Author: Deep Learner

Attention

Pervasive Attention: 2D Convolutional Networks for Sequence-to-Sequence Prediction

This is a fork of Fairseq(-py) with implementations of the following models: Pervasive Attention – 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction An NMT models with two-dimensional convolutions to jointly encode the source and the target sequences. Pervasive Attention also provides an extensive decoding grid that we leverage to efficiently train wait-k models. See README. Efficient Wait-k Models for Simultaneous Machine Translation Transformer Wait-k models (Ma et al., 2019) with unidirectional encoders and with joint training of multiple wait-k paths. […]

Read more
Sequences

Trellis Networks for Sequence Modeling

This repository contains the experiments done in paper Trellis Networks for Sequence Modeling by Shaojie Bai, J. Zico Kolter and Vladlen Koltun. On the one hand, a trellis network is a temporal convolutional network with special structure, characterized by weight tying across depth and direct injection of the input into deep layers. On the other hand, we show that truncated recurrent networks are equivalent to trellis networks with special sparsity structure in their weight matrices. Thus trellis networks with general […]

Read more
Neural Network

GPU-accelerated PyTorch implementation of Zero-shot User Intent Detection via Capsule Neural Networks

This repository implements a capsule model IntentCapsNet-ZSL on the SNIPS-NLU dataset in Python 3 with PyTorch, first introduced in the paper Zero-shot User Intent Detection via Capsule Neural Networks. The code aims to follow PyTorch best practices, using torch instead of numpy where possible, and using .cuda() for GPU computation. Feel free to contribute via pull requests. Congying Xia, Chenwei Zhang, Xiaohui Yan, Yi Chang, Philip S. Yu. Zero-shot User Intent Detection via Capsule Neural Networks. In Proceedings of the […]

Read more
Transformer

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

This repository contains the code in both PyTorch and TensorFlow for our paper Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context Zihang Dai*, Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov (*: equal contribution) Preprint 2018 TensorFlow The source code is in the tf/ folder, supporting (1) single-node multi-gpu training, and (2) multi-host TPU training. Besides the source code, we also provide pretrained “TensorFlow” models with state-of-the-art (SoTA) performances reported in the paper. Please refer to tf/README.md […]

Read more
Command-line Tools

A Python Command line parser for common log format

Command line parser for common log format (Nginx default). Usage It counts most important data: referrers, operating systems, browsers and daily unique visitors (IPs). # Console output python parse.py sitename.log.gz # HTML output python parse.py sitename.log.gz –html ~/sitename/logs.html Install and update PIP packages. pip install -U -r requirements.txt Speed logparser 24,249/s GoAccess 6,234/s Outputs HTML output is based on Jinja2 templates. It can be improved as you see fit. Console output for Subreply for    

Read more
URL

A custom ListView with a header that displays pictures from an URL

What is BlurStickyHeaderListView? It is a custom ListView with a header that displays pictures from an URL. It then adds a nice blur/parallax effect to the downloaded picture. It also provides the option of a sticky title. Here is a video of it in action. How do I use the thing? Add compile ‘me.emmano:blurstickyheaderlistview:0.1.+’ to the dependencies{} in your build.gradle. If you do not aleady have jcenter() added to your project, do so by adding the following to build.gradle: repositories […]

Read more
Plot

Python partial dependence plot toolbox

python partial dependence plot toolbox Motivation This repository is inspired by ICEbox. The goal is to visualize the impact of certain features towards model prediction for any supervised learning algorithm. (now support all scikit-learn algorithms) The common headache When using black box machine learning algorithms like random forest and boosting, it is hard to understand the relations between predictors and model outcome. For example, in terms of random forest, all we get is the feature importance. Although we can know […]

Read more
Natural Language Processing, NLP, Python

The NLP Cypher | 06.06.21

Welcome back to the simulation ✌ . So ACL 2021 data dump happened and now we have a huge list of repos to get through in the Repo Cypher this week. 😁 Also, we are updating the NLP index very soon with 100+ new repos (many of which are mentioned here) alongside 30+ new NLP notebooks like this one 👇 . If you would like to get an email alert for future newsletters and asset updates, you can sign-up here. […]

Read more
1 … 503 504 505 506 507 … 991