lightnn
The light(`light` means not many codes here) deep learning framework for study and for fun. Join us!
How to install
pip install
pip install lightnn
python install
python setup.py install
Modual structure
models
activations
- identity(None)
- sigmoid
- relu
- softmax
- tanh
- leaky relu
- elu
- selu
- thresholded relu
- softplus
- softsign
- hard sigmoid
losses
- MeanSquareLoss
- BinaryCategoryLoss
- LogLikelihoodLoss
- FocalLoss
initializers
- zeros
- ones
- xavier uniform initializer(glorot uniform initializer)
- default weight initializer
- large weight initializer
- orthogonal initializer
optimizers
- SGD
- Momentum(Nestrov included)
- RMSProp
- Adam
- Adagrad
- Adadelta
layers
- FullyConnected(Dense)
- Conv2d
- MaxPooling
- AvgPooling
- Softmax
- Dropout
- Flatten
- Activation
- RNN
- LSTM
- GRU
utils
- label smoothing
- sparse to dense
gradient check
- Dense
- CNN and Pooling
- RNN, LSTM and GRU
examples
- MLP MNIST Classification
- CNN MNIST Classification
- RNN Language Model
- LSTM Language Model
- GRU Language Model
Document instructions
- English for classes and functions
- Chinese for annotation
References
- Keras: a polular deep learning framework based on tensorflow and theano.
- NumpyDL: a simple deep learning framework with manual-grad, totally written with python and numpy.([Warning] Some errors in
backward part of this project)
- paradox: a simple deep learning framework with symbol calculation system. Lightweight for learning and for fun. It's totally written with python and numpy.
- Bingtao Han's blogs: easy way to go for deep learning([Warning] Some calculation errors in
RNN part).
