txtai builds an AI-powered index over sections of text. It supports building text indices to perform similarity searches and create extractive question-answering based systems. txtai also has functionality for zero-shot classification.
This app uses a pre-trained ESRGAN model from TensorFlow Hub and generates super-resolution images using TensorFlow Lite in an Android app. The final app looks like below and the complete code has been released in TensorFlow examples repo for reference.
The task of recovering a high resolution (HR) image from its low-resolution counterpart is commonly referred to as Single Image Super-Resolution (SISR). While interpolation methods, such as bilinear or cubic interpolation, can be used to upsample low-resolution images, the quality of resulting images is generally less appealing. Deep learning, especially Generative Adversarial Networks, has successfully been applied to generate more photo-realistic images, for example, SRGAN and ESRGAN.
Activeloop Hub is an open-source dataset management tool (think Docker Hub for datasets). It’s one of the fastest and easiest ways to access and manage datasets for Tensorflow or PyTorch, as well as build scalable data pipelines. Generate datasets using plug-and-play data pipelines.
Using the python-native framework to seamlessly build data pipelines for feature extraction, machine learning and deep learning. Automatically ingest, clean and transform your raw data as new data comes in.
Hub is also an open-source framework which empowers the Data 2.0 paradigm. With it, you can stream your data while working on it as fast as if it were on-premise, regardless of its size. You can have large datasets stored and version-controlled as single NumPy-like arrays on the cloud and access them from any machine at scale. You can also access and visualize any chunk of the data, as well as sync it with the team. No more data locality, RAM, local folder structure dependency issues.
Test locally, then scale to the cloud with no code change
Activeloop enables building streamable data pipelines which work locally and can be simply scaled to thousand machines on the cloud. No need to configure cloud infrastructure anymore.
Leverage most cost-efficient hardware on the cloud with the support of preemptible/spot instances.
Collaborate with your team
Data versioning and synchronization protocol implemented for you to be accessed across teams. User access management with encryption at rest and in transit. Access your data from anywhere.
Visualize data at any step
View results with our visualization engine deployed on-premise or on the cloud. Preview slices of data with no load time and keep track of feature engineering pipeline.
Reach out to us on [email protected] to get featured here. Learn data science and machine learning with free hands-on data science courses on Jovian.