File size: 4,503 Bytes
bfa3aba 51d37d8 1b875e8 bfa3aba c032acd bfa3aba c032acd bfa3aba 6209508 |
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 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
import os
import sys
# set CUDA_HOME
os.environ["CUDA_HOME"] = "/usr/local/cuda-12.3/"
import gradio as gr
from tqdm import tqdm
import cv2
import os
import numpy as np
import pandas as pd
import torch
from typing import Tuple
from PIL import Image
from owl_core import owl_full_video
def run_owl(input_vid,
text_prompt,
confidence_threshold,
fps_processed,
scaling_factor
):
# new_input_vid = input_vid.replace(" ", "_")
# os.rename(input_vid, new_input_vid)
print(input_vid)
csv_path, vid_path = owl_full_video(input_vid,
text_prompt,
confidence_threshold,
fps_processed=fps_processed,
scaling_factor=scaling_factor)
global CSV_PATH
CSV_PATH = csv_path
global VID_PATH
VID_PATH = vid_path
return vid_path
def vid_download():
"""
"""
print(CSV_PATH, VID_PATH)
return [CSV_PATH, VID_PATH]
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 align="center" style="font-size:xxx-large">🦍 Primate Detection</h1>
"""
)
with gr.Row():
with gr.Column():
input = gr.Video(label="Input Video", interactive=True)
text_prompt = gr.Textbox(label="What do you want to detect? (Multiple species should be separated by commas")
with gr.Accordion("Advanced Options", open=False):
conf_threshold = gr.Slider(
label="Confidence Threshold",
info="Adjust the threshold to change the sensitivity of the model, lower thresholds being more sensitive.",
minimum=0.0,
maximum=1.0,
value=0.3,
step=0.05
)
fps_processed = gr.Slider(
label="Frame Detection Rate",
info="Adjust the frame detection rate. I.e. a value of 120 will run detection every 120 frames, a value of 1 will run detection on every frame. Note: the lower the number the slower the processing time.",
minimum=1,
maximum=120,
value=1,
step=1)
scaling_factor = gr.Slider(
label="Downsample Factor",
info="Adjust the downsample factor. Note: the higher the number the faster the processing time but lower the accuracy.",
minimum=1,
maximum=5,
value=4,
step=1
)
# TODO: Make button visible only after a file has been uploaded
run_btn = gr.Button(value="Run Detection", visible=True)
with gr.Column():
vid = gr.Video(label="Output Video", height=350, interactive=False, visible=True)
# download_btn = gr.Button(value="Generate Download", visible=True)
download_file = gr.Files(label="CSV, Video Output", interactive=False)
run_btn.click(fn=run_owl, inputs=[input, text_prompt, conf_threshold, fps_processed, scaling_factor, ], outputs=[vid])
vid.change(fn=vid_download, outputs=download_file)
# gr.Examples(
# [["baboon_15s.mp4", "baboon", 0.25, 0.25, 1, 1]],
# inputs = [input, text_prompt, conf_threshold, fps_processed, scaling_factor],
# outputs = [vid],
# fn=run_sam_dino,
# cache_examples=True,
# label='Example'
# )
gr.DuplicateButton()
gr.Markdown(
"""
## Frequently Asked Questions
##### How can I run the interface on my own computer?
By clicking on the three dots on the top right corner of the interface, you will be able to clone the repository or run it with a Docker image on your local machine. \
For local machine setup instructions please check the README file.
##### The video is very slow to process, how can I speed it up?
You can speed up the processing by adjusting the frame detection rate in the advanced options. The lower the number the slower the processing time. Choosing only\
bounding boxes will make the processing faster. You can also duplicate the space using the Duplicate Button and choose a different GPU which will make the processing faster.
"""
)
demo.launch(share=True) |