okankop / Vidaug
Licence: mit
Effective Video Augmentation Techniques for Training Convolutional Neural Networks
Stars: ✭ 178
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Vidaug
Lenet 5
PyTorch implementation of LeNet-5 with live visualization
Stars: ✭ 122 (-31.46%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Bender
Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.
Stars: ✭ 1,728 (+870.79%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Hyperdensenet
This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-30.34%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Har Keras Cnn
Human Activity Recognition (HAR) with 1D Convolutional Neural Network in Python and Keras
Stars: ✭ 97 (-45.51%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Self Driving Car
Udacity Self-Driving Car Engineer Nanodegree projects.
Stars: ✭ 2,103 (+1081.46%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Awslambdaface
Perform deep neural network based face detection and recognition in the cloud (via AWS lambda) with zero model configuration or tuning.
Stars: ✭ 98 (-44.94%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Deep Steganography
Hiding Images within other images using Deep Learning
Stars: ✭ 136 (-23.6%)
Mutual labels: deep-neural-networks, 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 (+616.85%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Models Comparison.pytorch
Code for the paper Benchmark Analysis of Representative Deep Neural Network Architectures
Stars: ✭ 148 (-16.85%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
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 (-19.66%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-45.51%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Tf Adnet Tracking
Deep Object Tracking Implementation in Tensorflow for 'Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning(CVPR 2017)'
Stars: ✭ 162 (-8.99%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Grenade
Deep Learning in Haskell
Stars: ✭ 1,338 (+651.69%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Top Deep Learning
Top 200 deep learning Github repositories sorted by the number of stars.
Stars: ✭ 1,365 (+666.85%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Fast Autoaugment
Official Implementation of 'Fast AutoAugment' in PyTorch.
Stars: ✭ 1,297 (+628.65%)
Mutual labels: convolutional-neural-networks, augmentation
Pytorch convlstm
convolutional lstm implementation in pytorch
Stars: ✭ 126 (-29.21%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Gcommandspytorch
ConvNets for Audio Recognition using Google Commands Dataset
Stars: ✭ 65 (-63.48%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Breast Cancer Classification
Breast Cancer Classification using CNN and transfer learning
Stars: ✭ 86 (-51.69%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Shainet
SHAInet - a pure Crystal machine learning library
Stars: ✭ 143 (-19.66%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Sign Language Interpreter Using Deep Learning
A sign language interpreter using live video feed from the camera.
Stars: ✭ 157 (-11.8%)
Mutual labels: deep-neural-networks, convolutional-neural-networks
Video Augmentation Techniques for Deep Learning
This python library helps you with augmenting videos for your deep learning architectures. It converts input videos into a new, much larger set of slightly altered videos.
Original Video
Requirements and installation
Required packages:
- numpy
- PIL
- scipy
- skimage
- OpenCV (i.e.
cv2)
For installation, simply use sudo pip install git+https://github.com/okankop/vidaug.
Alternatively, the repository can be download via git clone https://github.com/okankop/vidaug and installed by using python setup.py sdist && pip install dist/vidaug-0.1.tar.gz.
Examples
A classical video classification with CNN using augmentations on videos. Train on batches of images and augment each batch via random crop, random crop and horizontal flip:
from vidaug import augmentors as va
sometimes = lambda aug: va.Sometimes(0.5, aug) # Used to apply augmentor with 50% probability
seq = va.Sequential([
va.RandomCrop(size=(240, 180)), # randomly crop video with a size of (240 x 180)
va.RandomRotate(degrees=10), # randomly rotates the video with a degree randomly choosen from [-10, 10]
sometimes(va.HorizontalFlip()) # horizontally flip the video with 50% probability
])
for batch_idx in range(1000):
# 'video' should be either a list of images from type of numpy array or PIL images
video = load_batch(batch_idx)
video_aug = seq(video)
train_on_video(video)
The videos below show examples for most augmentation techniques:
| Augmentation Type | Augmented Video |
|---|---|
| Piecewise Affine Transform |  |
| Superpixel |  |
| Gausian Blur |  |
| Invert Color |  |
| Rondom Rotate |  |
| Random Resize |  |
| Translate |  |
| Center Crop |  |
| Horizontal Flip |  |
| Vertical Flip |  |
| Add |  |
| Multiply |  |
| Downsample |  |
| Upsample |  |
| Elastic Transformation |  |
| Salt |  |
| Pepper |  |
| Shear |  |
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].