|
|
|
CSV_PATH = "" |
|
VID_PATH = "" |
|
BATCH_SIZE = 5 |
|
CUDA_PATH = "/usr/local/cuda-12.3/" |
|
|
|
import subprocess |
|
import os |
|
import sys |
|
|
|
os.environ["CUDA_HOME"] = "/usr/local/cuda-12.3/" |
|
os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:5000' |
|
subprocess.run(['pip', 'install', '-e', 'GroundingDINO']) |
|
sys.path.append(os.path.join(os.getcwd(), "GroundingDINO")) |
|
sys.path.append(os.path.join(os.getcwd(), "segment_anything")) |
|
|
|
import gradio as gr |
|
from dino_sam import sam_dino_vid |
|
|
|
|
|
|
|
def run_sam_dino(input_vid, |
|
grounding_caption, |
|
box_threshold, |
|
text_threshold, |
|
fps_processed, |
|
scaling_factor, |
|
video_options): |
|
new_input_vid = input_vid.replace(" ", "_") |
|
os.rename(input_vid, new_input_vid) |
|
csv_path, vid_path = sam_dino_vid(vid_path=new_input_vid, |
|
text_prompt=grounding_caption, |
|
box_threshold=box_threshold, |
|
text_threshold=text_threshold, |
|
fps_processed=fps_processed, |
|
scaling_factor=(1/scaling_factor), |
|
video_options=video_options, |
|
batch_size=BATCH_SIZE) |
|
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) |
|
grounding_caption = gr.Textbox(label="What do you want to detect? (Multiple species should be separated by periods. i.e. 'baboon . chimpanzee .')") |
|
with gr.Accordion("Advanced Options", open=False): |
|
box_threshold = gr.Slider( |
|
label="Box Threshold", |
|
info="Adjust the threshold to change the sensitivity of the model, lower thresholds being more sensitive.", |
|
minimum=0.0, |
|
maximum=1.0, |
|
value=0.25, |
|
step=0.01 |
|
) |
|
text_threshold = gr.Slider( |
|
label="Text Threshold", minimum=0.0, maximum=1.0, value=0.25, step=0.01 |
|
) |
|
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=30, |
|
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=2, |
|
step=1 |
|
) |
|
video_options = gr.CheckboxGroup(choices=["Bounding boxes", "Masks"], |
|
label="Video Output Options", |
|
info="Select the options to display in the output video. Note: if masks are selected, runtime will increase.", |
|
value=["Bounding boxes"], |
|
interactive=True) |
|
|
|
|
|
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_file = gr.Files(label="CSV, Video Output", interactive=False) |
|
|
|
run_btn.click(fn=run_sam_dino, inputs=[input, grounding_caption, box_threshold, text_threshold, fps_processed, scaling_factor, video_options], outputs=[vid]) |
|
vid.change(fn=vid_download, outputs=download_file) |
|
|
|
gr.Examples( |
|
[["baboon_15s.mp4", "baboon", 0.25, 0.25, 1, 1, ["Bounding boxes", "Masks"]]], |
|
inputs = [input, grounding_caption, box_threshold, text_threshold, fps_processed, scaling_factor, video_options], |
|
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=False) |
