Deploying Meta’s Transcoder on E2E’s Cloud GPU Server to Translate C++ and Java Code into Python

January 17, 2024

Introduction - Language Migration

The business of changing code databases or porting code from one language to another, known as language migration, is a significant and multifaceted endeavor in software development. It often involves moving from a familiar language to another to address technical debt, exploit better tools, or leverage a more active developer community. While the reasons for migration might vary, ranging from seeking improved features, functionalities, or even attracting talent, the process is generally complex, risky, and costly. Companies may undertake gradual migration if languages are compatible or might need to be rewritten entirely for different language families. The decision involves weighing the technical and operational costs against the potential long-term benefits and is influenced by the company's size, the scope of the codebase, and specific business needs. Ultimately, a migration should be carefully planned and executed, considering both immediate needs and future sustainability.

Some notable examples of companies migrating their code to different languages include:

1. Twitter: Moved from Ruby to Scala for better performance and scalability.

2. Netflix: Transitioned from Java to Node.js for its user interface layer to improve load times and user experience.

3. Google: Developed Go language and migrated some components for better performance and efficiency.

4. Facebook: Introduced and moved significant parts of its code to Hack, a language specifically designed to maintain the speed of PHP while offering additional type safety.

The cost of migrating a codebase to a different language can be substantial, depending on various factors like the size of the codebase, the complexity of the migration, and the languages involved. For example, the Commonwealth Bank of Australia reportedly spent approximately $750 million over five years to switch its platform from COBOL to Java. This example illustrates that while the costs can vary widely, migrating significant codebases, especially for large organizations, is generally a major financial undertaking.

Transcoder by Meta: An Overview

Transcoder by Meta, previously known as Facebook, represents an ambitious endeavor in the domain of automated code translation. The aim is to streamline the process of migrating codebases across diverse programming languages. As part of Meta's initiative titled ‘Unsupervised Translation of Programming Languages,’ Transcoder is designed to leverage artificial intelligence for understanding and converting code from one language to another. By employing machine learning techniques, it can recognize patterns, functions, and structures in one language and adeptly translate them to another while ensuring that the logical flow and functionality are maintained.

The development of tools like Transcoder indicates a growing capability and interest in automating language migration. For businesses, the implications are profound, offering potential reductions in costs and timeframes associated with codebase migration. The process, which traditionally requires extensive manual effort and deep expertise in both the source and destination languages, can be assisted or even fully automated by AI. However, quality assurance and a thorough understanding of the output remain critical components of the process.

Despite these advancements, the task of automatic code translation is rife with complexity. Each programming language comes with its own set of paradigms, libraries, and environment specifics, making a one-size-fits-all solution challenging. Tools like Transcoder significantly aid the translation process but might not always produce deployment-ready results without further tuning and testing. Therefore, while Transcoder can potentially revolutionize how companies maintain and evolve their technology stacks, it's important for organizations to consider the nuances of integrating such translations into their production environments. Factors such as cost, risk, and long-term maintainability are crucial in determining whether to adopt such automated translation solutions for business operations. The rise of tools like Transcoder by Meta could provide more flexibility in dealing with technical debt and legacy systems, yet they necessitate a careful balance of benefits against the complexities and intricacies involved.

E2E’s Cloud GPU Server

E2E's Cloud GPU servers are tailored for high-performance computations, offering a cost-effective solution for deep machine learning, architectural visualization, video processing, and scientific computing. These servers are equipped with modern NVIDIA GPU chipsets, including the latest Tesla V100 & T4 cards, known for their high operation speed and power. They also utilize CUDA technology, a parallel computing architecture from NVIDIA, which enhances GPU computing performance significantly. CUDA's advantages include the use of common programming languages, application of advanced technologies for efficient computing, multi-GPU support, and excellent scalability for various projects.

In this article, we’ll deploy Transcoder onto V100 GPUs available on E2E’s cloud server.

Deploying Transcoder

First:


# Clone the git repository for transcoder
# in local environment
git clone https://github.com/facebookresearch/TransCoder transcoder/

Download model files:


# for C++ -> Java, Java -> C++ and Java -> Python
wget https://dl.fbaipublicfiles.com/transcoder/model_1.pth
# for C++ -> Python, Python -> C++ and Python -> Java
wget https://dl.fbaipublicfiles.com/transcoder/model_2.pth

Installing dependencies:


# Since transcoder is implemented in pytorch,
# we need to install pytorch first
pip install torch torchvision


# Now install other required documentations
pip install numpy Moses libclang submitit six sacrebleu==1.2.11

Now go to TransCoder/XLM/tools/, where you will need to install fastBPE:


cd transcoder/XLM/tools/fastBPE
git clone https://github.com/glample/fastBPE
cd fastBPE
g++ -std=c++11 -pthread -O3 fastBPE/main.cc -IfastBPE -o fast

