All Projects → JaveyWang → Pyramid Attention Networks Pytorch

JaveyWang / Pyramid Attention Networks Pytorch

Licence: gpl-3.0
Implementation of Pyramid Attention Networks for Semantic Segmentation.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Pyramid Attention Networks Pytorch

Fastpunct
Punctuation restoration and spell correction experiments.
Stars: ✭ 121 (-33.52%)
Mutual labels:  attention
Prediction Flow
Deep-Learning based CTR models implemented by PyTorch
Stars: ✭ 138 (-24.18%)
Mutual labels:  attention
Pyrollbar
Error tracking and logging from Python to Rollbar
Stars: ✭ 169 (-7.14%)
Mutual labels:  pyramid
Absa keras
Keras Implementation of Aspect based Sentiment Analysis
Stars: ✭ 126 (-30.77%)
Mutual labels:  attention
Mapchete
Tile-based geodata processing using rasterio & Fiona
Stars: ✭ 129 (-29.12%)
Mutual labels:  pyramid
Zappa
Serverless Python
Stars: ✭ 11,859 (+6415.93%)
Mutual labels:  pyramid
Nlp Models Tensorflow
Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0
Stars: ✭ 1,603 (+780.77%)
Mutual labels:  attention
Attentionn
All about attention in neural networks. Soft attention, attention maps, local and global attention and multi-head attention.
Stars: ✭ 175 (-3.85%)
Mutual labels:  attention
Vqa regat
Research Code for ICCV 2019 paper "Relation-aware Graph Attention Network for Visual Question Answering"
Stars: ✭ 129 (-29.12%)
Mutual labels:  attention
Hey Jetson
Deep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.
Stars: ✭ 161 (-11.54%)
Mutual labels:  attention
Asr syllable
基于卷积神经网络的语音识别声学模型的研究
Stars: ✭ 127 (-30.22%)
Mutual labels:  attention
Image Caption Generator
A neural network to generate captions for an image using CNN and RNN with BEAM Search.
Stars: ✭ 126 (-30.77%)
Mutual labels:  attention
Medical Transformer
Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation"
Stars: ✭ 153 (-15.93%)
Mutual labels:  attention
Ccnet Pure Pytorch
Criss-Cross Attention for Semantic Segmentation in pure Pytorch with a faster and more precise implementation.
Stars: ✭ 124 (-31.87%)
Mutual labels:  attention
Multimodal Sentiment Analysis
Attention-based multimodal fusion for sentiment analysis
Stars: ✭ 172 (-5.49%)
Mutual labels:  attention
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (-36.26%)
Mutual labels:  attention
Multihead Siamese Nets
Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task.
Stars: ✭ 144 (-20.88%)
Mutual labels:  attention
Rnn For Joint Nlu
Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)
Stars: ✭ 176 (-3.3%)
Mutual labels:  attention
Transformers.jl
Julia Implementation of Transformer models
Stars: ✭ 173 (-4.95%)
Mutual labels:  attention
Lrf Net
Learning Rich Features at High-Speed for Single-Shot Object Detection, ICCV, 2019
Stars: ✭ 160 (-12.09%)
Mutual labels:  pyramid

PAN-pytorch

A Pytorch implementation of Pyramid Attention Networks for Semantic Segmentation from 2018 paper by Hanchao Li, Pengfei Xiong, Jie An, Lingxue Wang. image

Installation

  • Env: Python3.6, Pytorch1.0-preview
  • Clone this repository.
  • Download the dataset by following the instructions below.

VOC2012 Dataset

The overall dataset is augmented by Semantic Boundaries Dataset, resulting in training data 10582 and test data 1449. https://www.sun11.me/blog/2018/how-to-use-10582-trainaug-images-on-DeeplabV3-code/

After preparing the data, please change the directory below for training.

training_data = Voc2012('/home/tom/DISK/DISK2/jian/PASCAL/VOC2012', 'train_aug', transform=train_transforms)
test_data = Voc2012('/home/tom/DISK/DISK2/jian/PASCAL/VOC2012', 'val',transform=test_transforms)

Evaluation

image

Pixel acc mIOU
93.19% 78.498%
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].