Spaces:
Sleeping
Sleeping
File size: 1,588 Bytes
556d554 0a3ea02 556d554 0a3ea02 556d554 0a3ea02 556d554 0a3ea02 556d554 0a3ea02 556d554 0a3ea02 556d554 0a3ea02 556d554 0a3ea02 556d554 0a3ea02 125aaee 0a3ea02 1d13429 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
import os
from typing import Any
import gradio as gr
import torch
import numpy as np
from transformers import pipeline
from PIL import Image
# Load the depth estimation model from Hugging Face Transformers
depth_estimator = pipeline(task="depth-estimation", model="Intel/dpt-hybrid-midas")
def launch(input_image: Image.Image) -> Image.Image:
"""
Process an input image to estimate its depth map.
Args:
input_image: An image object as received from the Gradio interface.
Returns:
A PIL Image object representing the depth map.
"""
# Generate depth estimation from the input image
out = depth_estimator(input_image)
# Resize the prediction to match the input image size
prediction = torch.nn.functional.interpolate(
out["predicted_depth"].unsqueeze(1),
size=input_image.size[::-1], # PIL images use width x height, whereas torch uses height x width
mode="bicubic",
align_corners=False,
)
# Normalize the prediction to be in the range [0, 255]
output = prediction.squeeze().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
# Convert the numpy array back to a PIL image
depth = Image.fromarray(formatted)
return depth
# Define the Gradio interface
iface = gr.Interface(
fn=launch,
inputs=gr.Image(type='pil'),
outputs=gr.Image(type='pil'),
title="Depth Estimation",
description="Upload an image to estimate its depth map."
)
# Launch the Gradio app with sharing option enabled
if __name__ == "__main__":
iface.launch(share=True)
|