conan7882 / Cnn Visualization
Licence: mit
TensorFlow implementations of visualization of convolutional neural networks, such as Grad-Class Activation Mapping and guided back propagation
Stars: ✭ 194
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Cnn Visualization
Slot filling intent joint model
attention based joint model for intent detection and slot filling
Stars: ✭ 175 (-9.79%)
Mutual labels: cnn
Speech Emotion Recognition
Speech emotion recognition implemented in Keras (LSTM, CNN, SVM, MLP) | 语音情感识别
Stars: ✭ 181 (-6.7%)
Mutual labels: cnn
Depression Detect
Predicting depression from acoustic features of speech using a Convolutional Neural Network.
Stars: ✭ 187 (-3.61%)
Mutual labels: cnn
Vincent Ai Artist
Style transfer using deep convolutional neural nets
Stars: ✭ 176 (-9.28%)
Mutual labels: cnn
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (-7.73%)
Mutual labels: cnn
Anime4k
A High-Quality Real Time Upscaler for Anime Video
Stars: ✭ 14,083 (+7159.28%)
Mutual labels: cnn
Autoclint
A specially designed light version of Fast AutoAugment
Stars: ✭ 171 (-11.86%)
Mutual labels: cnn
Did Mdn
Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)
Stars: ✭ 192 (-1.03%)
Mutual labels: cnn
Hand tracking samples
👋 👌 research codebase for depth-based hand pose estimation using dynamics based tracking and CNNs
Stars: ✭ 180 (-7.22%)
Mutual labels: cnn
Freihand
A dataset for estimation of hand pose and shape from single color images.
Stars: ✭ 187 (-3.61%)
Mutual labels: cnn
Sentence Classification
Sentence Classifications with Neural Networks
Stars: ✭ 177 (-8.76%)
Mutual labels: cnn
Lidc nodule detection
lidc nodule detection with CNN and LSTM network
Stars: ✭ 187 (-3.61%)
Mutual labels: cnn
Paircnn Ranking
A tensorflow implementation of Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks
Stars: ✭ 176 (-9.28%)
Mutual labels: cnn
Beauty Net
A simple, flexible, and extensible template for PyTorch. It's beautiful.
Stars: ✭ 190 (-2.06%)
Mutual labels: cnn
Tensorflow Mnist Cnn
MNIST classification using Convolutional NeuralNetwork. Various techniques such as data augmentation, dropout, batchnormalization, etc are implemented.
Stars: ✭ 182 (-6.19%)
Mutual labels: cnn
Cnn Re Tf
Convolutional Neural Network for Multi-label Multi-instance Relation Extraction in Tensorflow
Stars: ✭ 190 (-2.06%)
Mutual labels: cnn
Bilinear Cnn Tensorflow
This is an implementation of Bilinear CNN for fine grained visual recognition using TensorFlow.
Stars: ✭ 187 (-3.61%)
Mutual labels: cnn
Visualization of Deep Covolutional Neural Networks
- This repository contains implementations of visualizatin of CNN in recent papers.
- The source code in the repository can be used to demostrate the algorithms as well as test on your own data.
Requirements
- Python 3.3+
- Tensorflow 1.3
- TensorCV
Algorithms
- Visulization of filters and feature maps of GoogLeNet
- Deconvolutional Networks (ECCV'14)
- Guided back propagation (2014)
- Class Activation Mapping (CAM) (CVPR'16)
- Gradient-weighted Class Activation Mapping (Grad-CAM) (ICCV'17)
Visulization of filters and feature maps of GoogLeNet
- The most straightforward approach to visualize a CNN is to show the feature maps (activations) and filters.
- Details of the implementation and more results can be found here
Deconvnet
- Pick a specific activation on a feature map and set other activation to zeros, then reconstruct an image by mapping back this new feature map to input pixel space.
- Details of the implementation and more results can be found here. Some results:
Guided back propagation
- Details of the implementation and more results can be found here. Some results:
Class Activation Mapping (CAM)
- The class activation map highlights the most informative image regions relevant to the predicted class. This map can be obtained by adding a global average pooling layer at the end of convolutional layers.
- Details of the implementation and more results can be found here. Some results:
Gradient-weighted Class Activation Mapping (Grad-CAM)
- Grad-CAM generates similar class heatmap as CAM, but it does not require to re-train the model for visualizatin.
- Details of the implementation and more results can be found here. Some results:
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].