import mediapy import gradio as gr from utils import load_image from interpolator import Interpolator, interpolate_recursively path = "./smoot.mp4" interpolator = Interpolator() def predict(image_a, image_b): image1 = load_image(image_a) image2 = load_image(image_b) input_frames = [image1, image2] frames = list(interpolate_recursively(input_frames, interpolator)) mediapy.write_video(path, frames, fps=30) return path footer = r"""
Demo for DELF
""" coffe = r"""
""" with gr.Blocks(title="DELF") as app: gr.HTML("

Match images using DELF

") gr.HTML("

Neural network and logic for processing images to identify keypoints and their " "descriptors.

") with gr.Row(equal_height=False): with gr.Column(): input_img_a = gr.Image(type="filepath", label="Input image A") input_img_b = gr.Image(type="filepath", label="Input image B") run_btn = gr.Button(variant="primary") with gr.Column(): output_img = gr.Video(format="mp4", label="Interpolate video") gr.ClearButton(components=[input_img_a, input_img_b, output_img], variant="stop") run_btn.click(predict, [input_img_a, input_img_b], [output_img]) with gr.Row(): blobs_a = [[f"examples/image_a/{x:02d}.jpg"] for x in range(1, 2)] examples_a = gr.Dataset(components=[input_img_a], samples=blobs_a) examples_a.click(lambda x: x[0], [examples_a], [input_img_a]) with gr.Row(): blobs_b = [[f"examples/image_b/{x:02d}.jpg"] for x in range(1, 2)] examples_b = gr.Dataset(components=[input_img_b], samples=blobs_b) examples_b.click(lambda x: x[0], [examples_b], [input_img_b]) with gr.Row(): gr.HTML(footer) with gr.Row(): gr.HTML(coffe) app.launch(share=False, debug=True, show_error=True) app.queue()