| import cv2 | |
| import numpy as np | |
| import gradio as gr | |
| import onnxruntime as rt | |
| from huggingface_hub import hf_hub_download | |
| def predict(img): | |
| img = img.astype(np.float32) / 255 | |
| s = 768 | |
| h, w = img.shape[:-1] | |
| h, w = (s, int(s * w / h)) if h > w else (int(s * h / w), s) | |
| ph, pw = s - h, s - w | |
| img_input = np.zeros([s, s, 3], dtype=np.float32) | |
| img_input[ph // 2:ph // 2 + h, pw // 2:pw // 2 + w] = cv2.resize(img, (w, h)) | |
| img_input = np.transpose(img_input, (2, 0, 1)) | |
| img_input = img_input[np.newaxis, :] | |
| pred = model.run(None, {"img": img_input})[0].item() | |
| return pred | |
| if __name__ == "__main__": | |
| model_path = hf_hub_download(repo_id="skytnt/anime-aesthetic", filename="model.onnx") | |
| model = rt.InferenceSession(model_path, providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) | |
| examples = [[f"examples/{x:02d}.jpg"] for x in range(0, 2)] | |
| app = gr.Interface(predict, gr.Image(label="input image"), gr.Number(label="score"),title="Anime Aesthetic Predict", | |
| allow_flagging="never", examples=examples, cache_examples=False) | |
| app.launch() | |