Encrypt Passwords and Documents in Art
Preprocess selected classical music and train a GAN to attempt creation and discrimination of the GAN based on significant characteristics learned from a generated spectrogram waveform.
Unleash the power of your hand and automate anything
Automated task/test framework for differentiable software.
To help people create and automate quality social media post to bring more traffic and awareness to their brand. Beside, it also a machine to help people think about the content with image or text.
Making the world a better place one posture at a time
I propose to create a machine learning model that takes a picture of our face while we are on social media so it can better understand how we feel even when we don't engage with the platform.
Low cost solution to detect pneumothorax using raspberry pi for remote areas where there are no radiologist.
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
We will create an end-to-end Deep learning solution for Chest X-ray diagnosis. It will be a cost-effective solution for rural population with inadequate access to diagnostic imaging specialists.
Code for Hands On Intelligent Agents with OpenAI Gym book to get started and learn to build deep reinforcement learning agents using PyTorch
A web app to get actionable insights into your Robinhood Portfolio
Code & experiments done for the transfer learning contest that measures a RL algorithm's ability to generalize from previous experience
A Python library for recommender system. RecLib makes it easy to design and evaluate deep learning models for recommender system, along with the infrastructure to easily run them in the cloud.
4x faster pinned CPU -> GPU data transfer than Pytorch pinned CPU tensors, and 110x faster GPU -> CPU transfer. Augment parameter size by hosting on CPU. Use non sparse optimizers for sparse training
1. torchdata - Implement (and extend) tensorflow.data.Dataset with PyTorch's torch.utils.data.Dataset. 2.torchfunc - improve performance, analyse, plot and make daily life of DL dev easier.
Make images protect privacy and comply with the GDPR.
This will be a short tagline for the project.
Transforming Aerial Imagery into Actionable Insights for Wildfire Prevention and Rehabilitation
Detecting plant diseases using neural network
Using AI techniques to build a national building inventory
Our system will only take Geographical Solution of a Building and give building's height, Number of Floors, Window locations, Number of Windows and Window-Wall ratio using Machine Learning Solutions
Insect pests in climate change context
Plant Disease Recognition and Localization