app.py

import gradio as gr
#import torch
import yolov7
import subprocess
import tempfile
import time
from pathlib import Path

import cv2
import gradio as gr



# Images
#torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg', 'zidane.jpg')
#torch.hub.download_url_to_file('https://raw.githubusercontent.com/obss/sahi/main/tests/data/small-vehicles1.jpeg', 'small-vehicles1.jpeg')
    
def image_fn(
    image: gr.inputs.Image = None,
    model_path: gr.inputs.Dropdown = None,
    image_size: gr.inputs.Slider = 640,
    conf_threshold: gr.inputs.Slider = 0.25,
    iou_threshold: gr.inputs.Slider = 0.45,
):
    """
    YOLOv7 inference function
    Args:
        image: Input image
        model_path: Path to the model
        image_size: Image size
        conf_threshold: Confidence threshold
        iou_threshold: IOU threshold
    Returns:
        Rendered image
    """

    model = yolov7.load(model_path, device="cpu", hf_model=True, trace=False)
    model.conf = conf_threshold
    model.iou = iou_threshold
    results = model([image], size=image_size)
    return results.render()[0]
  
  
        
def video_fn(model_path, video_file, conf_thres, iou_thres, start_sec, duration):
    model = yolov7.load(model_path, device="cpu", hf_model=True, trace=False)
    start_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec))
    end_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec + duration))

    suffix = Path(video_file).suffix

    clip_temp_file = tempfile.NamedTemporaryFile(suffix=suffix)
    subprocess.call(
        f"ffmpeg -y -ss {start_timestamp} -i {video_file} -to {end_timestamp} -c copy {clip_temp_file.name}".split()
    )

    # Reader of clip file
    cap = cv2.VideoCapture(clip_temp_file.name)

    # This is an intermediary temp file where we'll write the video to
    # Unfortunately, gradio doesn't play too nice with videos rn so we have to do some hackiness
    # with ffmpeg at the end of the function here.
    with tempfile.NamedTemporaryFile(suffix=".mp4") as temp_file:
        out = cv2.VideoWriter(temp_file.name, cv2.VideoWriter_fourcc(*"MP4V"), 30, (1280, 720))

        num_frames = 0
        max_frames = duration * 30
        while cap.isOpened():
            try:
                ret, frame = cap.read()
                if not ret:
                    break
            except Exception as e:
                print(e)
                continue
            print("FRAME DTYPE", type(frame))
            out.write(model(frame, conf_thres, iou_thres))
            num_frames += 1
            print("Processed {} frames".format(num_frames))
            if num_frames == max_frames:
                break

        out.release()

        # Aforementioned hackiness
        out_file = tempfile.NamedTemporaryFile(suffix="out.mp4", delete=False)
        subprocess.run(f"ffmpeg -y -loglevel quiet -stats -i {temp_file.name} -c:v libx264 {out_file.name}".split())

    return out_file.name

image_interface = gr.Interface(
    fn=image_fn,
    inputs=[
    gr.inputs.Image(type="pil", label="Input Image"),
    gr.inputs.Dropdown(
        choices=[
            "alshimaa/model_baseline",
            "alshimaa/model_yolo7",
            #"kadirnar/yolov7-v0.1",
        ],
        default="alshimaa/model_baseline",
        label="Model",
    )
    #gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size")
    #gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"),
    #gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold")
],
    outputs=gr.outputs.Image(type="filepath", label="Output Image"),
    title="Smart Environmental Eye (SEE)",
    examples=[['image1.jpg', 'alshimaa/model_yolo7', 640, 0.25, 0.45], ['image2.jpg', 'alshimaa/model_yolo7', 640, 0.25, 0.45], ['image3.jpg', 'alshimaa/model_yolo7', 640, 0.25, 0.45]],
    cache_examples=True,
    theme='huggingface',
)


video_interface = gr.Interface(
    fn=video_fn,
    inputs=[
        gr.Video(type="file"),
        gr.inputs.Dropdown(
        choices=[
            "alshimaa/model_baseline",
            "alshimaa/model_yolo7",
            #"kadirnar/yolov7-v0.1",
        ],
        default="alshimaa/model_baseline",
        label="Model",
    ),
    ],
    outputs=gr.outputs.Video(type="filepath", format="mp4", label="Output Video"),
    # examples=[
    #     ["video.mp4", 0.25, 0.45, 0, 2],
       
