Adding README file

.ipynb_checkpoints/cwgan-gp_time_series-checkpoint.ipynb

@@ -11,11 +11,9 @@
     "from tensorflow import keras\n",
     "from tensorflow.keras import layers\n",
     "\n",
-    "#from tensorflow_docs.vis import embed\n",
     "import matplotlib.pyplot as plt\n",
     "import tensorflow as tf\n",
     "import numpy as np\n",
-    "import imageio\n",
     "plt.rcParams['figure.figsize'] = (20.0, 8.0)"
    ]
   },

README.md

@@ -0,0 +1,31 @@
+# Conditional Wasserstein GAN for Synthetic Time Series Generation
+
+Conditional Wasserstein GAN with gradient penalty for the generation of synthetic time series.
+
+## Description
+
+Propriatary dataset was used to train the conditional WGAN with gradient penalty. Any dataset with shape (num_samples, num_features) will work.
+
+Run the cells in sequence in `cwgan-gp_time_series.ipynb` jupyter notebook. Final cell contains code to create synthetic 
+image conditioned on a label.
+
+Code in part based on:
+
+* https://keras.io/examples/generative/conditional_gan/
+* https://keras.io/examples/generative/wgan_gp/
+* https://keras.io/examples/generative/dcgan_overriding_train_step/
+
+## Getting Started
+
+### Dependencies
+
+* tensorflow
+* numpy
+* matplotlib
+
+See `requirements.txt` file.
+
+
+## License
+
+Free to use for any purpose

cwgan-gp_time_series.ipynb

@@ -11,11 +11,9 @@
     "from tensorflow import keras\n",
     "from tensorflow.keras import layers\n",
     "\n",
-    "#from tensorflow_docs.vis import embed\n",
     "import matplotlib.pyplot as plt\n",
     "import tensorflow as tf\n",
     "import numpy as np\n",
-    "import imageio\n",
     "plt.rcParams['figure.figsize'] = (20.0, 8.0)"
    ]
   },

requirements.txt

@@ -0,0 +1,3 @@
+tensorflow
+numpy
+matplotlib