├── __init__.py ├── requirements.txt ├── image_search.py ├── clip_siglip.py ├── .gitignore ├── README.md └── LICENSE /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | datasets 2 | sentencepiece 3 | torch 4 | transformers 5 | faiss-gpu 6 | gradio 7 | sentence-transformers 8 | -------------------------------------------------------------------------------- /image_search.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import gradio as gr 3 | from PIL import Image 4 | from transformers import AutoProcessor, SiglipModel 5 | import faiss 6 | import numpy as np 7 | from huggingface_hub import hf_hub_download 8 | from datasets import load_dataset 9 | 10 | hf_hub_download("merve/siglip-faiss-wikiart", "siglip_new.index", local_dir="./") 11 | index = faiss.read_index("./siglip_new.index") 12 | 13 | dataset = load_dataset("huggan/wikiart") 14 | device = torch.device('cuda' if torch.cuda.is_available() else "cpu") 15 | dataset = dataset.with_format("torch", device=device) 16 | 17 | processor = AutoProcessor.from_pretrained("nielsr/siglip-base-patch16-224") 18 | model = SiglipModel.from_pretrained("nielsr/siglip-base-patch16-224").to(device) 19 | 20 | 21 | def extract_features_siglip(image): 22 | with torch.no_grad(): 23 | inputs = processor(images=image, return_tensors="pt").to(device) 24 | image_features = model.get_image_features(**inputs) 25 | return image_features 26 | 27 | def infer(input_image): 28 | input_features = extract_features_siglip(input_image) 29 | input_features = input_features.detach().cpu().numpy() 30 | input_features = np.float32(input_features) 31 | faiss.normalize_L2(input_features) 32 | distances, indices = index.search(input_features, 9) 33 | gallery_output = [] 34 | for i,v in enumerate(indices[0]): 35 | sim = -distances[0][i] 36 | img_resized = dataset["train"][int(v)]['image'] 37 | gallery_output.append(img_resized) 38 | return gallery_output 39 | 40 | gr.Interface(infer, "sketchpad", "gallery", title="Draw to Search Art 🖼️").launch() 41 | -------------------------------------------------------------------------------- /clip_siglip.py: -------------------------------------------------------------------------------- 1 | import torch 2 | from transformers import pipeline, SiglipModel, AutoProcessor 3 | import numpy as np 4 | import gradio as gr 5 | 6 | 7 | siglip_checkpoint = "nielsr/siglip-base-patch16-224" 8 | clip_checkpoint = "openai/clip-vit-base-patch16" 9 | clip_detector = pipeline(model=clip_checkpoint, task="zero-shot-image-classification") 10 | siglip_model = SiglipModel.from_pretrained("nielsr/siglip-base-patch16-224") 11 | siglip_processor = AutoProcessor.from_pretrained("nielsr/siglip-base-patch16-224") 12 | 13 | 14 | def postprocess(output): 15 | return {out["label"]: float(out["score"]) for out in output} 16 | 17 | def postprocess_siglip(output, labels): 18 | return {labels[i]: float(np.array(output[0])[i]) for i in range(len(labels))} 19 | 20 | def siglip_detector(image, texts): 21 | inputs = siglip_processor(text=texts, images=image, return_tensors="pt", 22 | padding="max_length") 23 | 24 | with torch.no_grad(): 25 | outputs = siglip_model(**inputs) 26 | logits_per_image = outputs.logits_per_image 27 | probs = torch.sigmoid(logits_per_image) 28 | return probs 29 | 30 | 31 | def infer(image, candidate_labels): 32 | candidate_labels = [label.lstrip(" ") for label in candidate_labels.split(",")] 33 | siglip_out = siglip_detector(image, candidate_labels) 34 | clip_out = clip_detector(image, candidate_labels=candidate_labels) 35 | return postprocess(clip_out), postprocess_siglip(siglip_out, labels=candidate_labels) 36 | 37 | 38 | with gr.Blocks() as demo: 39 | gr.Markdown("# Compare CLIP and SigLIP") 40 | gr.Markdown("Compare the performance of CLIP and SigLIP on zero-shot classification in this Space 👇") 41 | with gr.Row(): 42 | with gr.Column(): 43 | image_input = gr.Image(type="pil") 44 | text_input = gr.Textbox(label="Input a list of labels") 45 | run_button = gr.Button("Run", visible=True) 46 | 47 | with gr.Column(): 48 | clip_output = gr.Label(label = "CLIP Output", num_top_classes=3) 49 | siglip_output = gr.Label(label = "SigLIP Output", num_top_classes=3) 50 | 51 | examples = [["./baklava.jpg", "baklava, souffle, tiramisu"]] 52 | gr.Examples( 53 | examples = examples, 54 | inputs=[image_input, text_input], 