Update app.py

app.py

@@ -1,60 +1,86 @@
-from PIL import Image
-import numpy as np
-import io
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import pathlib
+
+import cv2
 import gradio as gr
+import huggingface_hub
+import insightface
+import numpy as np
+import onnxruntime as ort
 
-def encode_pil_to_bytes(pil_image: Image.Image, format: str, **params) -> bytes:
-    with io.BytesIO() as output_bytes:
-        pil_image.save(output_bytes, format=format, **params)
-        output_bytes.seek(0)  # Rewind the BytesIO object to the beginning
-        return output_bytes.read()
+TITLE = "insightface Person Detection"
+DESCRIPTION = "https://github.com/deepinsight/insightface/tree/master/examples/person_detection"
 
-def save_pil_to_cache(pil_image: Image.Image, format: str) -> bytes:
-    return encode_pil_to_bytes(pil_image, format)
+def load_model():
+    path = huggingface_hub.hf_hub_download("public-data/insightface", "models/scrfd_person_2.5g.onnx")
+    options = ort.SessionOptions()
+    options.intra_op_num_threads = 8
+    options.inter_op_num_threads = 8
+    session = ort.InferenceSession(
+        path, sess_options=options, providers=["CPUExecutionProvider", "CUDAExecutionProvider"]
+    )
+    model = insightface.model_zoo.retinaface.RetinaFace(model_file=path, session=session)
+    return model
 
-def extract_persons(image: np.ndarray, bboxes: np.ndarray) -> list[Image.Image]:
-    person_images = []
-    for bbox in bboxes:
+def detect_person(
+    img: np.ndarray, detector: insightface.model_zoo.retinaface.RetinaFace
+) -> tuple[np.ndarray, np.ndarray]:
+    bboxes, kpss = detector.detect(img)
+    bboxes = np.round(bboxes[:, :4]).astype(int)
+    kpss = np.round(kpss).astype(int)
+    kpss[:, :, 0] = np.clip(kpss[:, :, 0], 0, img.shape[1])
+    kpss[:, :, 1] = np.clip(kpss[:, :, 1], 0, img.shape[0])
+    vbboxes = bboxes.copy()
+    vbboxes[:, 0] = kpss[:, 0, 0]
+    vbboxes[:, 1] = kpss[:, 0, 1]
+    vbboxes[:, 2] = kpss[:, 4, 0]
+    vbboxes[:, 3] = kpss[:, 4, 1]
+    return bboxes, vbboxes
+
+def visualize(image: np.ndarray, bboxes: np.ndarray, vbboxes: np.ndarray) -> np.ndarray:
+    res = image.copy()
+    for i in range(bboxes.shape[0]):
+        bbox = bboxes[i]
+        vbbox = vbboxes[i]
         x1, y1, x2, y2 = bbox
-        person_image = image[y1:y2, x1:x2]  # Crop the detected person
-        person_pil_image = Image.fromarray(person_image).convert('RGB')  # Convert to RGB
-        person_images.append(person_pil_image)
-    return person_images
+        vx1, vy1, vx2, vy2 = vbbox
+        cv2.rectangle(res, (x1, y1), (x2, y2), (0, 255, 0), 1)
+        alpha = 0.8
+        color = (255, 0, 0)
+        for c in range(3):
+            res[vy1:vy2, vx1:vx2, c] = res[vy1:vy2, vx1:vx2, c] * alpha + color[c] * (1.0 - alpha)
+        cv2.circle(res, (vx1, vy1), 1, color, 2)
+        cv2.circle(res, (vx1, vy2), 1, color, 2)
+        cv2.circle(res, (vx2, vy1), 1, color, 2)
+        cv2.circle(res, (vx2, vy2), 1, color, 2)
+    return res
+
+detector = load_model()
+detector.prepare(-1, nms_thresh=0.5, input_size=(640, 640))
 
-def detect(image: np.ndarray) -> tuple[Image.Image, list[Image.Image]]:
+def detect(image: np.ndarray) -> np.ndarray:
     if image is None:
-        return None, []
+        return np.array([])  # Retourne une image vide si aucune image n'est fournie
 
     image = image[:, :, ::-1]  # RGB -> BGR
     bboxes, vbboxes = detect_person(image, detector)
     res = visualize(image, bboxes, vbboxes)
-    person_images = extract_persons(res, bboxes)
-    processed_image = Image.fromarray(res[:, :, ::-1], 'RGB')  # BGR -> RGB
-    return processed_image, person_images
-
-def process_image(image: Image.Image) -> tuple[Image.Image, list[Image.Image]]:
-    try:
-        np_image = np.array(image)
-        processed_image, person_images = detect(np_image)
-        return processed_image, person_images
-    except Exception as e:
-        print(f"An error occurred: {e}")
-        return None, []
-
-def build_gradio_interface():
-    with gr.Blocks() as demo:
-        gr.Markdown("## Person Detection App")
-
-        with gr.Row():
-            input_image = gr.Image(type="pil", label="Upload an Image")
-            output_image = gr.Image(type="pil", label="Processed Image")
-            gallery = gr.Gallery(label="Detected Persons")
+    return res[:, :, ::-1]  # BGR -> RGB
 
-        input_image.change(fn=process_image, inputs=input_image, outputs=[output_image, gallery])
+examples = sorted(pathlib.Path("images").glob("*.jpg"))
 
-    return demo
+demo = gr.Interface(
+    fn=detect,
+    inputs=gr.Image(label="Input", type="numpy"),
+    outputs=gr.Image(label="Output"),
+    examples=examples,
+    examples_per_page=30,
+    title=TITLE,
+    description=DESCRIPTION,
+)
 
-# Example usage
 if __name__ == "__main__":
-    demo = build_gradio_interface()
-    demo.launch()
+    demo.queue(max_size=10).launch()