Eyyub / Numpy Convnet
A small and pure Numpy Convolutional Neural Network library.
Stars: ✭ 50
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Numpy Convnet
Numpycnn
Building Convolutional Neural Networks From Scratch using NumPy
Stars: ✭ 436 (+772%)
Mutual labels: convolutional-neural-networks, numpy
Thesemicolon
This repository contains Ipython notebooks and datasets for the data analytics youtube tutorials on The Semicolon.
Stars: ✭ 345 (+590%)
Mutual labels: convolutional-neural-networks, numpy
Antsrnet
Medical image analysis framework merging ANTsR and deep learning
Stars: ✭ 42 (-16%)
Mutual labels: convolutional-neural-networks
Accurate Binary Convolution Network
Binary Convolution Network for faster real-time processing in ASICs
Stars: ✭ 49 (-2%)
Mutual labels: convolutional-neural-networks
Data Science Complete Tutorial
For extensive instructor led learning
Stars: ✭ 1,027 (+1954%)
Mutual labels: numpy
Svhn Cnn
Google Street View House Number(SVHN) Dataset, and classifying them through CNN
Stars: ✭ 44 (-12%)
Mutual labels: convolutional-neural-networks
Meshcnn
Convolutional Neural Network for 3D meshes in PyTorch
Stars: ✭ 1,032 (+1964%)
Mutual labels: convolutional-neural-networks
Computervision Recipes
Best Practices, code samples, and documentation for Computer Vision.
Stars: ✭ 8,214 (+16328%)
Mutual labels: convolutional-neural-networks
Ncar Python Tutorial
Numerical & Scientific Computing with Python Tutorial
Stars: ✭ 50 (+0%)
Mutual labels: numpy
Ml In Tf
Get started with Machine Learning in TensorFlow with a selection of good reads and implemented examples!
Stars: ✭ 45 (-10%)
Mutual labels: convolutional-neural-networks
Eulerian Remote Heartrate Detection
Remote heart rate detection through Eulerian magnification of face videos
Stars: ✭ 48 (-4%)
Mutual labels: numpy
Yolo tensorflow
🚖 Object Detection (YOLOv1) implentation in tensorflow, with training, testing and video features.
Stars: ✭ 45 (-10%)
Mutual labels: convolutional-neural-networks
Wynullview
An easy way to use for view's empty state 一行代码显示空视图,高度自定义
Stars: ✭ 44 (-12%)
Mutual labels: numpy
Keras Sincnet
Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)
Stars: ✭ 47 (-6%)
Mutual labels: convolutional-neural-networks
Efficientnas
Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906
Stars: ✭ 44 (-12%)
Mutual labels: convolutional-neural-networks
Tensorflow Cnn Time Series
Feeding images of time series to Conv Nets! (Tensorflow + Keras)
Stars: ✭ 49 (-2%)
Mutual labels: convolutional-neural-networks
Machine Learning
notebooks with example for machine learning examples
Stars: ✭ 45 (-10%)
Mutual labels: numpy
Iml
Курс "Введение в машинное обучение" (ВМК, МГУ имени М.В. Ломоносова)
Stars: ✭ 46 (-8%)
Mutual labels: numpy
Numerical Linear Algebra
Free online textbook of Jupyter notebooks for fast.ai Computational Linear Algebra course
Stars: ✭ 8,263 (+16426%)
Mutual labels: numpy
numpy-convnet
A small and pure Numpy Convolutional Neural Network library I wrote in order to understand backprop through conv layers.
Example
Here is an example on how to build a not-so-deep convnet that uses strided convolution:
layers = [
Conv((4, 4, 1, 20), strides=2, activation=lkrelu, filter_init=lambda shp: np.random.normal(size=shp)),
Conv((5, 5, 20, 40), strides=2, activation=lkrelu, filter_init=lambda shp: np.random.normal(size=shp)),
Flatten((5, 5, 40)),
FullyConnected((5*5*40, 100), activation=sigmoid, weight_init=lambda shp: np.random.normal(size=shp)),
FullyConnected((100, 10), activation=linear, weight_init=lambda shp: np.random.normal(size=shp))
]
net = Network(layers, lr=0.001, loss=cross_entropy)
You can see that it somehow takes inspiration from Keras.
Requirements
- Python 2.7
- Numpy
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].