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

>>> from transformers import AutoProcessor, AutoModel
>>> 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 8 frames
>>> indices = sample_frame_indices(clip_len=8, frame_sample_rate=1, seg_len=container.streams.video[0].frames)
>>> video = read_video_pyav(container, indices)

>>> processor = AutoProcessor.from_pretrained("microsoft/xclip-base-patch32")
>>> model = AutoModel.from_pretrained("microsoft/xclip-base-patch32")

>>> inputs = processor(
...     text=["playing sports", "eating spaghetti", "go shopping"],
...     videos=list(video),
...     return_tensors="pt",
...     padding=True,
... )

>>> # forward pass
>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> logits_per_video = outputs.logits_per_video  # this is the video-text similarity score
>>> probs = logits_per_video.softmax(dim=1)  # we can take the softmax to get the label probabilities
>>> print(probs)
tensor([[1.9496e-04, 9.9960e-01, 2.0825e-04]])

>>> import torch
>>> from transformers import AutoTokenizer, AutoModel

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/xclip-base-patch32")
>>> model = AutoModel.from_pretrained("microsoft/xclip-base-patch32")

>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt")
>>> with torch.inference_mode():
...     text_features = model.get_text_features(**inputs)

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

>>> from transformers import AutoProcessor, AutoModel
>>> 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 8 frames
>>> indices = sample_frame_indices(clip_len=8, frame_sample_rate=1, seg_len=container.streams.video[0].frames)
>>> video = read_video_pyav(container, indices)

>>> processor = AutoProcessor.from_pretrained("microsoft/xclip-base-patch32")
>>> model = AutoModel.from_pretrained("microsoft/xclip-base-patch32")

>>> inputs = processor(videos=list(video), return_tensors="pt")

>>> video_features = model.get_video_features(**inputs)

>>> from transformers import AutoTokenizer, XCLIPTextModel

>>> model = XCLIPTextModel.from_pretrained("microsoft/xclip-base-patch32")
>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/xclip-base-patch32")

>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt")

>>> outputs = model(**inputs)
>>> last_hidden_state = outputs.last_hidden_state
>>> pooled_output = outputs.pooler_output  # pooled (EOS token) states

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

>>> from transformers import AutoProcessor, XCLIPVisionModel
>>> 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=8, frame_sample_rate=1, seg_len=container.streams.video[0].frames)
>>> video = read_video_pyav(container, indices)

>>> processor = AutoProcessor.from_pretrained("microsoft/xclip-base-patch32")
>>> model = XCLIPVisionModel.from_pretrained("microsoft/xclip-base-patch32")

>>> pixel_values = processor(videos=list(video), return_tensors="pt").pixel_values

>>> batch_size, num_frames, num_channels, height, width = pixel_values.shape
>>> pixel_values = pixel_values.reshape(-1, num_channels, height, width)

>>> outputs = model(pixel_values)
>>> last_hidden_state = outputs.last_hidden_state