All Projects → Cyanogenoid → Dspn

Cyanogenoid / Dspn

Licence: mit
[NeurIPS 2019] Deep Set Prediction Networks

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Dspn

Deep Learning Time Series
List of papers, code and experiments using deep learning for time series forecasting
Stars: ✭ 796 (+895%)
Mutual labels:  prediction
Bevel
Ordinal regression in Python
Stars: ✭ 41 (-48.75%)
Mutual labels:  prediction
Deepzip
NN based lossless compression
Stars: ✭ 69 (-13.75%)
Mutual labels:  prediction
Gpdotnetv4
C# implementation of the various algorithms based on Genetic Algorithm, Genetic Programming and Artificial Neural Networks.
Stars: ✭ 19 (-76.25%)
Mutual labels:  prediction
Online Relationship Learning
Unsupervised ML algorithm for predictive modeling and time-series analysis
Stars: ✭ 34 (-57.5%)
Mutual labels:  prediction
Tensorflow Lstm Sin
TensorFlow 1.3 experiment with LSTM (and GRU) RNNs for sine prediction
Stars: ✭ 52 (-35%)
Mutual labels:  prediction
Go Set
Type-safe, zero-allocation sets for Go
Stars: ✭ 751 (+838.75%)
Mutual labels:  set
Mlbox
MLBox is a powerful Automated Machine Learning python library.
Stars: ✭ 1,199 (+1398.75%)
Mutual labels:  prediction
Gpt2 Telegram Chatbot
GPT-2 Telegram Chat bot
Stars: ✭ 41 (-48.75%)
Mutual labels:  prediction
Buckets Js
A complete, fully tested and documented data structure library written in pure JavaScript.
Stars: ✭ 1,128 (+1310%)
Mutual labels:  set
L
Simple set notation in Kotlin
Stars: ✭ 11 (-86.25%)
Mutual labels:  set
Attentive Neural Processes
implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)
Stars: ✭ 33 (-58.75%)
Mutual labels:  prediction
Limit orderbook prediction
Stars: ✭ 61 (-23.75%)
Mutual labels:  prediction
Hash Set
#️⃣ Set with custom equality comparisons
Stars: ✭ 6 (-92.5%)
Mutual labels:  set
Deep Segmentation
CNNs for semantic segmentation using Keras library
Stars: ✭ 69 (-13.75%)
Mutual labels:  prediction
Algorithm
Algorithm is a library of tools that is used to create intelligent applications.
Stars: ✭ 787 (+883.75%)
Mutual labels:  set
Apiset
API Set resolver for Windows
Stars: ✭ 42 (-47.5%)
Mutual labels:  set
Ai Reading Materials
Some of the ML and DL related reading materials, research papers that I've read
Stars: ✭ 79 (-1.25%)
Mutual labels:  prediction
Mirdeep2
Discovering known and novel miRNAs from small RNA sequencing data
Stars: ✭ 70 (-12.5%)
Mutual labels:  prediction
Neural prophet
NeuralProphet - A simple forecasting model based on Neural Networks in PyTorch
Stars: ✭ 1,125 (+1306.25%)
Mutual labels:  prediction

Deep Set Prediction Networks

Overview of set optimisation on the example of CLEVR bounding box prediction

This is the official implementation of our NeurIPS 2019 paper Deep Set Prediction Networks. We propose a new way of predicting sets with a neural network that doesn't suffer from discontinuity issues. This is done by backpropagating through a set encoder to act as a set decoder. You can take a look at the poster for NeurIPS 2019 or the poster for the NeurIPS 2019 workshop on Sets & Partitions.

To use the decoder, you only need dspn.py. You can see how it is used in model.py with build_net and the Net class. For details on the exact steps to reproduce the experiments, check out the README in the dspn directory. You can download pre-trained models and the predictions thereof from the Resources page.

BibTeX entry

@inproceedings{zhang2019dspn,
    author        = {Yan Zhang and Jonathon Hare and Adam Pr\"ugel-Bennett},
    title         = {{Deep Set Prediction Networks}},
    booktitle     = {Advances in Neural Information Processing Systems 32},
    year          = {2019},
    eprint        = {1906.06565},
    url           = {https://arxiv.org/abs/1906.06565},
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].