In A New Visual Approach to Machine Learning Modeling, we talked about how TensorFlow is one of the most popular machine learning (ML) framework today, but it's not necessarily an easy one for beginners to start building ML models. That's why we decided to create a GUI on top of TensorFlow. With PerceptiLabs, beginners can get started building a model more quickly, and those with more experience can still dive into the code. Both types of users benefit from PerceptiLabs' rich set of visualizations that include the ability to see a model's architecture, experiment and see how parameter and code changes affect models in real time, and view a rich set of training and validation stats. Given that PerceptiLabs runs TensorFlow behind the scenes, we thought we'd walk through the framework so you can understand its basics, and how it is utilized by PerceptiLabs.

Over the last several years, machine learning (ML) has transitioned from a discipline once reserved for researchers and PhDs into a lucrative field comprised of a growing and diversifying set of users and ML practitioners. This is due in part to the increased processing power found in today's hardware, the discovery of new ML algorithms, and the growing number of open source ML tools, frameworks, and datasets. Collectively, these factors are democratizing ML by putting new and more powerful ML capabilities into the hands of more users and ML practitioners than ever before. However, despite all of these advances, many ML tools and frameworks fail to address the overall workflow of designing, training, and tuning ML models. Many frameworks such as TensorFlow and PyTorch, while incredibly powerful, are still fundamentally programmatic frameworks aimed at coders.

Manipulating tensors is not an easy task as it requires a lot of prerequisites, such as keeping track of multiple dimensions, Dtype compatibility, mathematical correctness, and tensor shape. The real challenge is identifying the right TensorFlow operations from the hundreds of options available. TensorFlow Coder(TF-Coder) makes the tensor manipulation possible without coding and by using examples. TF-Coder helps you write the TensorFlow code. The process is providing input-output examples of the required transformation.

A large chunk of research on the security issues of neural networks is focused on adversarial attacks. However, there exists a vast sea of simpler attacks one can perform both against and with neural networks. This paper gives a quick introduction on how deep learning in security works and explore the basic methods of exploitation, but also look at the offensive capabilities deep learning enabled tools provide. All presented attacks, such as backdooring, GPU-based buffer overflows or automated bug hunting, are accompanied by short open-source exercises for anyone to try out. The TensorFlow code for this paper can be found HERE.

A large chunk of research on the security issues of neural networks is focused on adversarial attacks. However, there exists a vast sea of simpler attacks one can perform both against and with neural networks. This paper gives a quick introduction on how deep learning in security works and explore the basic methods of exploitation, but also look at the offensive capabilities deep learning enabled tools provide. All presented attacks, such as backdooring, GPU-based buffer overflows or automated bug hunting, are accompanied by short open-source exercises for anyone to try out. The TensorFlow code for this paper can be found HERE.

In this post, you'll learn the main recipe to convert a pretrained TensorFlow model in a pretrained PyTorch model, in just a few hours. We'll take the example of a simple architecture like OpenAI GPT-2 Doing such a conversion assumes a good familiarity with both TensorFlow and PyTorch but it's also one of the best ways to get to know better both frameworks! The first step is to retrieve the TensorFlow code and a pretrained checkpoint. Let's get them from OpenAI GPT-2 official repository: TensorFlow checkpoints are usually composed of three files named XXX.ckpt.data-YYY A trained NLP model should also be provided with a vocabulary to associate the tokens to the embeddings indices (here encoder.json

Roundup Hello, here's a quick recap on all the latest AI-related news beyond what we've already reported this week. You may have seen news reports that autonomous cars are unlikely to detect pedestrians crossing the road if they have dark skin, and thus run them over. And yes, the internal alarm bells in your head should be going off, as a closer look at the research behind the stories shows all those headlines screaming about racist AI are a little off the mark. The academic paper at the heart of the matter described a series of experiments testing different computer vision models, such as the Faster R-CNN model and R-50-FPN, on images of pedestrians with different skin tones. The study's authors, based at the Georgia Institute of Technology in the US, described how they paid humans to look through the collection of roughly 3,500 photos, and individually tag people in the snaps as either "LS" for light skin or "DS" for dark skin, and then trained the neural networks using this dataset.

You can use Amazon SageMaker to train a model using custom TensorFlow code. If you choose to deploy your code using Amazon SageMaker hosting services, you can also provide custom TensorFlow inference code. This section provides guidelines for writing custom TensorFlow code for both model training and inference, and an example that includes sample TensorFlow code and instructions for model training and deployment. For information about TensorFlow supported versions, see Supported Versions.

We are currently collecting all feedback and already started working on a more complete report -- stay tuned! For most of us, deep learning still happens on Nvidia GPUs. There is currently no alternative with practical relevance. Google's Tensor Processing Unit (TPU), a custom-developed chip for deep learning, promises to change that. Nine months after the initial announcement, Google last week finally released TPUv2 to early beta users on the Google Cloud Platform.

This is a guide to the main differences I've found between PyTorch and TensorFlow. This post is intended to be useful for anyone considering starting a new project or making the switch from one deep learning framework to another. The focus is on programmability and flexibility when setting up the components of the training and deployment deep learning stack. PyTorch is better for rapid prototyping in research, for hobbyists and for small scale projects. TensorFlow is better for large-scale deployments, especially when cross-platform and embedded deployment is a consideration.