GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → adityac94 → Grad_cam_plus_plus

adityac94 / Grad_cam_plus_plus

A generalized gradient-based CNN visualization technique

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningtensorflowconvolutional-neural-networkscnn

Projects that are alternatives of or similar to Grad cam plus plus

Style transfer
CNN image style transfer 🎨.
Stars: ✭ 210 (-2.78%)
Mutual labels:  convolutional-neural-networks, cnn
Transfer Learning Suite
Transfer Learning Suite in Keras. Perform transfer learning using any built-in Keras image classification model easily!
Stars: ✭ 212 (-1.85%)
Mutual labels:  convolutional-neural-networks, cnn
Tf Adnet Tracking
Deep Object Tracking Implementation in Tensorflow for 'Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning(CVPR 2017)'
Stars: ✭ 162 (-25%)
Mutual labels:  convolutional-neural-networks, cnn
Image classifier
CNN image classifier implemented in Keras Notebook 🖼️.
Stars: ✭ 139 (-35.65%)
Mutual labels:  convolutional-neural-networks, cnn
Depression Detect
Predicting depression from acoustic features of speech using a Convolutional Neural Network.
Stars: ✭ 187 (-13.43%)
Mutual labels:  convolutional-neural-networks, cnn
Livianet
This repository contains the code of LiviaNET, a 3D fully convolutional neural network that was employed in our work: "3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study"
Stars: ✭ 143 (-33.8%)
Mutual labels:  convolutional-neural-networks, cnn
Cnnimageretrieval
CNN Image Retrieval in MatConvNet: Training and evaluating CNNs for Image Retrieval in MatConvNet
Stars: ✭ 168 (-22.22%)
Mutual labels:  convolutional-neural-networks, cnn
Lenet 5
PyTorch implementation of LeNet-5 with live visualization
Stars: ✭ 122 (-43.52%)
Mutual labels:  convolutional-neural-networks, cnn
Bilinear Cnn Tensorflow
This is an implementation of Bilinear CNN for fine grained visual recognition using TensorFlow.
Stars: ✭ 187 (-13.43%)
Mutual labels:  convolutional-neural-networks, cnn
Anime4k
A High-Quality Real Time Upscaler for Anime Video
Stars: ✭ 14,083 (+6419.91%)
Mutual labels:  convolutional-neural-networks, cnn
Pytorch convlstm
convolutional lstm implementation in pytorch
Stars: ✭ 126 (-41.67%)
Mutual labels:  convolutional-neural-networks, cnn
Cnn 3d Images Tensorflow
3D image classification using CNN (Convolutional Neural Network)
Stars: ✭ 199 (-7.87%)
Mutual labels:  convolutional-neural-networks, cnn
Motionblur Detection By Cnn
Stars: ✭ 126 (-41.67%)
Mutual labels:  convolutional-neural-networks, cnn
Simple cnn
Simple Convolutional Neural Network Library
Stars: ✭ 158 (-26.85%)
Mutual labels:  convolutional-neural-networks, cnn
Hyperdensenet
This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-42.59%)
Mutual labels:  convolutional-neural-networks, cnn
Iresnet
Improved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: ✭ 163 (-24.54%)
Mutual labels:  convolutional-neural-networks, cnn
Deepway
This project is an aid to the blind. Till date there has been no technological advancement in the way the blind navigate. So I have used deep learning particularly convolutional neural networks so that they can navigate through the streets.
Stars: ✭ 118 (-45.37%)
Mutual labels:  convolutional-neural-networks, cnn
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (-44.44%)
Mutual labels:  convolutional-neural-networks, cnn
Autoclint
A specially designed light version of Fast AutoAugment
Stars: ✭ 171 (-20.83%)
Mutual labels:  convolutional-neural-networks, cnn
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (-9.72%)
Mutual labels:  convolutional-neural-networks, cnn
View All Similar Projects ➔

Grad-CAM++

A generalized gradient-based CNN visualization technique code for the paper:

Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

To be presented at WACV 2018,
Authors:
Aditya Chattopadhyay*, Anirban Sarkar*, Prantik Howlader* and Vineeth N Balasubramanian,
(* equal contribution)

Gradcam++ Architecture

alt text

Performance of grad-cam++ with respect to grad-cam

alt text Above we do a comparision of the performance of gradcam++ with respect to grad-cam. Gradcam++ does a better image localization that Gradcam, not only in scenarios where there is more than one object of same class in an image, but also in cases where there is a single object in an image.

Implementation in python using tensorflow 1.3.
Kindly download the pretrained weights of the vgg16 network (vgg16.npy) from the following link, and copy the file to the models/ subdirectory.
https://drive.google.com/drive/folders/0BzS5KZjihEdyUjBHcGFNRnk4bFU?usp=sharing

USAGE:

python classify.py -f images/water-bird.JPEG -gpu 3 -o output.jpeg

Arguments:

  • f: path to input image
  • gpu: the gpu id to use, 0-indexed
  • l: class label, default is -1 (chooses the class predicted by the model)
  • o: Specify output file name for Grad-CAM++ visualization, default is output.jpeg. All results would be saved in the output/ subdirectory.

For Help:

python classify.py -h

The above code is for the vgg16 network, pre-trained on imagenet.
We tested our code on tensorflow 1.3, compatibility with other versions is not guaranteed.

Acknowledgements

Parts of the code have been borrowed and modified from:

For the Grad-CAM tensorflow implementation

https://github.com/Ankush96/grad-cam.tensorflow
https://github.com/insikk/Grad-CAM-tensorflow

For porting pre-trained vgg16-model from caffe model zoo to tensorflow

https://github.com/ry/tensorflow-vgg16

If using this code, please cite our work:

 @article{chattopadhyay2017grad,
  title={Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks},
  author={Chattopadhyay, Aditya and Sarkar, Anirban and Howlader, Prantik and Balasubramanian, Vineeth N},
  journal={arXiv preprint arXiv:1710.11063},
  year={2017}
}
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].