Skip to content
Try PyTorch, Tensorflow, Keras, Chainer, make them have same output as possible.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
chainer_func
dataset
tf_func
theano_func
torch_func
.gitignore
ExpUtils.py
README.md
chainer.ipynb
chainer_vat_cifar10.ipynb
dynamic_template.ipynb
pytorch-cmp-2-tf.ipynb
pytorch-vat-chainer-cifar10.ipynb
requirements.txt
tf_eager-cmp-2-pytorch.ipynb
tf_graph.ipynb
theano.ipynb

README.md

DeepLearningCMP

Try PyTorch, Tensorflow, Keras, Chainer, make them have same output as possible.

PyTorch == 0.4.1, Tensorflow-gpu == 1.12.0, Chainer == 5.2.0, Keras == ???

Status

Now I have implemented PyTorch and Chainer. By setting a weight initializer to PyTorch model, I can have models created by PyTorch and Chainer to have same outputs for most layers(I can't figure Dropout layer out).

I also had Keras implemented model by different versions of Keras.

You can’t perform that action at this time.