app.py

import os
import cv2
import imutils
import torch
import numpy as np
import gradio as gr



def parse_video(video_file):
    vs = cv2.VideoCapture(video_file)

    frames = []
    while True:
        (gotit, frame) = vs.read()
        if frame is not None:
            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            frames.append(frame)
        if not gotit:
            break

    return np.stack(frames)



@spaces.GPU
def cotracker_demo(
    input_video,
    grid_size: int = 10,
    tracks_leave_trace: bool = False,
):
    load_video = parse_video(input_video)
    load_video = torch.from_numpy(load_video).permute(0, 3, 1, 2)[None].float()

    import time

    def current_milli_time():
        return round(time.time() * 1000)

    filename = str(current_milli_time())
    
    return os.path.join(
        os.path.dirname(__file__), "results", f"{filename}.mp4"
    )





app = gr.Interface(
    title="🎨 CoTracker: It is Better to Track Together",
    description="<div style='text-align: left;'> \
    <p>Welcome to <a href='http://co-tracker.github.io' target='_blank'>CoTracker</a>! This space demonstrates point (pixel) tracking in videos. \
    Points are sampled on a regular grid and are tracked jointly. </p> \
    <p> To get started, simply upload your <b>.mp4</b> video in landscape orientation or click on one of the example videos to load them. The shorter the video, the faster the processing. We recommend submitting short videos of length <b>2-7 seconds</b>.</p> \
    <ul style='display: inline-block; text-align: left;'> \
        <li>The total number of grid points is the square of <b>Grid Size</b>.</li> \
        <li>Check <b>Visualize Track Traces</b> to visualize traces of all the tracked points. </li> \
    </ul> \
    <p style='text-align: left'>For more details, check out our <a href='https://github.com/facebookresearch/co-tracker' target='_blank'>GitHub Repo</a> ⭐</p> \
    </div>",
    fn=cotracker_demo,
    inputs=[
        gr.Video(type="file", label="Input video", interactive=True),
        gr.Slider(minimum=10, maximum=80, step=1, value=10, label="Number of tracks"),
    ],
    outputs=gr.Video(label="Video with predicted tracks"),
    cache_examples=True,
    allow_flagging=False,
)
app.queue(max_size=20, concurrency_count=1).launch(debug=True)