    # ],
    title="Smart Environmental Eye (SEE)",
    cache_examples=True,
    theme='huggingface',
   
)

if __name__ == "__main__":
    gr.TabbedInterface(
        [image_interface, video_interface],
        ["Run on Images", "Run on Videos"],
    ).launch()

# import subprocess
# import tempfile
# import time
# from pathlib import Path

# import cv2
# import gradio as gr

# from inferer import Inferer

# pipeline = Inferer("alshimaa/model_yolo7", device='cuda')


# def fn_image(image, conf_thres, iou_thres):
#     return pipeline(image, conf_thres, iou_thres)


# def fn_video(video_file, conf_thres, iou_thres, start_sec, duration):
#     start_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec))
#     end_timestamp = time.strftime("%H:%M:%S", time.gmtime(start_sec + duration))

#     suffix = Path(video_file).suffix

#     clip_temp_file = tempfile.NamedTemporaryFile(suffix=suffix)
#     subprocess.call(
#         f"ffmpeg -y -ss {start_timestamp} -i {video_file} -to {end_timestamp} -c copy {clip_temp_file.name}".split()
#     )

#     # Reader of clip file
#     cap = cv2.VideoCapture(clip_temp_file.name)

#     # This is an intermediary temp file where we'll write the video to
#     # Unfortunately, gradio doesn't play too nice with videos rn so we have to do some hackiness
#     # with ffmpeg at the end of the function here.
#     with tempfile.NamedTemporaryFile(suffix=".mp4") as temp_file:
#         out = cv2.VideoWriter(temp_file.name, cv2.VideoWriter_fourcc(*"MP4V"), 30, (1280, 720))

#         num_frames = 0
#         max_frames = duration * 30
#         while cap.isOpened():
#             try:
#                 ret, frame = cap.read()
#                 if not ret:
#                     break
#             except Exception as e:
#                 print(e)
#                 continue
#             print("FRAME DTYPE", type(frame))
#             out.write(pipeline(frame, conf_thres, iou_thres))
#             num_frames += 1
#             print("Processed {} frames".format(num_frames))
#             if num_frames == max_frames:
#                 break

#         out.release()

#         # Aforementioned hackiness
#         out_file = tempfile.NamedTemporaryFile(suffix="out.mp4", delete=False)
#         subprocess.run(f"ffmpeg -y -loglevel quiet -stats -i {temp_file.name} -c:v libx264 {out_file.name}".split())

#     return out_file.name


# image_interface = gr.Interface(
#     fn=fn_image,
#     inputs=[
#         "image",
#         gr.Slider(0, 1, value=0.5, label="Confidence Threshold"),
#         gr.Slider(0, 1, value=0.5, label="IOU Threshold"),
#     ],
#     outputs=gr.Image(type="file"),
#     examples=[["image1.jpg", 0.5, 0.5], ["image2.jpg", 0.25, 0.45], ["image3.jpg", 0.25, 0.45]],
#     title="Smart Environmental Eye (SEE)",
#     allow_flagging=False,
#     allow_screenshot=False,
# )

# video_interface = gr.Interface(
#     fn=fn_video,
#     inputs=[
#         gr.Video(type="file"),
#         gr.Slider(0, 1, value=0.25, label="Confidence Threshold"),
#         gr.Slider(0, 1, value=0.45, label="IOU Threshold"),
#         gr.Slider(0, 10, value=0, label="Start Second", step=1),
#         gr.Slider(0, 10 if pipeline.device.type != 'cpu' else 3, value=4, label="Duration", step=1),
#     ],
#     outputs=gr.Video(type="file", format="mp4"),
#     # examples=[
#     #     ["video.mp4", 0.25, 0.45, 0, 2],
       
#     # ],
#     title="Smart Environmental Eye (SEE)",
#     allow_flagging=False,
#     allow_screenshot=False,
# )



# if __name__ == "__main__":
#     gr.TabbedInterface(
#         [image_interface, video_interface],
#         ["Run on Images", "Run on Videos"],
#     ).launch()