All Projects → zjjMaiMai → Deep Alignment Network A Convolutional Neural Network For Robust Face Alignment
zjjMaiMai / Deep Alignment Network A Convolutional Neural Network For Robust Face Alignment
This is a Tensorflow implementations of paper "Deep Alignment Network: A convolutional neural network for robust face alignment".
Stars: ✭ 219
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Deep Alignment Network A Convolutional Neural Network For Robust Face Alignment
Cnn 3d Images Tensorflow
3D image classification using CNN (Convolutional Neural Network)
Stars: ✭ 199 (-9.13%)
Mutual labels: convolutional-neural-networks
Caffe Deepbinarycode
Supervised Semantics-preserving Deep Hashing (TPAMI18)
Stars: ✭ 206 (-5.94%)
Mutual labels: convolutional-neural-networks
Dynamic Training Bench
Simplify the training and tuning of Tensorflow models
Stars: ✭ 210 (-4.11%)
Mutual labels: convolutional-neural-networks
Image To 3d Bbox
Build a CNN network to predict 3D bounding box of car from 2D image.
Stars: ✭ 200 (-8.68%)
Mutual labels: convolutional-neural-networks
Deep Mri Reconstruction
Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction: Implementation & Demo
Stars: ✭ 204 (-6.85%)
Mutual labels: convolutional-neural-networks
Metalimage
MetalImage is more faster and powerful than opengles for iOS. It is very similar to GPUImage framework, but perform a better 3D rendering and multithreads computing abilities.
Stars: ✭ 207 (-5.48%)
Mutual labels: convolutional-neural-networks
Miscnn
A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
Stars: ✭ 194 (-11.42%)
Mutual labels: convolutional-neural-networks
Grad cam plus plus
A generalized gradient-based CNN visualization technique
Stars: ✭ 216 (-1.37%)
Mutual labels: convolutional-neural-networks
Graph Cnn In 3d Point Cloud Classification
Code for A GRAPH-CNN FOR 3D POINT CLOUD CLASSIFICATION (ICASSP 2018)
Stars: ✭ 206 (-5.94%)
Mutual labels: convolutional-neural-networks
Im2latex Tensorflow
Tensorflow implementation of the HarvardNLP paper - What You Get Is What You See: A Visual Markup Decompiler (https://arxiv.org/pdf/1609.04938v1.pdf)
Stars: ✭ 207 (-5.48%)
Mutual labels: convolutional-neural-networks
Iseebetter
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
Stars: ✭ 202 (-7.76%)
Mutual labels: convolutional-neural-networks
Neurite
Neural networks toolbox focused on medical image analysis
Stars: ✭ 203 (-7.31%)
Mutual labels: convolutional-neural-networks
Style transfer
CNN image style transfer 🎨.
Stars: ✭ 210 (-4.11%)
Mutual labels: convolutional-neural-networks
Traffic Sign Detection
Traffic Sign Detection. Code for the paper entitled "Evaluation of deep neural networks for traffic sign detection systems".
Stars: ✭ 200 (-8.68%)
Mutual labels: convolutional-neural-networks
Transfer Learning Suite
Transfer Learning Suite in Keras. Perform transfer learning using any built-in Keras image classification model easily!
Stars: ✭ 212 (-3.2%)
Mutual labels: convolutional-neural-networks
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (-10.96%)
Mutual labels: convolutional-neural-networks
Mobilenet V2
A Complete and Simple Implementation of MobileNet-V2 in PyTorch
Stars: ✭ 206 (-5.94%)
Mutual labels: convolutional-neural-networks
3dmmasstn
MatConvNet implementation for incorporating a 3D Morphable Model (3DMM) into a Spatial Transformer Network (STN)
Stars: ✭ 218 (-0.46%)
Mutual labels: convolutional-neural-networks
Tfwss
Weakly Supervised Segmentation with Tensorflow. Implements instance segmentation as described in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).
Stars: ✭ 212 (-3.2%)
Mutual labels: convolutional-neural-networks
Cnn From Scratch
A scratch implementation of Convolutional Neural Network in Python using only numpy and validated over CIFAR-10 & MNIST Dataset
Stars: ✭ 210 (-4.11%)
Mutual labels: convolutional-neural-networks
Deep Alignment Network: A convolutional neural network for robust face alignment
This is a Tensorflow implementations of paper "Deep Alignment Network: A convolutional neural network for robust face alignment". You can see Original implementation here.
System
- No Windows !
Getting started
- Tensorflow 1.7.0
- OpenCV 3.1.0 or newer
Train Model
- Download Datasets.
- Put
images & ptsinSAMEfolder. - Write mirror file. There is a 68 landmark mirror file. download
- Preprocess.
python preprocessing.py --input_dir=... --output_dir=... --istrain=True --repeat=10 --img_size=112 --mirror_file=./Mirror68.txt
- Train model.
python DAN_V2.py -ds 1 --data_dir=preprocess_output_dir --data_dir_test=...orNone -nlm 68 -te=15 -epe=1 -mode train
python DAN_V2.py -ds 2 --data_dir=preprocess_output_dir --data_dir_test=...orNone -nlm 68 -te=45 -epe=1 -mode train
Eval Acc
- Download Datasets for test.
- Put
images & ptsinSAMEfolder. - Preprocess.
python preprocessing.py --input_dir=... --output_dir=... --istrain=False --img_size=112
- Eval model Acc.
python DAN_V2.py -ds 2 --data_dir=preprocess_output_dir -nlm 68 -mode eval
Results on 300W
- Speed : 4ms per Image on GTX 1080 Ti
- Err :
1.34 %on 300W common subset(bounding box diagonal normalization).
Pre-trained Model
TODO:You can download pre-trained model here. This model trained on 300W dataset.
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].