Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
This project compares different models for news article classification.
Deep Learning, Prediction, NLP, Language Model, Attention, Seq2Seq, RNN, Transformer, Machine Learning, Neural Network, Prediction
We plan to take a picture and extract the most important representative words from the picture then write a story plot using those words.
Application of tensor flow to reimplement “extractive summarization as text matching” by Ming Zhong et al, with modified transformer architecture and data set to reduce quantity of GPU necessary
Exploring deep learning models for visual question answering!
We chose to work with style transfer and experiment with the Chinese ink style. We plan to exploit CNN for neural style transfer and GAN for image colorization.
Use LSTM, Transformer to generate different styles of music
A deep neural network implementation for colorizing black and white images.
We are extracting structured data from a custom unstructured and grammatically non-homogenous dataset of fashion listings on the second-hand fashion website Grailed.
This project performs video captioning task - localizing interesting events from an untrimmed video and producing textual description for each event in Youtube Clips and description dataset.
We aim to create a model that can identify the composer of a piece of classical music. We initially plan to work with piano music limited to six composers, and use an RNN.
Use deep learning methods to transcribe audio into music notes with high accuracy
This project seeks to model Vision-Language Navigation as an RL problem and solve it with an offline RL algorithm -- Decision Transformer.
We are trying to solve the issue of diagnosing breast cancer from mammograms. This work is important to create a more consistent and accurate diagnosis for each patient and to detect cancers early.
We build a dialogue generator for the TV show The Office. The dialogue generator takes in an image, identifies the present characters, and outputs lines based on what the characters would say.
Whether it's writing the perfect score to match the mood of a movie scene or choosing the right song to match your Instagram Story post, matching music to a visual experience is meaningful.
Model trains on images of food, and at testing time, the model is given a new food name and generates an image of the dish. The accuracy of the model is tested using a classifier we create.
Stable Diffusion, CIFAR Classification
49 – 66 of 66
