fix a typo in code snippet and processor config (#2)

- fix a typo in code snippet (d4a091673f1e222362b66e76cd12503485811488)
- Update README.md (283d3dadb4278dff272703e1e49660120ac9ee32)
- Update README.md (3d47cc1abbe7e66e6e1508588b094529329c99a0)
- fix processor config (5c99ed640fbd5953e8c10441c808bbb1d4eedca4)


Co-authored-by: Fatih <fcakyon@users.noreply.huggingface.co>

README.md

@@ -20,16 +20,16 @@ You can use the raw model for video classification into one of the 600 possible
 Here is how to use this model to classify a video:
 
 ```python
-from transformers import TimesformerFeatureExtractor, TimesformerForVideoClassification
+from transformers import AutoImageProcessor, TimesformerForVideoClassification
 import numpy as np
 import torch
 
-video = list(np.random.randn(8, 3, 224, 224))
+video = list(np.random.randn(16, 3, 448, 448))
 
-feature_extractor = TimesformerFeatureExtractor.from_pretrained("facebook/timesformer-hr-finetuned-k600")
+processor = AutoImageProcessor.from_pretrained("facebook/timesformer-hr-finetuned-k600")
 model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-hr-finetuned-k600")
 
-inputs = feature_extractor(video, return_tensors="pt")
+inputs = processor(images=video, return_tensors="pt")
 
 with torch.no_grad():
   outputs = model(**inputs)

preprocessor_config.json

@@ -1,7 +1,7 @@
 {
   "crop_size": {
-    "height": 224,
-    "width": 224
+    "height": 448,
+    "width": 448
   },
   "do_center_crop": true,
   "do_normalize": true,
@@ -21,6 +21,6 @@
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "shortest_edge": 224
+    "shortest_edge": 448
   }
 }