Update README.md

README.md

@@ -27,3 +27,54 @@ Model achieves accuracy of 88.93% and macro-f1 of 89.19%
 Class-wise accuracies: ECS - 91.16%, CS - 83.65, MS - 86.2%, FS - 90.74%, LS - 94.55%
 
 
+## How to use
+
+This is how model can be tested on a shot/clip from a video. 
+Same code is used to process, transform and evaluate on the movienet test set.
+
+```python
+from transformers import VideoMAEImageProcessor, VideoMAEForVideoClassification
+from pytorchvideo.transforms import ApplyTransformToKey
+from torchvision.transforms import v2
+from decord import VideoReader, cpu
+
+## Evaluation Transform
+transform = v2.Compose(
+    [
+        ApplyTransformToKey(
+            key="video",
+            transform=v2.Compose(
+                [
+                    v2.Lambda(lambda x: x.permute(0, 3, 1, 2)), # T, H, W, C -> T, C, H, W
+                    v2.UniformTemporalSubsample(16),
+                    v2.Resize(resize_to),
+                    v2.Lambda(lambda x: x / 255.0),
+                    v2.Normalize(img_mean, img_std)
+                ]
+            ),
+        ),
+    ]
+)
+
+## Preprocessor and Model loading
+image_processor = VideoMAEImageProcessor.from_pretrained("gullalc/videomae-base-finetuned-kinetics-movieshots-scale")
+model = VideoMAEForVideoClassification.from_pretrained("gullalc/videomae-base-finetuned-kinetics-movieshots-scale")
+
+img_mean = image_processor.image_mean
+img_std = image_processor.image_std
+height = width = image_processor.size["shortest_edge"]
+resize_to = (height, width)
+
+## load video/clip and predict
+video_path = "random_clip.mp4"
+vr = VideoReader(video_path, width=480, height=270, ctx=cpu(0))
+frames_tensor = torch.stack([torch.tensor(vr[i].asnumpy()) for i in range(len(vr))])  ## Shape: (T, H, W, C)
+
+frames_tensor = transform({"video": frames_tensor})["video"]
+
+output = model(pixel_values=frames_tensor)
+pred = torch.argmax(outputs.logits, axis=1).cpu().numpy()
+
+print(model.config.id2label[pred[0]])
+```
+