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 → lidq92 → Cnniqa

lidq92 / Cnniqa

CVPR2014-Convolutional neural networks for no-reference image quality assessment

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchconvolutional-neural-networks

Projects that are alternatives of or similar to Cnniqa

Reinforcement Learning For Self Driving Cars
Project on design and implement neural network that maximises driving speed of self-driving car through reinforcement learning.
Stars: ✭ 85 (-11.46%)
Mutual labels:  convolutional-neural-networks
Fast Autoaugment
Official Implementation of 'Fast AutoAugment' in PyTorch.
Stars: ✭ 1,297 (+1251.04%)
Mutual labels:  convolutional-neural-networks
Projectaiai
AiAi.care project is teaching computers to "see" chest X-rays and interpret them how a human Radiologist would. We are using 700,000 Chest X-Rays + Deep Learning to build an FDA 💊 approved, open-source screening tool for Tuberculosis and Lung Cancer. After an MRMC clinical trial, AiAi CAD will be distributed for free to emerging nations, charitable hospitals, and organizations like WHO 🌏 We will also release our pretrained models and weights as Medical Imagenet.
Stars: ✭ 92 (-4.17%)
Mutual labels:  convolutional-neural-networks
Text classification
Text Classification Algorithms: A Survey
Stars: ✭ 1,276 (+1229.17%)
Mutual labels:  convolutional-neural-networks
Trained Ternary Quantization
Reducing the size of convolutional neural networks
Stars: ✭ 90 (-6.25%)
Mutual labels:  convolutional-neural-networks
Label Reg
(This repo is no longer up-to-date. Any updates will be at https://github.com/DeepRegNet/DeepReg/) A demo of the re-factored label-driven registration code, based on "Weakly-supervised convolutional neural networks for multimodal image registration"
Stars: ✭ 91 (-5.21%)
Mutual labels:  convolutional-neural-networks
Tensorflow Cifar 10
Cifar-10 CNN implementation using TensorFlow library with 20% error.
Stars: ✭ 85 (-11.46%)
Mutual labels:  convolutional-neural-networks
Cardiac Segmentation
Convolutional Neural Networks for Cardiac Segmentation
Stars: ✭ 94 (-2.08%)
Mutual labels:  convolutional-neural-networks
Kerasr
R interface to the keras library
Stars: ✭ 90 (-6.25%)
Mutual labels:  convolutional-neural-networks
Incremental Learning
Pytorch implementation of ACCV18 paper "Revisiting Distillation and Incremental Classifier Learning."
Stars: ✭ 92 (-4.17%)
Mutual labels:  convolutional-neural-networks
Capsnet Pytorch
My attempt at implementing CapsNet from the paper Dynamic Routing Between Capsules
Stars: ✭ 87 (-9.37%)
Mutual labels:  convolutional-neural-networks
Deep Learning For Beginners
videos, lectures, blogs for Deep Learning
Stars: ✭ 89 (-7.29%)
Mutual labels:  convolutional-neural-networks
3dunet abdomen cascade
Stars: ✭ 91 (-5.21%)
Mutual labels:  convolutional-neural-networks
Niftynet
[unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy
Stars: ✭ 1,276 (+1229.17%)
Mutual labels:  convolutional-neural-networks
Dped
Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks
Stars: ✭ 1,315 (+1269.79%)
Mutual labels:  convolutional-neural-networks
Breast Cancer Classification
Breast Cancer Classification using CNN and transfer learning
Stars: ✭ 86 (-10.42%)
Mutual labels:  convolutional-neural-networks
Image Quality Assessment
Convolutional Neural Networks to predict the aesthetic and technical quality of images.
Stars: ✭ 1,300 (+1254.17%)
Mutual labels:  convolutional-neural-networks
Grenade
Deep Learning in Haskell
Stars: ✭ 1,338 (+1293.75%)
Mutual labels:  convolutional-neural-networks
Fakeimagedetector
Image Tampering Detection using ELA and CNN
Stars: ✭ 93 (-3.12%)
Mutual labels:  convolutional-neural-networks
Core50
CORe50: a new Dataset and Benchmark for Continual Learning
Stars: ✭ 91 (-5.21%)
Mutual labels:  convolutional-neural-networks
View All Similar Projects ➔

CNNIQA

PyTorch 1.3 implementation of the following paper: Kang L, Ye P, Li Y, et al. Convolutional neural networks for no-reference image quality assessment[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 1733-1740.

Note

  • The optimizer is chosen as Adam here, instead of the SGD with momentum in the paper.
  • the mat files in data/ are the information extracted from the datasets and the index information about the train/val/test split. The subjective scores of LIVE is from the realigned data.

Training

CUDA_VISIBLE_DEVICES=0 python main.py --exp_id=0 --database=LIVE

Before training, the im_dir in config.yaml must to be specified. Train/Val/Test split ratio in intra-database experiments can be set in config.yaml (default is 0.6/0.2/0.2).

Evaluation

Test Demo

python test_demo.py --im_path=data/I03_01_1.bmp

Cross Dataset

python test_cross_dataset.py --help

TODO: add metrics calculation. SROCC, KROCC can be easily get. PLCC, RMSE, MAE, OR should be calculated after a non-linear fitting since the quality score ranges are not the same across different IQA datasets.

Visualization

tensorboard --logdir=tensorboard_logs --port=6006 # in the server (host:port)
ssh -p port -L 6006:localhost:6006 [email protected] # in your PC. See the visualization in your PC

Requirements

conda create -n reproducibleresearch pip python=3.6
source activate reproducibleresearch
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
source deactive

Note: You need to install the right CUDA version.

TODO (If I have free time)

  • Simplify the code
  • Report results on some common databases
  • etc.
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].