All Projects → tsurumeso → chainer-grad-cam

tsurumeso / chainer-grad-cam

Licence: MIT license
Chainer implementation of Grad-CAM

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to chainer-grad-cam

Chainer Cifar10
Various CNN models for CIFAR10 with Chainer
Stars: ✭ 134 (+570%)
Mutual labels:  chainer, resnet
mxnet-retrain
Create mxnet finetuner (retrain) for mac/linux ,no need install docker and supports CPU, GPU(eGpu/cudnn).support the inception,resnet ,squeeznet,mobilenet...
Stars: ✭ 32 (+60%)
Mutual labels:  resnet
Deep metric learning
Deep metric learning methods implemented in Chainer
Stars: ✭ 153 (+665%)
Mutual labels:  chainer
Einops
Deep learning operations reinvented (for pytorch, tensorflow, jax and others)
Stars: ✭ 4,022 (+20010%)
Mutual labels:  chainer
Imgclsmob
Sandbox for training deep learning networks
Stars: ✭ 2,405 (+11925%)
Mutual labels:  chainer
kawaii creator
Photo to illustration converter
Stars: ✭ 79 (+295%)
Mutual labels:  chainer
Eend
End-to-End Neural Diarization
Stars: ✭ 153 (+665%)
Mutual labels:  chainer
Xtreme-Vision
A High Level Python Library to empower students, developers to build applications and systems enabled with computer vision capabilities.
Stars: ✭ 77 (+285%)
Mutual labels:  resnet
grad-cam-text
Implementation of Grad-CAM for text.
Stars: ✭ 37 (+85%)
Mutual labels:  grad-cam
Fcn
Chainer Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
Stars: ✭ 211 (+955%)
Mutual labels:  chainer
Bert Chainer
Chainer implementation of "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding"
Stars: ✭ 205 (+925%)
Mutual labels:  chainer
Nnpulearning
Non-negative Positive-Unlabeled (nnPU) and unbiased Positive-Unlabeled (uPU) learning reproductive code on MNIST and CIFAR10
Stars: ✭ 181 (+805%)
Mutual labels:  chainer
MQBench Quantize
QAT(quantize aware training) for classification with MQBench
Stars: ✭ 29 (+45%)
Mutual labels:  resnet
Pai
Resource scheduling and cluster management for AI
Stars: ✭ 2,223 (+11015%)
Mutual labels:  chainer
Distributed-ResNet-Tensorflow
A Distributed ResNet on multi-machines each with one GPU card.
Stars: ✭ 20 (+0%)
Mutual labels:  resnet
CNN-models
YOLO-v2, ResNet-32, GoogLeNet-lite
Stars: ✭ 32 (+60%)
Mutual labels:  resnet
Alpha Zero General
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
Stars: ✭ 2,617 (+12985%)
Mutual labels:  chainer
sharpmask
TensorFlow implementation of DeepMask and SharpMask
Stars: ✭ 31 (+55%)
Mutual labels:  resnet
Portrait FCN and 3D Reconstruction
This project is to convert PortraitFCN+ (by Xiaoyong Shen) from Matlab to Tensorflow, then refine the outputs from it (converted to a trimap) using KNN and ResNet, supervised by Richard Berwick.
Stars: ✭ 61 (+205%)
Mutual labels:  resnet
pyner
🌈 Implementation of Neural Network based Named Entity Recognizer (Lample+, 2016) using Chainer.
Stars: ✭ 45 (+125%)
Mutual labels:  chainer

chainer-grad-cam

Chainer implementation of Grad-CAM [1]. Grad-CAM can localize and highlight important region in the image for predicting the concept without changing the model architecture. Currently, this implementation supports AlexNet, VGGNet and ResNet.

Summary

Grad-CAM Guided Backpropagation Guided Grad-CAM
Boxer (242)
Tiger Cat (282)

Requirements

  • Chainer
  • Cupy (for GPU support)
  • OpenCV

Usage

python run.py --input images/dog_cat.png --label 242 --layer conv5_3 --gpu 0
python run.py --input images/dog_cat.png --label 282 --layer conv5_3 --gpu 0

References

  • [1] Ramprasaath R. Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra, "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization", https://arxiv.org/abs/1610.02391
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].