=1,
-                value=self.DEFAULT_DENOISE_STEPS,
-            )
-            processing_res = gr.Radio(
-                [
-                    ("Native", 0),
-                    ("Recommended", 768),
-                ],
-                label="Processing resolution",
-                value=self.DEFAULT_PROCESSING_RES,
-            )
-        return {
-            "ensemble_size": ensemble_size,
-            "denoise_steps": denoise_steps,
-            "processing_res": processing_res,
-        }
-
-    def process(self, image_in: Image.Image, **kwargs):
-        ensemble_size = kwargs.get("ensemble_size", self.DEFAULT_ENSEMBLE_SIZE)
-        denoise_steps = kwargs.get("denoise_steps", self.DEFAULT_DENOISE_STEPS)
-        processing_res = kwargs.get("processing_res", self.DEFAULT_PROCESSING_RES)
-        generator = torch.Generator(device=device).manual_seed(self.DEFAULT_SEED)
-
-        pipe_out = pipe(
-            image_in,
-            ensemble_size=ensemble_size,
-            num_inference_steps=denoise_steps,
-            processing_resolution=processing_res,
-            batch_size=1 if processing_res == 0 else 2,
-            output_uncertainty=ensemble_size >= 3,
-            generator=generator,
-        )
-
-        depth_vis = pipe.image_processor.visualize_depth(pipe_out.prediction)[0]
-        depth_16bit = pipe.image_processor.export_depth_to_16bit_png(pipe_out.prediction)[0]
-
-        out_modalities = {
-            "Depth Visualization": depth_vis,
-            "Depth 16-bit": depth_16bit,
-        }
-        if ensemble_size >= 3:
-            uncertainty = pipe.image_processor.visualize_uncertainty(pipe_out.uncertainty)[0]
-            out_modalities["Uncertainty"] = uncertainty
-
-        out_settings = {
-            "ensemble_size": ensemble_size,
-            "denoise_steps": denoise_steps,
-            "processing_res": processing_res,
-        }
-        return out_modalities, out_settings
-
 
-with MarigoldDepthApp(
-    title="ApDepth",
-    examples_path="files",
-    examples_per_page=12,
-    squeeze_canvas=True,
-    spaces_zero_gpu_enabled=True,
-) as demo:
-    demo.queue(
-        api_open=False,
-    ).launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-    )
+def predict(image: Image.Image):
+    out = pipe(image)
+    depth_vis = pipe.image_processor.visualize_depth(out.prediction)[0]
+    return depth_vis
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil", label="Input Image"),
+    outputs=gr.Image(type="pil", label="Depth Map"),
+    title="ApDepth Demo",
+    description="Monocular Depth Estimation based on Marigold"
+)
+
+if __name__ == "__main__":
+    demo.launch()