Now, to get the Python API for the code; run the following commands:


# installs header files 
sudo apt-get install python3-dev


pip install cython


python setup.py install

Now, to install Apex, run the following command. Make sure you have navigated out of the Transcoder directory.


git clone https://github.com/NVIDIA/apex
cd apex
# if pip >= 23.1 (ref: https://pip.pypa.io/en/stable/news/#v23-1) which supports multiple `--config-settings` with the same key... 
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
# otherwise
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Make sure to install libclang:


sudo apt-get install libclang-dev

And the following dependency for Python:


pip install clang-5

Clang is basically a compiler front end for the C, C++, and Objective-C programming languages. It is designed to be a replacement for the GNU Compiler Collection's (GCC) traditional compiler front end. Clang is part of the LLVM (Low-Level Virtual Machine) project and serves as its primary front end.

‍

Important: If your libclang.so is not in /usr/lib/llvm-7/lib/, replace the path to libclang.so to the correct path in clang.cindex.Config.set_library_path('path_to_libclang') in code_tokenizer.py

Translating the Code


python translate.py --src_lang cpp --tgt_lang java --model_path trained_model.pth < input_code.cpp

Use the above command to translate the code.

--src_lang: This is the source language

--tgt_lang: This is the target language

--model_path: This represents the model used for translation

Input_code.cpp: This is the file that contains the source code

‍

Let’s take C++ and Java code for generating the sum of first n natural numbers. We’ll attempt to convert this code into Python using Transcoder.

‍

Input_code.cpp code:


#include 
using namespace std;

int main() {
    int n, sum = 0;

    cout << "Enter a positive integer: ";
    cin >> n;

    for (int i = 1; i <= n; ++i) {
        sum += i;
    }

    cout << "Sum = " << sum;
    return 0;
}

First, let’s convert the C++ code into Python:

python translate.py --src_lang cpp --tgt_lang python --model_path model_2.pth < Input_code.cpp

Output:

‍

‍

Now let’s convert the Java code into Python:

python translate.py --src_lang java --tgt_lang python --model_path model_1.pth < Input_code.java

Output:

‍

‍

As you can see, the code translation from Java to Python makes some sense, but the one from C++ to Python produces a garbage output. This shows that Transcoder still needs a lot of improvements to be able to translate code without errors. Some more examples need to be tested to further understand Transcoder’s capabilities. Please go ahead and experiment, now that you know how to deploy it.

Conclusion

In conclusion, this article provides a comprehensive overview of language migration in software development, emphasizing the complexities and costs associated with porting code from one programming language to another. It introduces Transcoder by Meta, an automated code translation tool that leverages artificial intelligence for converting codebases across diverse languages. The deployment process of Transcoder onto E2E's cloud GPU servers is explained, showcasing the potential benefits and challenges of automating language migration.

The article highlights the growing interest in AI-driven tools like Transcoder, which can potentially reduce costs and timeframes associated with codebase migration. However, it acknowledges the complexities involved in automatic code translation, showcasing examples of both successful and less accurate translations.

Reference

https://github.com/facebookresearch/TransCoder

Sign up for Free Trial

Latest Blogs

May 16, 2024

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.
CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels.

Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

‍

Reference Links

https://www.helpscout.com/customer-acquisition/

https://www.cloudways.com/blog/customer-acquisition-strategy-for-startups/

https://blog.hubspot.com/service/customer-acquisition

This is a decorative image for: Constructing 3D objects through Deep Learning

October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

Highly calibrated cameras that take a photograph of the image from various angles.
Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website.

‍

Reference Links

https://tongtianta.site/paper/68922

https://github.com/natowi/3D-Reconstruction-with-Deep-Learning-Methods

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts

October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

https://analyticsindiamag.com/comprehensive-guide-to-deep-q-learning-for-data-science-enthusiasts/

https://medium.com/@jereminuerofficial/a-comprehensive-guide-to-deep-q-learning-8aeed632f52f

October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
GAUDI also removes GANs pathologies like mode collapse and improved GAN.
GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
The scenes are thus synthesized by interpolation within the hidden space.
The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

‍

Reference Links

https://www.researchgate.net/publication/362323995_GAUDI_A_Neural_Architect_for_Immersive_3D_Scene_Generation

https://www.technology.org/2022/07/31/gaudi-a-neural-architect-for-immersive-3d-scene-generation/

https://www.patentlyapple.com/2022/08/apple-has-unveiled-gaudi-a-neural-architect-for-immersive-3d-scene-generation.html