support show detection result, support get video resolution automatically

demo/mask_detection/python/README.md

@@ -54,7 +54,7 @@ python infer.py --models_dir=/path/to/models --img_paths=/path/to/images --video
 | img_paths |img_paths/video_path 二选一|需要预测的图片目录 |
 | video_path |img_paths/video_path 二选一|需要预测的视频目录|
 | use_camera |No|是否打开摄像头进行预测，默认为False |
-| open_imshow |No|是否进行检测结果实时绘图，默认为False |
+| open_imshow |No|是否对视频的检测结果实时绘图，默认为False |
 | use_gpu |No|是否GPU，默认为False|
 
 说明：

demo/mask_detection/python/infer.py

@@ -33,24 +33,27 @@ import argparse
 
 def parse_args():
     parser = argparse.ArgumentParser('mask detection.')
-    parser.add_argument(
-        '--models_dir', type=str, default='', help='path of models.')
-    parser.add_argument(
-        '--img_paths', type=str, default='', help='path of images')
-    parser.add_argument(
-        '--video_path', type=str, default='', help='path of video.')
-    parser.add_argument(
-        '--use_camera',
+    parser.add_argument('--models_dir',
+                        type=str,
+                        default='',
+                        help='path of models.')
+    parser.add_argument('--img_paths',
+                        type=str,
+                        default='',
+                        help='path of images')
+    parser.add_argument('--video_path',
+                        type=str,
+                        default='',
+                        help='path of video.')
+    parser.add_argument('--use_camera',
                         type=bool,
                         default=False,
                         help='switch detect video or camera, default:video.')
-    parser.add_argument(
-        '--open_imshow',
+    parser.add_argument('--open_imshow',
                         type=bool,
                         default=False,
-        help='visualize results in real time.')
-    parser.add_argument(
-        '--use_gpu',
+                        help='visualize video detection results in real time.')
+    parser.add_argument('--use_gpu',
                         type=bool,
                         default=False,
                         help='switch cpu/gpu, default:cpu.')
@@ -105,8 +108,7 @@ class MaskClassifier:
         h, w = self.EVAL_SIZE[1], self.EVAL_SIZE[0]
         inputs = []
         for face in faces:
-            im = cv2.resize(
-                face.rect_data, (128, 128),
+            im = cv2.resize(face.rect_data, (128, 128),
                             fx=0,
                             fy=0,
                             interpolation=cv2.INTER_CUBIC)
@@ -149,8 +151,10 @@ class FaceDetector:
 
     def Preprocess(self, image, shrink):
         h, w = int(image.shape[1] * shrink), int(image.shape[0] * shrink)
-        im = cv2.resize(
-            image, (h, w), fx=0, fy=0, interpolation=cv2.INTER_CUBIC)
+        im = cv2.resize(image, (h, w),
+                        fx=0,
+                        fy=0,
+                        interpolation=cv2.INTER_CUBIC)
         # HWC -> CHW
         im = im.swapaxes(1, 2)
         im = im.swapaxes(0, 1)
@@ -190,15 +194,13 @@ class FaceDetector:
 
 
 def predict_images(args):
-    detector = FaceDetector(
-        model_dir=args.models_dir + '/pyramidbox_lite/',
+    detector = FaceDetector(model_dir=args.models_dir + '/pyramidbox_lite/',
                             mean=[104.0, 177.0, 123.0],
                             scale=[0.007843, 0.007843, 0.007843],
                             use_gpu=args.use_gpu,
                             threshold=0.7)
 
-    classifier = MaskClassifier(
-        model_dir=args.models_dir + '/mask_detector/',
+    classifier = MaskClassifier(model_dir=args.models_dir + '/mask_detector/',
                                 mean=[0.5, 0.5, 0.5],
                                 scale=[1.0, 1.0, 1.0],
                                 use_gpu=args.use_gpu)
@@ -227,15 +229,13 @@ def predict_video(args, im_shape=(1920, 1080), use_camera=False):
         capture = cv2.VideoCapture(0)
     else:
         capture = cv2.VideoCapture(args.video_path)
-    detector = FaceDetector(
-        model_dir=args.models_dir + '/pyramidbox_lite/',
+    detector = FaceDetector(model_dir=args.models_dir + '/pyramidbox_lite/',
                             mean=[104.0, 177.0, 123.0],
                             scale=[0.007843, 0.007843, 0.007843],
                             use_gpu=args.use_gpu,
                             threshold=0.7)
 
-    classifier = MaskClassifier(
-        model_dir=args.models_dir + '/mask_detector/',
+    classifier = MaskClassifier(model_dir=args.models_dir + '/mask_detector/',
                                 mean=[0.5, 0.5, 0.5],
                                 scale=[1.0, 1.0, 1.0],
                                 use_gpu=args.use_gpu)
@@ -248,8 +248,8 @@ def predict_video(args, im_shape=(1920, 1080), use_camera=False):
     width = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
     height = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
     fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    writer = cv2.VideoWriter(
-        os.path.join(path, 'result.mp4'), fourcc, fps, (width, height))
+    writer = cv2.VideoWriter(os.path.join(path, 'result.mp4'), fourcc, fps,
+                             (width, height))
     import time
     start_time = time.time()
     index = 0