55 | outputs=[clip_output, 56 | siglip_output 57 | ], 58 | fn=infer, 59 | cache_examples=True 60 | ) 61 | run_button.click(fn=infer, 62 | inputs=[image_input, text_input], 63 | outputs=[clip_output, 64 | siglip_output 65 | ]) 66 | 67 | demo.launch() 68 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # SigLIP Projects 📎📓 2 | 3 | SigLIP is [CLIP](https://huggingface.co/docs/transformers/model_doc/clip), a multimodal model, with a better loss function. The sigmoid loss operates solely on image-text pairs and does not require a global view of the pairwise similarities for normalization. This allows further scaling up the batch size, while also performing better at smaller batch sizes. 4 | 5 | **Update:** SigLIP 2 is released today, here's [an intuitive explanation](https://huggingface.co/blog/siglip2) about what's new, and Naflex variant. 6 | 7 | A TL;DR of SigLIP by one of the authors can be found [here](https://twitter.com/giffmana/status/1692641733459267713). 8 | 9 | ## What is this repository for? 👀 10 | 11 | This repository shows how you can utilize [SigLIP](https://arxiv.org/abs/2303.15343) and SigLIP 2 for search in different modalities. 12 | 13 | 📚 It contains: 14 | - A notebook on how to create an embedding index using SigLIP with Hugging Face Transformers and FAISS, 15 | - An image similarity search application that uses the created index, ([link to 🤗Space](https://huggingface.co/spaces/merve/draw_to_search_art)) 16 | - An application that compares SigLIP and CLIP ([link to the 🤗Space](https://huggingface.co/spaces/merve/compare_clip_siglip)) 17 | - Another notebook to index text embeddings the 🤗datasets-FAISS integration. 18 | 19 | Screenshot 2024-01-08 at 22 23 44 20 | 21 | 22 | 23 | ## Intended uses & limitations 24 | 25 | You can use the raw SigLIP for tasks like zero-shot image classification and image-text retrieval. See the [SigLIP checkpoints on Hugging Face Hub](https://huggingface.co/models?search=google/siglip) to look for other versions on a task that interests you. 26 | 27 | ### How to use with 🤗transformers 28 | 29 | Here is how to use this model to perform zero-shot image classification. This also supports SigLIP 2 checkpoints. For Naflex variant, use `padding="max_length", max_length=64"`. 30 | 31 | ```python 32 | from PIL import Image 33 | import requests 34 | from transformers import AutoProcessor, AutoModel 35 | import torch 36 | 37 | model = AutoModel.from_pretrained("google/siglip-base-patch16-256-i18n") 38 | processor = AutoProcessor.from_pretrained("google/siglip-base-patch16-256-i18n") 39 | 40 | url = "http://images.cocodataset.org/val2017/000000039769.jpg" 41 | image = Image.open(requests.get(url, stream=True).raw) 42 | 43 | texts = ["a photo of 2 cats", "a photo of 2 dogs"] 44 | inputs = processor(text=texts, images=image, return_tensors="pt") 45 | 46 | with torch.no_grad(): 47 | outputs = model(**inputs) 48 | 49 | logits_per_image = outputs.logits_per_image 50 | probs = torch.sigmoid(logits_per_image) # these are the probabilities 51 | print(f"{probs[0][0]:.1%} that image 0 is '{texts[0]}'") 52 | ``` 53 | 54 | Alternatively, one can leverage the pipeline API which abstracts away the complexity for the user: 55 | 56 | ``` 57 | from transformers import pipeline 58 | from PIL import Image 59 | import requests 60 | 61 | # load pipe 62 | image_classifier = pipeline(task="zero-shot-image-classification", model="google/siglip-base-patch16-256-i18n") 63 | 64 | # load image 65 | url = 'http://images.cocodataset.org/val2017/000000039769.jpg' 66 | image = Image.open(requests.get(url, stream=True).raw) 67 | 68 | # inference 69 | outputs = image_classifier(image, candidate_labels=["2 cats", "a plane", "a remote"]) 70 | outputs = [{"score": round(output["score"], 4), "label": output["label"] } for output in outputs] 71 | print(outputs) 72 | ``` 73 | For more code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/siglip.html#). 74 | 75 | 76 | 77 | **Citation** 78 | 79 | ```bibtex 80 | @misc{zhai2023sigmoid, 81 | title={Sigmoid Loss for Language Image Pre-Training}, 82 | author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer}, 83 | year={2023}, 84 | eprint={2303.15343}, 85 | archivePrefix={arXiv}, 86 | primaryClass={cs.CV} 87 | } 88 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------