Active Hackathon

Pavan Kandru

Pavan Kandru

AI enthusiast with a flair for NLP. I love playing with exotic data.
Developers Corner

What is Haystack for Neural Question Answering

Haystack is a python framework for developing End to End question answering systems. It provides a flexible way to use the latest NLP models to solve several QA tasks in real-world settings with huge data collections.

Developers Corner

Guide To Asymmetric Non-local Neural Networks Using PaddleSeg 

PaddleSeg is an Image segmentation framework based on Baidu’s PaddlePaddle(Parallel Distributed Deep Learning). It provides high performance and efficiency, SOTA segmentation models optimized for MultiNode and MultiGPU production systems.

Developers Corner

Guide to Perceiver: A Scalable Transformer-based Model

Perceiver is a transformer-based model that uses both cross attention and self-attention layers to generate representations of multimodal data. A latent array is used to extract information from the input byte array using top-down or feedback processing

Developers Corner

Guide To THiNC: A Refreshing Functional Take On Deep Learning

THiNC is a lightweight DL framework that makes model composition facile. It’s various enticing advantages like Shape inference, concise model representation, effortless debugging and awesome config system, makes this a recommendable choice of framework.

Developers Corner

How To Detect Objects With Detection Transformers?

DETR(Detection Transformer) is an end to end object detection model that does object classification and localization i.e boundary box detection. It is a simple encoder-decoderTransformer with a novel loss function that allows us to formulate the complex object detection problem as a set prediction problem.

Developers Corner

What is Apple’s Quant for Neural Networks Quantization

Quantization is the process of mapping the high precision values (a large set of possible values) to low precision values(a smaller set of possible values). Quantization can be done on both weights and activations of a model.

Subscribe to our Newsletter