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

app_title = "Clash of Clans Object Detection"
models_ids = ['keremberke/yolov5n-clash-of-clans', 'keremberke/yolov5s-clash-of-clans', 'keremberke/yolov5m-clash-of-clans']
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/clash-of-clans-object-detection'>huggingface.co/keremberke/clash-of-clans-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/IMG_1879_jpg.rf.c0e9cd93962f7cf2df6fbeef63ab6ed9.jpg', 0.25, 'keremberke/yolov5m-clash-of-clans'], ['test_images/IMG_1906_jpg.rf.e3d1ef9a4c55d6576e95ba057984d204.jpg', 0.25, 'keremberke/yolov5m-clash-of-clans'], ['test_images/IMG_1931_jpg.rf.16f42f6d309c3de5661625af454aeb0c.jpg', 0.25, 'keremberke/yolov5m-clash-of-clans'], ['test_images/IMG_2016_jpg.rf.6013a2119e90b56bb2a07d83954dc637.jpg', 0.25, 'keremberke/yolov5m-clash-of-clans'], ['test_images/IMG_2023_jpg.rf.01d180bc2ed3d5bab7b0026cd8e4c09a.jpg', 0.25, 'keremberke/yolov5m-clash-of-clans'], ['test_images/IMG_2034_jpg.rf.40ab3489487d018d0112f49622f0f9a0.jpg', 0.25, 'keremberke/yolov5m-clash-of-clans']]


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)