Colab Notebook · Pre-trained Models · Report Bug
OpenAI recently released the paper Learning Transferable Visual Models From Natural Language Supervision in which they present the CLIP (Contrastive Language–Image Pre-training) model. This model is trained to connect text and images, by matching their corresponding vector representations using a contrastive learning objective. CLIP consists of two separate models, a visual encoder and a text encoder. These were trained on a wooping 400 Million images and corresponding captions. OpenAI has since released a set of their smaller CLIP models, which can be found on the official CLIP Github.
We propose a fine-tuning to replace the original English text encoder with a pre-trained text model in any language. This method makes it possible to adapt the powerful CLIP model to any language in roughly 24 GPU hours.
- Pytorch inference code
- Tensorflow training code
- Pre-trained CLIP-Text encoders for multiple languages
- Training data and pre-computed CLIP text encodings for a large porton of the the image captions of GCC + MSCOCO + VizWiz
While it is possible that other versions works equally fine, we have worked with the following:
- Python = 3.6.9
- Transformers = 4.1.1
- Model Weights
$ conda install --yes -c pytorch pytorch=1.7.1 torchvision cudatoolkit=11.0
$ pip install ftfy regex tqdm
$ pip install git+https://github.com/openai/CLIP.gitReplace cudatoolkit=11.0 above with the appropriate CUDA version on your machine or cpuonly when installing on a machine without a GPU.
For more information please see the official CLIP repostitory.
# Linear Model Weights
$ bash get-weights.shfrom src import multilingual_clip
print(multilingual_clip.AVAILABLE_MODELS.keys())
model = multilingual_clip.load_model('M-BERT-Distil-40')
embeddings = model(['Älgen är skogens konung!', 'Wie leben Eisbären in der Antarktis?', 'Вы знали, что все белые медведи левши?'])
print(embeddings.shape)
# Yields: torch.Size([3, 640])For a more elaborate example, comparing the textual embeddings to the CLIP image embeddings see this colab notebook.
Every text encoder is a Huggingface available transformer, with an additional linear layer on top. Neither of the models have been extensively tested, but for more information and qualitative test results for a specific model, click the Model Name to see its model card.
*** Make sure to update to the most recent version of the repostitory when downloading a new model, and re-run the shell script to download the Linear Weights. ***
| Name | Model Base | Vision Model | Pre-trained Languages | Target Languages | #Parameters |
|---|---|---|---|---|---|
| Multilingual | |||||
| M-BERT Distil 40 | M-BERT Distil | RN50x4 | 101 Languages | 40 Languages | 66 M |
| M-BERT Base 69 | M-BERT Base | RN50x4 | 101 Languages | 68 Languages | 110 M |
| Monolingual | |||||
| Swe-CLIP 500k | KB-BERT | RN50x4 | Swedish | Swedish | 110 M |
| Swe-CLIP 2M | KB-BERT | RN50x4 | Swedish | Swedish | 110 M |
This folder contains the code used for training the above models. If you wsh to train your own model you must do the following things:
- Prepare a set of translated sentence pairs from English -> Your Language(s)
- Compute regular CLIP-Text embeddings for the English sentences.
- Edit Training.py to load your data.
- Train a new CLIP-Text encoder via Teacher Learning
[This Google Drive folder]https://drive.google.com/drive/folders/1I9a7naSZubUATWzLFv61DQMWyFlF7wR5?usp=sharing) contains both pre-computed CLIP-Text Embeddings for a large porton of the the image captions of GCC + MSCOCO + VizWiz.
The Google Drive folder also contains the translation data used to train the currently available models. Good Luck
If you have trained a CLIP Text encoder specific to your language, or another model covering a language not supported here, Please feel free to contact us and we will either upload your model and credit you, or simply link to your already uploaded model.
If you have questions regarding the code or otherwise related to this Github page, please open an issue.
For other purposes, feel free to contact me directly at: [email protected]
Distributed under the MIT License. See LICENSE for more information.