Displaying 1 to 20 from 26 results

NLP-Models-Tensorflow - Gathers machine learning and Tensorflow deep learning models for NLP problems, 1

  •    Jupyter

NLP-Models-Tensorflow, Gathers machine learning and tensorflow deep learning models for NLP problems, code simplify inside Jupyter Notebooks 100%. I will attached github repositories for models that I not implemented from scratch, basically I copy, paste and fix those code for deprecated issues.

attention-transfer - Improving Convolutional Networks via Attention Transfer (ICLR 2017)

  •    Jupyter

The code uses PyTorch https://pytorch.org. Note that the original experiments were done using torch-autograd, we have so far validated that CIFAR-10 experiments are exactly reproducible in PyTorch, and are in process of doing so for ImageNet (results are very slightly worse in PyTorch, due to hyperparameters). This section describes how to get the results in the table 1 of the paper.

tf-rnn-attention - Tensorflow implementation of attention mechanism for text classification tasks.

  •    Python

Tensorflow implementation of attention mechanism for text classification tasks. Inspired by "Hierarchical Attention Networks for Document Classification", Zichao Yang et al. (http://www.aclweb.org/anthology/N16-1174).

spatial-transformer-network - A Tensorflow Implementation of Spatial Transformer Networks

  •    Python

This is a Tensorflow implementation of Spatial Transformer Networks by Max Jaderberg, Karen Simonyan, Andrew Zisserman and Koray Kavukcuoglu, accompanying by two-part blog tutorial series. Spatial Transformer Networks (STN) is a differentiable module that can be inserted anywhere in ConvNet architecture to increase its geometric invariance. It effectively gives the network the ability to spatially transform feature maps at no extra data or supervision cost.

long-range-arena - Long Range Arena for Benchmarking Efficient Transformers

  •    Python

Long-range arena is an effort toward systematic evaluation of efficient transformer models. The project aims at establishing benchmark tasks/dtasets using which we can evaluate transformer-based models in a systematic way, by assessing their generalization power, computational efficiency, memory foot-print, etc. Long-range arena also implements different variants of Transformer models in JAX, using Flax.

pointer-networks-experiments - Sorting numbers with pointer networks

  •    Python

Code for genereting data, training and testing. There are two tasks: ordering single numbers, or sums or numbers (the _sums suffix). The training scripts save model weights each epoch. When started, they attempt to load appropriate weights - corresponding to the hidden size and the chosen number of steps in a sequence.

doc-han-att - Hierarchical Attention Networks for Chinese Sentiment Classification

  •    Jupyter

This is HAN version of sentiment classification, with pre-trained character-level embedding, and used RAN instead of GRU.

tf-rda-cell - Recurrent Discounted Attention unit (RDA) for Tensorflow

  •    Python

This is a implementation of Recurrent Discounted Attention unit that extends Tensorflow's RNNCell, RDA is builds on the RWA by additionally allowing the discounting of the past.

ai_law - all kinds of baseline models for long text classificaiton( text categorization)

  •    Python

Update: Joint Model for law cases prediction is released. run python HAN_train.py to train the model for predict accusation, relevant articles and term of imprisonment.

recurrent-visual-attention - A PyTorch Implementation of "Recurrent Models of Visual Attention"

  •    Python

This is a PyTorch implementation of Recurrent Models of Visual Attention by Volodymyr Mnih, Nicolas Heess, Alex Graves and Koray Kavukcuoglu. The Recurrent Attention Model (RAM) is a recurrent neural network that processes inputs sequentially, attending to different locations within the image one at a time, and incrementally combining information from these fixations to build up a dynamic internal representation of the image.

attend_infer_repeat - A Tensorfflow implementation of Attend, Infer, Repeat

  •    Python

This is an unofficial Tensorflow implementation of Attend, Infear, Repeat (AIR), as presented in the following paper: S. M. Ali Eslami et. al., Attend, Infer, Repeat: Fast Scene Understanding with Generative Models. I describe the implementation and the issues I run into while working on it in this blog post.

ram_modified - "Recurrent Models of Visual Attention" in TensorFlow

  •    Python

This project is modified version of https://github.com/jlindsey15/RAM. The critical problem of last implemetnation is that the location network cannot learn because of tf.stop_gradient implementation so that they got just '94% accuracy'. It seems relatively bad compared to the result of paper. If 'tf.stop_gradient' was commented, the classification result was very bad. The reason I think is that the problem is originated from sharing the gradient flow through location, core, glimpse network. Through gradient sharing, gradients of classification part are corrupted by gradients of reinforcement part so that classification result become very bad. (If someone want to share gradient, the weighted loss should be needed. please refer https://arxiv.org/pdf/1412.7755.pdf) According to their post research, 'Multiple Object Recognition with Visual Attention' (https://arxiv.org/pdf/1412.7755.pdf) they softly separate location network and others through multi-layer RNN. From this, I assume that sharing the gradient through whole network is not a good idea so separate them, and finally got a good result. In summary, the learning stretegy is as follow. location network, baseline network : learn with gradients of reinforcement learning only.

VAD - Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD

  •    Matlab

This toolkit provides the voice activity detection (VAD) code and our recorded dataset. J. Kim and M. Hahn, "Voice Activity Detection Using an Adaptive Context Attention Model," in IEEE Signal Processing Letters, vol. PP, no. 99, pp. 1-1.

Im2LaTeX - An implementation of the Show, Attend and Tell paper in Tensorflow, for the OpenAI Im2LaTeX suggested problem

  •    Python

An implementation of the Show, Attend and Tell (Xu, Kelvin et. al., 2016) paper in TensorFlow, for the OpenAI Im2LaTeX suggested problem. The crux of the model is contained in cnn_enc_gru_dec_attn.py that uses the embedding attention decoder from TensorFlow to attend on the output of the CNN.

DeepLearningReading - Deep Learning and Machine Learning mini-projects

  •    Python

Currently working on replicating the Deep Attentive Reader in Keras. This model has been designed in the same way as described in the paper Teaching Machines to Read and Comprehend. So far, the results are consistantly improving - once 10% Accuracy has been achieved I intend to move over to an AWS instance to reduce the training time.

ban-vqa - Bilinear attention networks for visual question answering

  •    Python

This repository is the implementation of Bilinear Attention Networks for the visual question answering task. Our single model achieved 70.35 and an ensemble of 15 models achieved 71.84 (Test-standard, VQA 2.0). For the detail, please refer to our technical report. This repository is based on and inspired by @hengyuan-hu's work. We sincerely thank for their sharing of the codes.

jeelizGlanceTracker - JavaScript/WebGL lib: detect if the user is looking at the screen or not from the webcam video feed


This JavaScript/WebGL library detects if the user is looking at the screen or not. It is very robust to all lighting conditions and lightweight (only 150KB gzipped for the main script and the neural network JSON model). It is great for playing a video only if the user is watching it. In the paths /integrationDemo*, there are several integration examples. You can host them through a static HTTPS server.

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.