densenet

This project includes:

densenet.py, a keras implementation of DenseNet.
cifar10-test.py, code to train the model on Cifar 10, also to test the trained model.
vis_densenet.py, a demo to visualize the layers of the model, using keras-vis.
testnet.py, a vgg-like model, a convnet model with bottle-neck layers and densenet-style skip connections.

References

Gao Huang, Zhuang Liu and K. Weinberger. Densely Connected Convolutional Networks. Arxiv. Github.
DenseNet Other implementations, especially, copied Christopher Masch's code and fixed some issues for aligning to the original DenseNet paper.

Name		Name	Last commit message	Last commit date
Latest commit History 22 Commits
README.md		README.md
cifar10-test.py		cifar10-test.py
dense_augmodel-ep0300-loss0.112-acc0.999-val_loss0.332-val_acc0.946.h5		dense_augmodel-ep0300-loss0.112-acc0.999-val_loss0.332-val_acc0.946.h5
densenet.py		densenet.py
model.summary.txt		model.summary.txt
test_index.npy		test_index.npy
testnet.py		testnet.py
utils.py		utils.py
validation_index.npy		validation_index.npy
vis_densenet.py		vis_densenet.py
weights-verify.py		weights-verify.py