sanyam5 / Arc Pytorch
Licence: mit
The first public PyTorch implementation of Attentive Recurrent Comparators
Stars: ✭ 147
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Arc Pytorch
Keras Attention
Visualizing RNNs using the attention mechanism
Stars: ✭ 697 (+374.15%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Sangita
A Natural Language Toolkit for Indian Languages
Stars: ✭ 43 (-70.75%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Deep Learning Time Series
List of papers, code and experiments using deep learning for time series forecasting
Stars: ✭ 796 (+441.5%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
First Steps Towards Deep Learning
This is an open sourced book on deep learning.
Stars: ✭ 376 (+155.78%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Rnn Trajmodel
The source of the IJCAI2017 paper "Modeling Trajectory with Recurrent Neural Networks"
Stars: ✭ 72 (-51.02%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Ner Lstm
Named Entity Recognition using multilayered bidirectional LSTM
Stars: ✭ 532 (+261.9%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Theano Kaldi Rnn
THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.
Stars: ✭ 31 (-78.91%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Hey Jetson
Deep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.
Stars: ✭ 161 (+9.52%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Bitcoin Price Prediction Using Lstm
Bitcoin price Prediction ( Time Series ) using LSTM Recurrent neural network
Stars: ✭ 67 (-54.42%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Gdax Orderbook Ml
Application of machine learning to the Coinbase (GDAX) orderbook
Stars: ✭ 60 (-59.18%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Rmdl
RMDL: Random Multimodel Deep Learning for Classification
Stars: ✭ 375 (+155.1%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Mad Twinnet
The code for the MaD TwinNet. Demo page:
Stars: ✭ 99 (-32.65%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Hdltex
HDLTex: Hierarchical Deep Learning for Text Classification
Stars: ✭ 191 (+29.93%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Trending Deep Learning
Top 100 trending deep learning repositories sorted by the number of stars gained on a specific day.
Stars: ✭ 543 (+269.39%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Pytorch Kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+1326.53%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Zoneout Tensorflow
An implementation of zoneout regularizer on LSTM-RNN by Tensorflow
Stars: ✭ 23 (-84.35%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Deepseqslam
The Official Deep Learning Framework for Route-based Place Recognition
Stars: ✭ 49 (-66.67%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-34.01%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Top Deep Learning
Top 200 deep learning Github repositories sorted by the number of stars.
Stars: ✭ 1,365 (+828.57%)
Mutual labels: deep-neural-networks, recurrent-neural-networks
Bender
Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.
Stars: ✭ 1,728 (+1075.51%)
Mutual labels: deep-neural-networks
arc-pytorch
PyTorch implementation of Attentive Recurrent Comparators by Shyam et al.
A blog explaining Attentive Recurrent Comparators
Visualizing Attention
On Same characters
On Different Characters
How to run?
Download data
python download_data.py
A one-time 52MB download. Shouldn't take more than a few minutes.
Train
python train.py --cuda
Let it train until the accuracy rises to at least 80%. Early stopping is not implemented yet. You will have to manually kill the process.
Visualize
python viz.py --cuda --load 0.13591022789478302 --same
Run with exactly the same parameters as train.py and specify the model to load. Specify "--same" if you want to generate a sample with same characters in both images. The script dumps images to a directory in visualization. The name of directory is taken from --name parameter if specified, else name is a function of the parameters of network.
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].