Update README.md

README.md

@@ -28,17 +28,17 @@ You can use the raw model for predicting pixel values for masked patches of a vi
 Here is how to use this model to predict pixel values for randomly masked patches:
 
 ```python
-from transformers import VideoMAEFeatureExtractor, VideoMAEForPreTraining
+from transformers import VideoMAEImageProcessor, VideoMAEForPreTraining
 import numpy as np
 import torch
 
 num_frames = 16
 video = list(np.random.randn(16, 3, 224, 224))
 
-feature_extractor = VideoMAEFeatureExtractor.from_pretrained("MCG-NJU/videomae-base-short-ssv2")
+processor = VideoMAEImageProcessor.from_pretrained("MCG-NJU/videomae-base-short-ssv2")
 model = VideoMAEForPreTraining.from_pretrained("MCG-NJU/videomae-base-short-ssv2")
 
-pixel_values = feature_extractor(video, return_tensors="pt").pixel_values
+pixel_values = processor(video, return_tensors="pt").pixel_values
 
 num_patches_per_frame = (model.config.image_size // model.config.patch_size) ** 2
 seq_length = (num_frames // model.config.tubelet_size) * num_patches_per_frame