dev(narugo): update sizes

app.py

@@ -14,7 +14,7 @@ if __name__ == '__main__':
                     with gr.Column():
                         gr_face_input_image = gr.Image(type='pil', label='Original Image')
                         gr_face_model = gr.Dropdown(_FACE_MODELS, value=_DEFAULT_FACE_MODEL, label='Model')
-                        gr_face_infer_size = gr.Slider(480, 1600, value=1216, step=32, label='Max Infer Size')
+                        gr_face_infer_size = gr.Slider(480, 960, value=640, step=32, label='Max Infer Size')
                         with gr.Row():
                             gr_face_iou_threshold = gr.Slider(0.0, 1.0, 0.7, label='IOU Threshold')
                             gr_face_score_threshold = gr.Slider(0.0, 1.0, 0.25, label='Score Threshold')
@@ -38,7 +38,7 @@ if __name__ == '__main__':
                     with gr.Column():
                         gr_person_input_image = gr.Image(type='pil', label='Original Image')
                         gr_person_model = gr.Dropdown(_PERSON_MODELS, value=_DEFAULT_PERSON_MODEL, label='Model')
-                        gr_person_infer_size = gr.Slider(480, 1600, value=1216, step=32, label='Max Infer Size')
+                        gr_person_infer_size = gr.Slider(480, 960, value=640, step=32, label='Max Infer Size')
                         with gr.Row():
                             gr_person_iou_threshold = gr.Slider(0.0, 1.0, 0.5, label='IOU Threshold')
                             gr_person_score_threshold = gr.Slider(0.0, 1.0, 0.3, label='Score Threshold')
@@ -62,7 +62,7 @@ if __name__ == '__main__':
                     with gr.Column():
                         gr_manbit_input_image = gr.Image(type='pil', label='Original Image')
                         gr_manbit_model = gr.Dropdown(_MANBIT_MODELS, value=_DEFAULT_MANBIT_MODEL, label='Model')
-                        gr_manbit_infer_size = gr.Slider(480, 1600, value=1216, step=32, label='Max Infer Size')
+                        gr_manbit_infer_size = gr.Slider(480, 960, value=640, step=32, label='Max Infer Size')
                         with gr.Row():
                             gr_manbit_iou_threshold = gr.Slider(0.0, 1.0, 0.7, label='IOU Threshold')
                             gr_manbit_score_threshold = gr.Slider(0.0, 1.0, 0.25, label='Score Threshold')

face.py

@@ -26,18 +26,18 @@ def _open_face_detect_model(model_name):
 _LABELS = ['head']
 
 
-def detect_faces(image: ImageTyping, level: str = 's', max_infer_size=1216,
+def detect_faces(image: ImageTyping, model_name: str, max_infer_size=640,
                  conf_threshold: float = 0.25, iou_threshold: float = 0.7) \
         -> List[Tuple[Tuple[int, int, int, int], str, float]]:
     image = load_image(image, mode='RGB')
     new_image, old_size, new_size = _image_preprocess(image, max_infer_size)
 
     data = rgb_encode(new_image)[None, ...]
-    output, = _open_face_detect_model(level).run(['output0'], {'images': data})
+    output, = _open_face_detect_model(model_name).run(['output0'], {'images': data})
     return _data_postprocess(output[0], conf_threshold, iou_threshold, old_size, new_size, _LABELS)
 
 
-def _gr_detect_faces(image: ImageTyping, model_name: str, max_infer_size=1216,
+def _gr_detect_faces(image: ImageTyping, model_name: str, max_infer_size=640,
                      conf_threshold: float = 0.25, iou_threshold: float = 0.7):
     ret = detect_faces(image, model_name, max_infer_size, conf_threshold, iou_threshold)
     return detection_visualize(image, ret, _LABELS)

manbits.py

@@ -28,18 +28,18 @@ _LABELS = [
 ]
 
 
-def detect_manbits(image: ImageTyping, level: str = 'm', max_infer_size=1216,
+def detect_manbits(image: ImageTyping, model_name: str, max_infer_size=640,
                    conf_threshold: float = 0.25, iou_threshold: float = 0.7) \
         -> List[Tuple[Tuple[int, int, int, int], str, float]]:
     image = load_image(image, mode='RGB')
     new_image, old_size, new_size = _image_preprocess(image, max_infer_size)
 
     data = rgb_encode(new_image)[None, ...]
-    output, = _open_manbits_detect_model(level).run(['output0'], {'images': data})
+    output, = _open_manbits_detect_model(model_name).run(['output0'], {'images': data})
     return _data_postprocess(output[0], conf_threshold, iou_threshold, old_size, new_size, _LABELS)
 
 
-def _gr_detect_manbits(image: ImageTyping, model_name: str, max_infer_size=1216,
+def _gr_detect_manbits(image: ImageTyping, model_name: str, max_infer_size=640,
                        conf_threshold: float = 0.25, iou_threshold: float = 0.7):
     ret = detect_manbits(image, model_name, max_infer_size, conf_threshold, iou_threshold)
     return detection_visualize(image, ret, _LABELS)

person.py

@@ -27,17 +27,17 @@ def _open_person_detect_model(model_name):
 _LABELS = ['person']
 
 
-def detect_person(image: ImageTyping, level: str = 's', max_infer_size=1216,
+def detect_person(image: ImageTyping, model_name: str, max_infer_size=640,
                   conf_threshold: float = 0.3, iou_threshold: float = 0.5):
     image = load_image(image, mode='RGB')
     new_image, old_size, new_size = _image_preprocess(image, max_infer_size)
 
     data = rgb_encode(new_image)[None, ...]
-    output, = _open_person_detect_model(level).run(['output0'], {'images': data})
+    output, = _open_person_detect_model(model_name).run(['output0'], {'images': data})
     return _data_postprocess(output[0], conf_threshold, iou_threshold, old_size, new_size, _LABELS)
 
 
-def _gr_detect_person(image: ImageTyping, model_name: str, max_infer_size=1216,
+def _gr_detect_person(image: ImageTyping, model_name: str, max_infer_size=640,
                       conf_threshold: float = 0.3, iou_threshold: float = 0.5):
     ret = detect_person(image, model_name, max_infer_size, conf_threshold, iou_threshold)
     return detection_visualize(image, ret, _LABELS)

yolo_.py

@@ -65,7 +65,7 @@ def _yolo_nms(boxes, scores, thresh: float = 0.7) -> List[int]:
     return keep
 
 
-def _image_preprocess(image: Image.Image, max_infer_size: int = 1216, align: int = 32):
+def _image_preprocess(image: Image.Image, max_infer_size: int = 640, align: int = 32):
     old_width, old_height = image.width, image.height
     new_width, new_height = old_width, old_height
     r = max_infer_size / max(new_width, new_height)