Transformers documentation

SigLIP

Transformers

You are viewing v4.37.2 version. A newer version v4.46.3 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

SigLIP

Overview

The SigLIP model was proposed in Sigmoid Loss for Language Image Pre-Training by Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer. SigLIP proposes to replace the loss function used in CLIP by a simple pairwise sigmoid loss. This results in better performance in terms of zero-shot classification accuracy on ImageNet.

The abstract from the paper is the following:

We propose a simple pairwise Sigmoid loss for Language-Image Pre-training (SigLIP). Unlike standard contrastive learning with softmax normalization, the sigmoid loss operates solely on image-text pairs and does not require a global view of the pairwise similarities for normalization. The sigmoid loss simultaneously allows further scaling up the batch size, while also performing better at smaller batch sizes. Combined with Locked-image Tuning, with only four TPUv4 chips, we train a SigLiT model that achieves 84.5% ImageNet zero-shot accuracy in two days. The disentanglement of the batch size from the loss further allows us to study the impact of examples vs pairs and negative to positive ratio. Finally, we push the batch size to the extreme, up to one million, and find that the benefits of growing batch size quickly diminish, with a more reasonable batch size of 32k being sufficient.

Usage tips

Usage of SigLIP is similar to CLIP. The main difference is the training loss, which does not require a global view of all the pairwise similarities of images and texts within a batch. One needs to apply the sigmoid activation function to the logits, rather than the softmax.
Training is not yet supported. If you want to fine-tune SigLIP or train from scratch, refer to the loss function from OpenCLIP, which leverages various torch.distributed utilities.
When using the standalone SiglipTokenizer or SiglipProcessor, make sure to pass padding="max_length" as that’s how the model was trained.

SigLIP evaluation results compared to CLIP. Taken from the original paper.

This model was contributed by nielsr. The original code can be found here.

Usage example

There are 2 main ways to use SigLIP: either using the pipeline API, which abstracts away all the complexity for you, or by using the SiglipModel class yourself.

Pipeline API

The pipeline allows to use the model in a few lines of code:

>>> from transformers import pipeline
>>> from PIL import Image
>>> import requests

>>> # load pipe
>>> image_classifier = pipeline(task="zero-shot-image-classification", model="google/siglip-base-patch16-224")

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

>>> # inference
>>> outputs = image_classifier(image, candidate_labels=["2 cats", "a plane", "a remote"])
>>> outputs = [{"score": round(output["score"], 4), "label": output["label"] } for output in outputs]
>>> print(outputs)
[{'score': 0.1979, 'label': '2 cats'}, {'score': 0.0, 'label': 'a remote'}, {'score': 0.0, 'label': 'a plane'}]

Using the model yourself

If you want to do the pre- and postprocessing yourself, here’s how to do that:

>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, AutoModel
>>> import torch

>>> model = AutoModel.from_pretrained("google/siglip-base-patch16-224")
>>> processor = AutoProcessor.from_pretrained("google/siglip-base-patch16-224")

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

>>> texts = ["a photo of 2 cats", "a photo of 2 dogs"]
>>> # important: we pass `padding=max_length` since the model was trained with this
>>> inputs = processor(text=texts, images=image, padding="max_length", return_tensors="pt")

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

>>> logits_per_image = outputs.logits_per_image
>>> probs = torch.sigmoid(logits_per_image) # these are the probabilities
>>> print(f"{probs[0][0]:.1%} that image 0 is '{texts[0]}'")
31.9% that image 0 is 'a photo of 2 cats'

Transformers

SigLIP

Overview

Usage tips

Usage example

Pipeline API

Using the model yourself

SiglipConfig

class transformers.SiglipConfig

from_text_vision_configs

SiglipTextConfig

class transformers.SiglipTextConfig

SiglipVisionConfig

class transformers.SiglipVisionConfig

SiglipTokenizer

class transformers.SiglipTokenizer

build_inputs_with_special_tokens

get_special_tokens_mask

create_token_type_ids_from_sequences

save_vocabulary

SiglipImageProcessor

class transformers.SiglipImageProcessor

preprocess

SiglipProcessor

class transformers.SiglipProcessor

batch_decode

decode

SiglipModel

class transformers.SiglipModel

forward

get_text_features

get_image_features

SiglipTextModel

class transformers.SiglipTextModel

forward

SiglipVisionModel

class transformers.SiglipVisionModel

forward