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 seasonyc Update README.md Oct 16, 2018 234218d · Oct 16, 2018 History 22 Commits
README.md	README.md	Update README.md	Oct 16, 2018
cifar10-test.py	cifar10-test.py	Add files via upload	Oct 16, 2018
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	Add files via upload	Sep 27, 2018
densenet.py	densenet.py	Add files via upload	Sep 27, 2018
model.summary.txt	model.summary.txt	Update model.summary.txt	Sep 27, 2018
test_index.npy	test_index.npy	Add files via upload	Jul 17, 2018
testnet.py	testnet.py	Add files via upload	Oct 16, 2018
utils.py	utils.py	Add files via upload	Jul 17, 2018
validation_index.npy	validation_index.npy	Add files via upload	Jul 17, 2018
vis_densenet.py	vis_densenet.py	Add files via upload	Sep 27, 2018
weights-verify.py	weights-verify.py	Add files via upload	Sep 27, 2018