The deeplearning algorithms are carefully implemented by tensorflow.
- Python 3.5
- tensorflow 1.4
- pytorch 0.2.0
- Logistic Regression logisticRegression.py
- Multi-Layer Perceptron (MLP) mlp.py
- Convolution Neural Network (CNN) cnn.py
- Denoising Aotoencoder (DA) da.py
- Stacked Denoising Autoencoder (SDA) sda.py
- Restricted Boltzmann Machine (RBM) [rbm.py gbrbm.py]
- Deep Belief Network (DBN) dbn.py
Note: the project aims at imitating the well-implemented algorithms in Deep Learning Tutorials (coded by Theano).
- MobileNet [self paper ref]
- SqueezeNet [self paper]
- ResNet [self caffe ref paper1 paper2]
- ShuffleNet [self by pytorch paper]
- DenseNet [self pytorch_ref paper]
You can find more practical examples with tensorflow here:
- CNN for setence classification [self] [blog] [paper]
- RNN for language model [self] [blog] [blog_cn]
- LSTM for language model (PTB data) [self] [tutorial] [paper]
- VGG model for image classification (object recongnition) [self] [source]
- Residual network for cifar10_dataset [self] [source] [paper]
- LSTM for time series prediction [self] [source]
- Generative adversarial network (GAN) [self]
- Variational autoencoder (VAE) [self]
- Tensorflow for RNNs [tf_rnn.ipynb]
- Tensorflow for Autoencoder [tf_autoencoder.ipynb]
- ageron/handson-ml
- Hvass-Labs/TensorFlow-Tutorials
- BinRoot/TensorFlow-Book
- sjchoi86/dl_tutorials_10weeks
