arsyed + keras   27

Prodicode/ann-visualizer: A python library for visualizing Artificial Neural Networks (ANN)
"A great visualization python library used to work with Keras. It uses python's graphviz library to create a presentable graph of the neural network you are building."
python  libs  neural-net  keras  visualization  graphviz  graph 
may 2018 by arsyed
bckenstler/CLR
"This repository includes a Keras callback to be used in training that allows implementation of cyclical learning rate policies, as detailed in Leslie Smith's paper Cyclical Learning Rates for Training Neural Networks arXiv:1506.01186v4."
keras  libs  learning-rate  cycling 
march 2017 by arsyed
Added support for CTC in both Theano and Tensorflow along with image OCR example. by mbhenry · Pull Request #3436 · fchollet/keras
"This commit adds support for training RNNs with Connectionist Temporal Classification (CTC), which is a popular loss function for streams where the temporal or translational alignment between the input data and labels is unknown. An example would be raw speech spectrograms as input data and phonemes as labels. Another example is an input image that includes rendered text with an unknown translational location, word/character spacing, or rotation."
python  keras  ctc  tensorflow 
february 2017 by arsyed
osh/kerlym: KEras Reinforcement Learning gYM agents
"This repo is intended to host a handful of reinforcement learning agents implemented using the Keras (http://keras.io/) deep learning library for Theano and Tensorflow. It is intended to make it easy to run, measure, and experiment with different learning configuration and underlying value function approximation networks while running a variery of OpenAI Gym environments (https://gym.openai.com/)."
python  code  deep-learning  reinforcement-learning  keras 
june 2016 by arsyed
Building powerful image classification models using very little data
A message that I hear often is that "deep learning is only relevant when you have a huge amount of data". While not entirely incorrect, this is somewhat misleading. Certainly, deep learning requires the ability to learn features automatically from the data, which is generally only possible when lots of training data is available --especially for problems where the input samples are very high-dimensional, like images. However, convolutional neural networks --a pillar algorithm of deep learning-- are by design one of the best models available for most "perceptual" problems (such as image classification), even with very little data to learn from. Training a convnet from scratch on a small image dataset will still yield reasonable results, without the need for any custom feature engineering. Convnets are just plain good. They are the right tool for the job.

But what's more, deep learning models are by nature highly repurposable: you can take, say, an image classification or speech-to-text model trained on a large-scale dataset then reuse it on a significantly different problem with only minor changes, as we will see in this post. Specifically in the case of computer vision, many pre-trained models (usually trained on the ImageNet dataset) are now publicly available for download and can be used to bootstrap powerful vision models out of very little data.
deep-learning  convnet  keras  transfer-learning  small-data  data-augmentation 
june 2016 by arsyed
coreylynch/async-rl: Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"
"This is a Tensorflow + Keras implementation of asyncronous 1-step Q learning as described in "Asynchronous Methods for Deep Reinforcement Learning".

Since we're using multiple actor-learner threads to stabilize learning in place of experience replay (which is super memory intensive), this runs comfortably on a macbook w/ 4g of ram.

It uses Keras to define the deep q network (see model.py), OpenAI's gym library to interact with the Atari Learning Environment (see atari_environment.py), and Tensorflow for optimization/execution (see async_dqn.py)."
reinforcement-learning  python  code  tensorflow  keras  gaming  atari 
june 2016 by arsyed
udibr/headlines: Automatically generate headlines to short articles
"This project attempts to reproduce the results in the paper: Generating News Headlines with Recurrent Neural Networks"
papers  rnn  keras  examples  nlp  text  text-generation  generative  generative-models 
april 2016 by arsyed

Copy this bookmark:



description:


tags: