add remove duplicate frames in DAIN

applications/DAIN/my_args.py

@@ -90,4 +90,7 @@ parser.add_argument('--use_cuda',
                     type=bool,
                     help='use cuda or not')
 parser.add_argument('--use_cudnn', default=1, type=int, help='use cudnn or not')
-
+parser.add_argument('--remove_duplicates',
+                    default=True,
+                    type=bool,
+                    help='remove duplicate frames or not')

applications/DAIN/predict.py

@@ -80,7 +80,8 @@ class VideoFrameInterp(object):
                  video_path,
                  use_gpu=True,
                  key_frame_thread=0.,
-                 output_path='output'):
+                 output_path='output',
+                 remove_duplicates=True):
         self.video_path = video_path
         self.output_path = os.path.join(output_path, 'DAIN')
         if model_path is None:
@@ -138,6 +139,8 @@ class VideoFrameInterp(object):
             end = time.time()
 
             frames = sorted(glob.glob(os.path.join(out_path, '*.png')))
+            if remove_duplicates:
+                frames = remove_duplicates(out_path)
 
             img = imread(frames[0])
 
@@ -199,12 +202,12 @@ class VideoFrameInterp(object):
                 X0 = img_first.astype('float32').transpose((2, 0, 1)) / 255
                 X1 = img_second.astype('float32').transpose((2, 0, 1)) / 255
 
-                if key_frame:
-                    y_ = [
-                        np.transpose(255.0 * X0.clip(0, 1.0), (1, 2, 0))
-                        for i in range(num_frames)
-                    ]
-                else:
+                #if key_frame:
+                #    y_ = [
+                #        np.transpose(255.0 * X0.clip(0, 1.0), (1, 2, 0))
+                #        for i in range(num_frames)
+                #    ]
+                #else:
                 assert (X0.shape[1] == X1.shape[1])
                 assert (X0.shape[2] == X1.shape[2])
 
@@ -235,8 +238,7 @@ class VideoFrameInterp(object):
                 y_ = [
                     np.transpose(
                         255.0 * item.clip(
-                                0, 1.0)[0, :,
-                                        padding_top:padding_top + int_height,
+                            0, 1.0)[0, :, padding_top:padding_top + int_height,
                                     padding_left:padding_left + int_width],
                         (1, 2, 0)) for item in y_
                 ]
@@ -266,14 +268,16 @@ class VideoFrameInterp(object):
                                                 vidname + '.mp4')
             if os.path.exists(video_pattern_output):
                 os.remove(video_pattern_output)
-            frames2video(frame_pattern_combined, video_pattern_output,
-                                   r2)
+            frames2video(frame_pattern_combined, video_pattern_output, r2)
 
         return frame_pattern_combined, video_pattern_output
 
 
 if __name__ == '__main__':
     args = parser.parse_args()
-    predictor = VideoFrameInterp(args.time_step, args.saved_model,
-                                 args.video_path, args.output_path)
+    predictor = VideoFrameInterp(args.time_step,
+                                 args.saved_model,
+                                 args.video_path,
+                                 args.output_path,
+                                 remove_duplicates=args.remove_duplicates)
     predictor.run()

applications/DAIN/util.py

 import os, sys
 import glob
 import shutil
+import cv2
 
 
 class AverageMeter(object):
@@ -44,3 +45,34 @@ def combine_frames(input, interpolated, combined, num_frames):
             except Exception as e:
                 print(e)
                 print(len(frames2), num_frames, i, k, i * num_frames + k)
+
+
+def remove_duplicates(paths):
+    def dhash(image, hashSize=8):
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+        resized = cv2.resize(gray, (hashSize + 1, hashSize))
+        diff = resized[:, 1:] > resized[:, :-1]
+        return sum([2**i for (i, v) in enumerate(diff.flatten()) if v])
+
+    hashes = {}
+    imagePaths = sorted(glob.glob(os.path.join(paths, '*.png')))
+    for imagePath in imagePaths:
+        image = cv2.imread(imagePath)
+        h = dhash(image)
+        p = hashes.get(h, [])
+        p.append(imagePath)
+        hashes[h] = p
+
+    for (h, hashedPaths) in hashes.items():
+        if len(hashedPaths) > 1:
+            for p in hashedPaths[1:]:
+                os.remove(p)
+
+    frames = sorted(glob.glob(os.path.join(paths, '*.png')))
+    for fid, frame in enumerate(frames):
+        new_name = '{:08d}'.format(fid) + '.png'
+        new_name = os.path.join(paths, new_name)
+        os.rename(frame, new_name)
+
+    frames = sorted(glob.glob(os.path.join(paths, '*.png')))
+    return frames