Skip to content

GitLab

Unverified Commit 4b14ee70 authored by Jaeyoun Kim's avatar Jaeyoun Kim Committed by GitHub
Browse files

Update README.md 

Add an unofficial implementation link
parent 25542676
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 8 deletions
research/domain_adaptation/README.md
View file @ 4b14ee70
...@@ -17,6 +17,10 @@ adaptation by transfering the visual style of the target domain (which has few ...@@ -17,6 +17,10 @@ adaptation by transfering the visual style of the target domain (which has few
or no labels) to a source domain (which has many labels). This is accomplished or no labels) to a source domain (which has many labels). This is accomplished
using a Generative Adversarial Network (GAN). using a Generative Adversarial Network (GAN).
### Other implementations
* [Simplified-DSN](https://github.com/AmirHussein96/Simplified-DSN):
An unofficial implementation of the [Domain Separation Networks paper](https://arxiv.org/abs/1608.06019).
## Contact ## Contact
The domain separation code was open-sourced The domain separation code was open-sourced
by [Konstantinos Bousmalis](https://github.com/bousmalis) by [Konstantinos Bousmalis](https://github.com/bousmalis)
...@@ -26,14 +30,9 @@ open-sourced by [David Dohan](https://github.com/dmrd) (ddohan@google.com). ...@@ -26,14 +30,9 @@ open-sourced by [David Dohan](https://github.com/dmrd) (ddohan@google.com).
## Installation ## Installation
You will need to have the following installed on your machine before trying out the DSN code. You will need to have the following installed on your machine before trying out the DSN code.
* Tensorflow: https://www.tensorflow.org/install/ * TensorFlow 1.x: https://www.tensorflow.org/install/
* Bazel: https://bazel.build/ * Bazel: https://bazel.build/
## Important Note
We are working to open source the pose estimation dataset. For now, the MNIST to
MNIST-M dataset is available. Check back here in a few weeks or wait for a
relevant announcement from [@bousmalis](https://twitter.com/bousmalis).
## Initial setup ## Initial setup
In order to run the MNIST to MNIST-M experiments, you will need to set the In order to run the MNIST to MNIST-M experiments, you will need to set the
data directory: data directory:
...@@ -61,8 +60,6 @@ The MNIST-M dataset is available online [here](http://bit.ly/2nrlUAJ). Once it ...@@ -61,8 +60,6 @@ The MNIST-M dataset is available online [here](http://bit.ly/2nrlUAJ). Once it
$ bazel run domain_adaptation/datasets:download_and_convert_mnist_m -- --dataset_dir $DSN_DATA_DIR $ bazel run domain_adaptation/datasets:download_and_convert_mnist_m -- --dataset_dir $DSN_DATA_DIR
``` ```
# Running PixelDA from MNIST to MNIST-M # Running PixelDA from MNIST to MNIST-M
You can run PixelDA as follows (using Tensorboard to examine the results): You can run PixelDA as follows (using Tensorboard to examine the results):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment