Implemention of Capsule Net from the paper Dynamic Routing Between Capsules Edit Add topics
- pip install --pre mxnet-cu80 -i https://pypi.douban.com/simple --user
- pip install tqdm
- python main.py
Results to be added
I use SGD
to try Capsule Net, if use Adam
as described in the original paper, I got very low test accuracy.
I find if use large train batch_size, the results is also unaceptable. I haven't figure it out.
Any PR is welcomed.
-
Kaggle (this version as self-contained notebook):
- MNIST Dataset running on the standard MNIST and predicting for test data
- MNIST Fashion running on the more challenging Fashion images.
-
TensorFlow:
- naturomics/CapsNet-Tensorflow
Very good implementation. I referred to this repository in my code. - InnerPeace-Wu/CapsNet-tensorflow
I referred to the use of tf.scan when optimizing my CapsuleLayer. - LaoDar/tf_CapsNet_simple
- naturomics/CapsNet-Tensorflow
-
PyTorch:
-
MXNet:
-
Lasagne (Theano):
-
Chainer: