>>> from transformers import AutoImageProcessor, VideoMAEForPreTraining
>>> import numpy as np
>>> import torch

>>> num_frames = 16
>>> video = list(np.random.randint(0, 256, (num_frames, 3, 224, 224)))

>>> image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base")
>>> model = VideoMAEForPreTraining.from_pretrained("MCG-NJU/videomae-base")

>>> pixel_values = image_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
>>> bool_masked_pos = torch.randint(0, 2, (1, seq_length)).bool()

>>> outputs = model(pixel_values, bool_masked_pos=bool_masked_pos)
>>> loss = outputs.loss

>>> import av
>>> import torch
>>> import numpy as np

>>> from transformers import AutoImageProcessor, VideoMAEForVideoClassification
>>> from huggingface_hub import hf_hub_download

>>> np.random.seed(0)


>>> def read_video_pyav(container, indices):
...     '''
...     Decode the video with PyAV decoder.
...     Args:
...         container (`av.container.input.InputContainer`): PyAV container.
...         indices (`List[int]`): List of frame indices to decode.
...     Returns:
...         result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
...     '''
...     frames = []
...     container.seek(0)
...     start_index = indices[0]
...     end_index = indices[-1]
...     for i, frame in enumerate(container.decode(video=0)):
...         if i > end_index:
...             break
...         if i >= start_index and i in indices:
...             frames.append(frame)
...     return np.stack([x.to_ndarray(format="rgb24") for x in frames])


>>> def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
...     '''
...     Sample a given number of frame indices from the video.
...     Args:
...         clip_len (`int`): Total number of frames to sample.
...         frame_sample_rate (`int`): Sample every n-th frame.
...         seg_len (`int`): Maximum allowed index of sample's last frame.
...     Returns:
...         indices (`List[int]`): List of sampled frame indices
...     '''
...     converted_len = int(clip_len * frame_sample_rate)
...     end_idx = np.random.randint(converted_len, seg_len)
...     start_idx = end_idx - converted_len
...     indices = np.linspace(start_idx, end_idx, num=clip_len)
...     indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
...     return indices


>>> # video clip consists of 300 frames (10 seconds at 30 FPS)
>>> file_path = hf_hub_download(
...     repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
... )
>>> container = av.open(file_path)

>>> # sample 16 frames
>>> indices = sample_frame_indices(clip_len=16, frame_sample_rate=1, seg_len=container.streams.video[0].frames)
>>> video = read_video_pyav(container, indices)

>>> image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")
>>> model = VideoMAEForVideoClassification.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")

>>> inputs = image_processor(list(video), return_tensors="pt")

>>> with torch.no_grad():
...     outputs = model(**inputs)
...     logits = outputs.logits

>>> # model predicts one of the 400 Kinetics-400 classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
eating spaghetti