`python
        >>> from PIL import Image
        >>> import requests
        >>> from transformers import AutoProcessor, TFGroupViTModel
        >>> import tensorflow as tf

        >>> model = TFGroupViTModel.from_pretrained("nvidia/groupvit-gcc-yfcc")
        >>> processor = AutoProcessor.from_pretrained("nvidia/groupvit-gcc-yfcc")

        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)

        >>> inputs = processor(
        ...     text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="tf", padding=True
        ... )

        >>> outputs = model(**inputs)
        >>> logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
        >>> probs = tf.math.softmax(logits_per_image, axis=1)  # we can take the softmax to get the label probabilities
        ```)
rū