fix coding style

contrib/RealTimeHumanSeg/python/infer.py

@@ -22,7 +22,7 @@ import cv2
 import paddle.fluid as fluid
 
 
-def LoadModel(model_dir, use_gpu=False):
+def load_model(model_dir, use_gpu=False):
     """
     Load model files and init paddle predictor
     """
@@ -41,78 +41,94 @@ def LoadModel(model_dir, use_gpu=False):
 
 
 class HumanSeg:
+    """
+    Human Segmentation Class
+    """
     def __init__(self, model_dir, mean, scale, eval_size, use_gpu=False):
         self.mean = np.array(mean).reshape((3, 1, 1))
         self.scale = np.array(scale).reshape((3, 1, 1))
         self.eval_size = eval_size
-        self.predictor = LoadModel(model_dir, use_gpu)
-
-    def Preprocess(self, image):
-        im = cv2.resize(image,
-                        self.eval_size,
-                        fx=0,
-                        fy=0,
-                        interpolation=cv2.INTER_LINEAR)
+        self.predictor = load_model(model_dir, use_gpu)
+
+    def preprocess(self, image):
+        """
+        preprocess image: hwc_rgb to chw_bgr
+        """
+        img_mat = cv2.resize(
+            image, self.eval_size, fx=0, fy=0, interpolation=cv2.INTER_CUBIC)
         # HWC -> CHW
-        im = im.swapaxes(1, 2)
-        im = im.swapaxes(0, 1)
+        img_mat = img_mat.swapaxes(1, 2)
+        img_mat = img_mat.swapaxes(0, 1)
         # Convert to float
-        im = im[:, :, :].astype('float32')
-        # im  = (im - mean) * scale
-        im = im - self.mean
-        im = im * self.scale
-        im = im[np.newaxis, :, :, :]
-        return im
-
-    def Postprocess(self, image, output_data):
+        img_mat = img_mat[:, :, :].astype('float32')
+        # img_mat = (img_mat - mean) * scale
+        img_mat = img_mat - self.mean
+        img_mat = img_mat * self.scale
+        img_mat = img_mat[np.newaxis, :, :, :]
+        return img_mat
+
+    def postprocess(self, image, output_data):
+        """
+        postprocess result: merge background with segmentation result
+        """
         mask = output_data[0, 1, :, :]
         mask = cv2.resize(mask, (image.shape[1], image.shape[0]))
         scoremap = np.repeat(mask[:, :, np.newaxis], 3, axis=2)
-        bg = np.ones_like(scoremap) * 255
-        merge_im = (scoremap * image + (1 - scoremap) * bg).astype(np.uint8)
+        bg_im = np.ones_like(scoremap) * 255
+        merge_im = (scoremap * image + (1 - scoremap) * bg_im).astype(np.uint8)
         return merge_im
 
-    def Predict(self, image):
+    def run_predict(self, image):
+        """
+        run predict: return segmentation image mat
+        """
         ori_im = image.copy()
-        im = self.Preprocess(image)
-        im_tensor = fluid.core.PaddleTensor(im.copy().astype('float32'))
+        im_mat = self.preprocess(ori_im)
+        im_tensor = fluid.core.PaddleTensor(im_mat.copy().astype('float32'))
         output_data = self.predictor.run([im_tensor])[0]
         output_data = output_data.as_ndarray()
-        return self.Postprocess(image, output_data)
+        return self.postprocess(image, output_data)
+
+
+def predict_image(seg, image_path):
+    """
+    Do Predicting on a image
+    """
+    img_mat = cv2.imread(image_path)
+    img_mat = seg.run_predict(img_mat)
+    cv2.imwrite('result.jpeg', img_mat)
 
-# Do Predicting on a image
-def PredictImage(seg, image_path):
-    im = cv2.imread(input_path)
-    im = seg.Predict(im)
-    cv2.imwrite('result.jpeg', im)
 
-# Do Predicting on a video
-def PredictVideo(seg, video_path):
+def predict_video(seg, video_path):
+    """
+    Do Predicting on a video
+    """
     cap = cv2.VideoCapture(video_path)
-    if cap.isOpened() == False:
+    if not cap.isOpened():
         print("Error opening video stream or file")
         return
-    w = cap.get(cv2.CAP_PROP_FRAME_WIDTH)
-    h = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
     fps = cap.get(cv2.CAP_PROP_FPS)
     # Result Video Writer
     out = cv2.VideoWriter('result.avi',
-                          cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'),
-                          fps,
-                          (int(w), int(h)))
+                          cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), fps,
+                          (width, height))
     # Start capturing from video
     while cap.isOpened():
         ret, frame = cap.read()
-        if ret == True:
-            im = seg.Predict(frame)
-            out.write(im)
+        if ret:
+            img_mat = seg.run_predict(frame)
+            out.write(img_mat)
         else:
             break
     cap.release()
     out.release()
 
-# Do Predicting on a camera video stream
-def PredictCamera(seg):
+def predict_camera(seg):
+    """
+    Do Predicting on a camera video stream
+    """
     cap = cv2.VideoCapture(0)
     if not cap.isOpened():
         print("Error opening video stream or file")
@@ -121,8 +137,8 @@ def PredictCamera(seg):
     while cap.isOpened():
         ret, frame = cap.read()
         if ret:
-            im = seg.Predict(frame)
-            cv2.imshow('Frame', im)
+            img_mat = seg.run_predict(frame)
+            cv2.imshow('Frame', img_mat)
             if cv2.waitKey(1) & 0xFF == ord('q'):
                 break
         else:
@@ -137,16 +153,17 @@ def main(argv):
         print('Usage: python infer.py /path/to/model/ /path/to/video')
         return
 
-    model_dir = argv[1]
-    input_path = argv[2]
-    use_gpu = int(argv[3]) if len(argv) >= 4 else 0
+    model_dir = sys.argv[1]
+    input_path = sys.argv[2]
+    use_gpu = int(sys.argv[3]) if len(sys.argv) >= 4 else 0
     # Init model
     mean = [104.008, 116.669, 122.675]
     scale = [1.0, 1.0, 1.0]
     eval_size = (192, 192)
     seg = HumanSeg(model_dir, mean, scale, eval_size, use_gpu)
     # Run Predicting on a video and result will be saved as result.avi
-    PredictCamera(seg)
+    # predict_camera(seg)
+    predict_video(seg, input_path)
 
 
 if __name__ == "__main__":