CLIPfa: Connecting Farsi Text and Images

Overview

CLIPfa: Connecting Farsi Text and Images

OpenAI 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 vision encoder and a text encoder. These were trained on a wooping 400 Million images and corresponding captions. We have trained a Farsi (Persian) version of OpenAI's CLIP on a dataset of 400,000 (image, text) pairs. We used Farahani's RoBERTa-fa as the text encoder and ‍‍ViT‍ as the vision encoder from Original CLIP and finetuned them.

CLIPfa image

It should be noted that only 400K pairs were used for this training, whereas 4 million pairs were used for the Original CLIP. Also, the training took 30 days across 592 GPUs powered by the V100 chip.

How to use?

Both models generate vectors with 768 dimensions.

from transformers import CLIPVisionModel, RobertaModel, AutoTokenizer, CLIPFeatureExtractor
# download pre-trained models
vision_encoder = CLIPVisionModel.from_pretrained('SajjadAyoubi/clip-fa-vision')
preprocessor = CLIPFeatureExtractor.from_pretrained('SajjadAyoubi/clip-fa-vision')
text_encoder = RobertaModel.from_pretrained('SajjadAyoubi/clip-fa-text')
tokenizer = AutoTokenizer.from_pretrained('SajjadAyoubi/clip-fa-text')
# define input image and input text
text = 'something'
image = PIL.Image.open('my_favorite_image.jpg')
# compute embeddings
text_embedding = text_encoder(**tokenizer(text, return_tensors='pt')).pooler_output
image_embedding = vision_encoder(**preprocessor(image, return_tensors='pt')).pooler_output
text_embedding.shape == image_embedding.shape

Demo:

The followings are just some use cases of CLIPfa on 25K Unsplash images

  • use pip install -q git+https://github.com/sajjjadayobi/clipfa.git
from clipfa import CLIPDemo
demo = CLIPDemo(vision_encoder, text_encoder, tokenizer)
demo.compute_text_embeddings(['گاو' ,'اسب' ,'ماهی'])
demo.compute_image_embeddings(test_df.image_path.to_list())

Image Search:

demo.image_search(query='غروب خورشید')

demo.image_search(query='جنگل در زمستان برفی')

Analogy:

demo.anology('sunset.jpg', additional_text='دریا')

demo.anology('sunset.jpg', additional_text='برف')

Zero Shot Image Classification:

demo.zero_shot(image_path='apples.jpg')
  • Provided labels with their probability for each image.
گاو:36 , ماهی:22, اسب:42 گاو:41 , ماهی:23, اسب:36 گاو:26 , ماهی:45, اسب:27
image image image

Online Demo: CLIPfa at Huggingface 🤗 spaces

We used a small set of images (25K) to keep this app almost real-time, but it's obvious that the quality of image search depends heavily on the size of the image database.

Dataset: 400K

We started with this question that how much the original Clip model depends on its big training dataset containing a lot of conceptual samples. Our model shows that It is possible to meet an acceptable enough target with only a little amount of data even though, It may not have known enough concepts and subjects to be used widely. Our model trained on a dataset gathered from different resources such as The Flickr30k, MS-COCO 2017, Google CCm3, ... . We used these datasets and translated them into the Persian language with a tool prepared by ourselves. Using the Google Translate and Multilingual Similarity Check method we provided an automatic translator that has been given a list of English captions and filtered by the best translations.

  • Note: We used image2ds a great tool to download large scale image datasets such as MS-COCO. It can download, resize and package 100M urls in 20h on one machine. Also supports saving captions for url+caption datasets.
  • coco-flickr-fa 130K on Kaggle

Training:

Any dataset can be used with little change by the training code. CLIPfa can be trained with other encoders as long as they have the same hidden size at the last layer. In this notebook I used training code to train a small CLIP on translated flickr30K dataset.

Citation: ↩️

If you have a technical question regarding the model, code or publication, create an issue in the repository. we didn't publish any papers on the work. However, if you did, please cite us properly with an entry like one below.

@misc{ParsBigBird,
  author          = {Sajjad Ayoubi, Navid Kanaani},
  title           = {CLIPfa: Connecting Farsi Text and Images},
  year            = 2021,
  publisher       = {GitHub},
  journal         = {GitHub repository},
  howpublished    = {\url{https://github.com/SajjjadAyobi/CLIPfa}},
}

Made with ❤️ in my basement 🤫

You might also like...
Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks

Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks. It takes raw videos/images + text as inputs, and outputs task predictions. ClipBERT is designed based on 2D CNNs and transformers, and uses a sparse sampling strategy to enable efficient end-to-end video-and-language learning.

Scene Text Retrieval via Joint Text Detection and Similarity Learning

This is the code of "Scene Text Retrieval via Joint Text Detection and Similarity Learning". For more details, please refer to our CVPR2021 paper.

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple
Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

PyTorch implementation of Microsoft's text-to-speech system FastSpeech 2: Fast and High-Quality End-to-End Text to Speech.
PyTorch implementation of Microsoft's text-to-speech system FastSpeech 2: Fast and High-Quality End-to-End Text to Speech.

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Unsupervised text tokenizer for Neural Network-based text generation.

SentencePiece SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabu

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

T5: Text-To-Text Transfer Transformer The t5 library serves primarily as code for reproducing the experiments in Exploring the Limits of Transfer Lear

Unsupervised text tokenizer for Neural Network-based text generation.

SentencePiece SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabu

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

T5: Text-To-Text Transfer Transformer The t5 library serves primarily as code for reproducing the experiments in Exploring the Limits of Transfer Lear

Code for Text Prior Guided Scene Text Image Super-Resolution
Code for Text Prior Guided Scene Text Image Super-Resolution

Code for Text Prior Guided Scene Text Image Super-Resolution

Owner
Sajjad Ayoubi
Wants to be a Machine Learning Engineer
Sajjad Ayoubi
Ptorch NLU, a Chinese text classification and sequence annotation toolkit, supports multi class and multi label classification tasks of Chinese long text and short text, and supports sequence annotation tasks such as Chinese named entity recognition, part of speech tagging and word segmentation.

Pytorch-NLU,一个中文文本分类、序列标注工具包,支持中文长文本、短文本的多类、多标签分类任务,支持中文命名实体识别、词性标注、分词等序列标注任务。 Ptorch NLU, a Chinese text classification and sequence annotation toolkit, supports multi class and multi label classification tasks of Chinese long text and short text, and supports sequence annotation tasks such as Chinese named entity recognition, part of speech tagging and word segmentation.

null 182 Nov 27, 2022
WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

Google Research Datasets 734 Dec 1, 2022
Concept Modeling: Topic Modeling on Images and Text

Concept is a technique that leverages CLIP and BERTopic-based techniques to perform Concept Modeling on images.

Maarten Grootendorst 117 Dec 6, 2022
Generate text line images for training deep learning OCR model (e.g. CRNN)

Generate text line images for training deep learning OCR model (e.g. CRNN)

null 518 Dec 5, 2022
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

Kashgari Overview | Performance | Installation | Documentation | Contributing ?? ?? ?? We released the 2.0.0 version with TF2 Support. ?? ?? ?? If you

Eliyar Eziz 2.3k Dec 5, 2022
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

Kashgari Overview | Performance | Installation | Documentation | Contributing ?? ?? ?? We released the 2.0.0 version with TF2 Support. ?? ?? ?? If you

Eliyar Eziz 2k Feb 9, 2021
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.

textgenrnn Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code, or quickly tr

Max Woolf 4.8k Nov 29, 2022
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.

textgenrnn Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code, or quickly tr

Max Woolf 4.3k Feb 18, 2021