val-iisc / Cnn Fixations
Visualising predictions of deep neural networks
Stars: ✭ 87
Projects that are alternatives of or similar to Cnn Fixations
Resnetcam Keras
Keras implementation of a ResNet-CAM model
Stars: ✭ 269 (+209.2%)
Mutual labels: cnn, localization
Tf Mobilenet V2
Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow
Stars: ✭ 85 (-2.3%)
Mutual labels: cnn
Localizationkit ios
Realtime Dynamic localization translation delivery system for iOS and Mac OSX in Swift. Create and update texts from localization.com without needing to recompile or redeploy. Cocapod for iOS devices (iPad, iPhone, iPod Touch and Mac)
Stars: ✭ 1,206 (+1286.21%)
Mutual labels: localization
Ukfm
Unscented Kalman Filtering on (Parallelizable) Manifolds (UKF-M)
Stars: ✭ 82 (-5.75%)
Mutual labels: localization
Gatsby Starter Prismic I18n
Based on gatsby-starter-prismic with Internationalization (i18n) support
Stars: ✭ 77 (-11.49%)
Mutual labels: localization
Cnn For Stock Market Prediction Pytorch
CNN for stock market prediction using raw data & candlestick graph.
Stars: ✭ 86 (-1.15%)
Mutual labels: cnn
Single Human Parsing Lip
PSPNet implemented in PyTorch for single-person human parsing task, evaluating on Look Into Person (LIP) dataset.
Stars: ✭ 84 (-3.45%)
Mutual labels: cnn
Keys Translations Manager
KTM, a locale management web app built on MERN stack, lets you manage and control locales in one place. It's particularly useful for someone who needs to manage multiple internationalization/localization projects.
Stars: ✭ 81 (-6.9%)
Mutual labels: localization
Recursive Cnns
Implementation of my paper "Real-time Document Localization in Natural Images by Recursive Application of a CNN."
Stars: ✭ 80 (-8.05%)
Mutual labels: cnn
Odas web
A desktop visualization GUI for the ODAS library
Stars: ✭ 78 (-10.34%)
Mutual labels: localization
Crusader Kings Ii 2.6.3 Chinese Localization
Crusader Kings II（王国风云2）2.6.2、2.6.3 汉化包100%补完计划（基于52汉化组测试补丁）|王国风云2汉化|十字军之王2汉化|2.62汉化|2.63汉化
Stars: ✭ 83 (-4.6%)
Mutual labels: localization
Localizationprovider
Database driven localization provider for .NET applications (core assemblies)
Stars: ✭ 77 (-11.49%)
Mutual labels: localization
Tensorflow Cifar 10
Cifar-10 CNN implementation using TensorFlow library with 20% error.
Stars: ✭ 85 (-2.3%)
Mutual labels: cnn
Cnn Paper2
🎨 🎨 深度学习 卷积神经网络教程 ：图像识别，目标检测，语义分割，实例分割，人脸识别，神经风格转换，GAN等🎨🎨 https://dataxujing.github.io/CNN-paper2/
Stars: ✭ 77 (-11.49%)
Mutual labels: cnn
Urbannavdataset
UrbanNav: an Open-Sourcing Localization Data Collected in Asian Urban Canyons, Including Tokyo and Hong Kong
Stars: ✭ 79 (-9.2%)
Mutual labels: localization
Segan
A PyTorch implementation of SEGAN based on INTERSPEECH 2017 paper "SEGAN: Speech Enhancement Generative Adversarial Network"
Stars: ✭ 82 (-5.75%)
Mutual labels: cnn
Sentiment 2017 Imavis
From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction
Stars: ✭ 85 (-2.3%)
Mutual labels: cnn
CNN-Fixations
Code for the paper CNN fixations: An unravelling approach to identify discriminative image regions
Konda Reddy Mopuri, Utsav Garg, R. Venkatesh Babu
This repository can be used to visualize predictions for four CNNs namely: AlexNet, VGG-16, GoogLeNet and ResNet-101.
Usage Instructions
-
In the demo folder add path to caffe installation
-
Install the required dependencies
-
Navigate to the Demo folder and open a ipython notebook
Add the .caffemodels for the respective architechtures before running the codes
Samples
Results of running the demo for one image from ILSVRC validation set
AlexNet
VGG 16
GoogLeNet
ResNet 101
The VGG-16 demo now also has the option to use the TensorFlow backend in addition to the default Caffe backend. (Contributed by Joe Yearsley)
Contact Utsav Garg if you have questions.
If you use this work, please cite the paper:
CNN Fixations: An unraveling approach to visualize the discriminative image regions
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].