import json
import gradio as gr
import yolov5
from PIL import Image
from huggingface_hub import hf_hub_download

app_title = "Construction Safety Object Detection"
models_ids = ['keremberke/yolov5n-construction-safety', 'keremberke/yolov5s-construction-safety', 'keremberke/yolov5m-construction-safety']
article = f"<p style='text-align: center'> <a href='https://huggingface.co/{models_ids[-1]}'>huggingface.co/{models_ids[-1]}</a> | <a href='https://huggingface.co/keremberke/construction-safety-object-detection'>huggingface.co/keremberke/construction-safety-object-detection</a> | <a href='https://github.com/keremberke/awesome-yolov5-models'>awesome-yolov5-models</a> </p>"

current_model_id = models_ids[-1]
model = yolov5.load(current_model_id)

examples = [['test_images/-1079-_png_jpg.rf.eae5c731d79f3b240ce6b5ae84589e49.jpg', 0.25, 'keremberke/yolov5m-construction-safety'], ['test_images/construction-1-_mp4-147_jpg.rf.6593d553fd4c445c810aedcc8f9bf5b0.jpg', 0.25, 'keremberke/yolov5m-construction-safety'], ['test_images/construction-1023-_jpg.rf.10ea2a0d607573c1c90d7c38bacf2f04.jpg', 0.25, 'keremberke/yolov5m-construction-safety'], ['test_images/construction-3-_mp4-21_jpg.rf.f90d04a7fe8ee4d1d3331050b4e64e1b.jpg', 0.25, 'keremberke/yolov5m-construction-safety'], ['test_images/image_140_jpg.rf.e7727a5a4bd52d812adbd6f5d2fea6d9.jpg', 0.25, 'keremberke/yolov5m-construction-safety'], ['test_images/Mask-detector1_mov-46_jpg.rf.2122d830c41384952c89ef8cd23734ca.jpg', 0.25, 'keremberke/yolov5m-construction-safety']]


def predict(image, threshold=0.25, model_id=None):
    # update model if required
    global current_model_id
    global model
    if model_id != current_model_id:
        model = yolov5.load(model_id)
        current_model_id = model_id

    # get model input size
    config_path = hf_hub_download(repo_id=model_id, filename="config.json")
    with open(config_path, "r") as f:
        config = json.load(f)
    input_size = config["input_size"]

    # perform inference
    model.conf = threshold
    results = model(image, size=input_size)
    numpy_image = results.render()[0]
    output_image = Image.fromarray(numpy_image)
    return output_image


gr.Interface(
    title=app_title,
    description="Created by 'keremberke'",
    article=article,
    fn=predict,
    inputs=[
        gr.Image(type="pil"),
        gr.Slider(maximum=1, step=0.01, value=0.25),
        gr.Dropdown(models_ids, value=models_ids[-1]),
    ],
    outputs=gr.Image(type="pil"),
    examples=examples,
    cache_examples=True if examples else False,
).launch(enable_queue=True)