parasdahal / Deepnet
Licence: mit
Implementation of CNNs, RNNs, and many deep learning techniques in plain Numpy.
Stars: ✭ 285
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Deepnet
Tensorflow Mnist Cnn
MNIST classification using Convolutional NeuralNetwork. Various techniques such as data augmentation, dropout, batchnormalization, etc are implemented.
Stars: ✭ 182 (-36.14%)
Mutual labels: cnn, dropout
Svhn Cnn
Google Street View House Number(SVHN) Dataset, and classifying them through CNN
Stars: ✭ 44 (-84.56%)
Mutual labels: cnn, dropout
Tensorflow Tutorial
Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学
Stars: ✭ 4,122 (+1346.32%)
Mutual labels: cnn, dropout
Ailearnnotes
Artificial Intelligence Learning Notes.
Stars: ✭ 195 (-31.58%)
Mutual labels: cnn, dropout
social-cnn-pytorch
Human Trajectory Prediction in Socially Interacting Crowds Using a CNN-based Architecture
Stars: ✭ 24 (-91.58%)
Mutual labels: cnn
Named Entity Recognition With Bidirectional Lstm Cnns
Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs
Stars: ✭ 283 (-0.7%)
Mutual labels: cnn
In Prestissimo
A very fast neural network computing framework optimized for mobile platforms.QQ group: 676883532 【验证信息输：绝影】
Stars: ✭ 268 (-5.96%)
Mutual labels: cnn
Facedetection
C++ project to implement MTCNN, a perfect face detect algorithm, on different DL frameworks. The most popular frameworks: caffe/mxnet/tensorflow, are all suppported now
Stars: ✭ 255 (-10.53%)
Mutual labels: cnn
Caffe Hrt
Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original Caffe architecture which users deploy their applications seamlessly.
Stars: ✭ 271 (-4.91%)
Mutual labels: cnn
deep-learning-coursera-complete
Deep Learning Specialization by Andrew Ng on Coursera - My Completed Coursework Repo - All 5 Courses
Stars: ✭ 104 (-63.51%)
Mutual labels: cnn
RCAN-tf
TensorFlow code for ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"
Stars: ✭ 25 (-91.23%)
Mutual labels: cnn
Ffdnet
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising (TIP, 2018)
Stars: ✭ 274 (-3.86%)
Mutual labels: cnn
Handwritingrecognitionsystem
Handwriting Recognition System based on a deep Convolutional Recurrent Neural Network architecture
Stars: ✭ 262 (-8.07%)
Mutual labels: cnn
Facial Expression Recognition Using Cnn
Deep facial expressions recognition using Opencv and Tensorflow. Recognizing facial expressions from images or camera stream
Stars: ✭ 261 (-8.42%)
Mutual labels: cnn
deepnet
Implementations of CNNs, RNNs and cool new techniques in deep learning
Note: deepnet is a work in progress and things will be added gradually. It is not intended for production, use it to learn and study implementations of latest and greatest in deep learning.
What does it have?
Network Architecture
- Convolutional net
- Feed forward net
- Recurrent net (LSTM/GRU coming soon)
Optimization Algorithms
- SGD
- SGD with momentum
- Nesterov Accelerated Gradient
- Adagrad
- RMSprop
- Adam
Regularization
- Dropout
- L1 and L2 Regularization
Cool Techniques
- BatchNorm
- Xavier Weight Initialization
Nonlinearities
- ReLU
- Sigmoid
- tanh
Usage
-
virtualenv .env; create a virtual environment -
source .env/bin/activate; activate the virtual environment -
pip install -r requirements.txt; Install dependencies -
python run_cnn.py {mnist|cifar10}; mnist for shallow cnn and cifar10 for deep cnn
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].