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 🤫

Owner
Sajjad Ayoubi
Wants to be a Machine Learning Engineer
Sajjad Ayoubi
PyKaldi is a Python scripting layer for the Kaldi speech recognition toolkit.

PyKaldi is a Python scripting layer for the Kaldi speech recognition toolkit. It provides easy-to-use, low-overhead, first-class Python wrappers for t

922 Dec 31, 2022
SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples

SNCSE SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples This is the repository for SNCSE. SNCSE aims to allev

Sense-GVT 59 Jan 02, 2023
Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper

Data Augmentation using Pre-trained Transformer Models Code associated with the Data Augmentation using Pre-trained Transformer Models paper Code cont

44 Dec 31, 2022
A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

Ian 1 Jan 15, 2022
An automated program that helps customers of Pizza Palour place their pizza orders

PIzza_Order_Assistant Introduction An automated program that helps customers of Pizza Palour place their pizza orders. The program uses voice commands

Tindi Sommers 1 Dec 26, 2021
The swas programming language

The Swas programming language This is a language that was made for fun. Installation Step 0: Make sure you have python installed Step 1. Clone this re

Swas.py 19 Jul 18, 2022
GrammarTagger — A Neural Multilingual Grammar Profiler for Language Learning

GrammarTagger — A Neural Multilingual Grammar Profiler for Language Learning GrammarTagger is an open-source toolkit for grammatical profiling for lan

Octanove Labs 27 Jan 05, 2023
Maha is a text processing library specially developed to deal with Arabic text.

An Arabic text processing library intended for use in NLP applications Maha is a text processing library specially developed to deal with Arabic text.

Mohammad Al-Fetyani 184 Nov 27, 2022
Transformers and related deep network architectures are summarized and implemented here.

Transformers: from NLP to CV This is a practical introduction to Transformers from Natural Language Processing (NLP) to Computer Vision (CV) Introduct

Ibrahim Sobh 138 Dec 27, 2022
基于Transformer的单模型、多尺度的VAE模型

UniVAE 基于Transformer的单模型、多尺度的VAE模型 介绍 https://kexue.fm/archives/8475 依赖 需要大于0.10.6版本的bert4keras(当前还没有推到pypi上,可以直接从GitHub上clone最新版)。 引用 @misc{univae,

苏剑林(Jianlin Su) 49 Aug 24, 2022
Language-Agnostic SEntence Representations

LASER Language-Agnostic SEntence Representations LASER is a library to calculate and use multilingual sentence embeddings. NEWS 2019/11/08 CCMatrix is

Facebook Research 3.2k Jan 04, 2023
A highly sophisticated sequence-to-sequence model for code generation

CoderX A proof-of-concept AI system by Graham Neubig (June 30, 2021). About CoderX CoderX is a retrieval-based code generation AI system reminiscent o

Graham Neubig 39 Aug 03, 2021
An end to end ASR Transformer model training repo

END TO END ASR TRANSFORMER 本项目基于transformer 6*encoder+6*decoder的基本结构构造的端到端的语音识别系统 Model Instructions 1.数据准备: 自行下载数据,遵循文件结构如下: ├── data │ ├── train │

旷视天元 MegEngine 10 Jul 19, 2022
CATs: Semantic Correspondence with Transformers

CATs: Semantic Correspondence with Transformers For more information, check out the paper on [arXiv]. Training with different backbones and evaluation

74 Dec 10, 2021
Checking spelling of form elements

Checking spelling of form elements. You can check the source files of external workflows/reports and configuration files

СКБ Контур (команда 1с) 15 Sep 12, 2022
Prompt tuning toolkit for GPT-2 and GPT-Neo

mkultra mkultra is a prompt tuning toolkit for GPT-2 and GPT-Neo. Prompt tuning injects a string of 20-100 special tokens into the context in order to

61 Jan 01, 2023
This repository serves as a place to document a toy attempt on how to create a generative text model in Catalan, based on GPT-2

GPT-2 Catalan playground and scripts to train a GPT-2 model either from scrath or from another pretrained model.

Laura 1 Jan 28, 2022
Blender addon - Scrub timeline from viewport with a shortcut

Viewport scrub timeline Move in the timeline directly in viewport and snap to nearest keyframe Note : This standalone feature will be added in the nat

Samuel Bernou 40 Nov 07, 2022
Community and sentiment analysis based on tweets

The project has set itself the goal of analyzing the thoughts and interaction of Italian users through the social posts expressed through the Twitter platform on the day of the entry into force of th

3 Nov 17, 2022
Malware-Related Sentence Classification

Malware-Related Sentence Classification This repo contains the code for the ICTAI 2021 paper "Enrichment of Features for Malware-Related Sentence Clas

Chau Nguyen 1 Mar 26, 2022