What I cannot create, I do not understand - Richard Feynman
A directed acyclic computational graph builder, built from scratch on
C, with auto-differentiation supported.
This was not just another deep learning library, its clean code base was supposed to be read. Great for any one who want to learn about Backprop design in deep learning libraries.
mnist-mlp.py: Depth-2 multi layer perceptron, with ReLU and Dropout; 95.3% on MNIST.
lenet-bn.py: LeNet with Batch Normalization on first layer, 97% on MNIST.
lstm-embed.py: LSTM on word embeddings for Vietnamese Question classification + Dropout + L2 weight decay. 85% on test set and 98% on training set (overfit).
turing-copy.py: A neural turing machine with LSTM controller. Test result on copy task length 70:
visual-answer.py. Visual question answering with pretrained weight from VGG16 and a stack of 3 basic LSTMs, on Glove word2vec.
Q: What is the animal in the picture? . A: cat Q: Is there any person in the picture? . A: no Q: What is the cat doing? . A: sitting Q: Where is the cat sitting on? . A: floor Q: What is the cat color? . A: white Q: Is the cat smiling? . A: yes
dqn-cartpole.py: A classic solved with DQN, with experience replay and target network ofcourse. (Illustration below is one-take)
TODO: Memory network and GAN, for that I need to improve my speed of
conv module first.
GPL 3.0 (see License in this repo)