Add KMNIST dataset

Author: christianversloot

README.md

@@ -96,6 +96,28 @@ from extra_keras_datasets import emnist
 
 ---
 
+### KMNIST-KMNIST
+
+```
+from extra_keras_datasets import kmnist
+(input_train, target_train), (input_test, target_test) = kmnist.load_data(type='kmnist')
+```
+
+<a href="./assets/kmnist-kmnist.png"><img src="./assets/kmnist-kmnist.png" width="500" style="border: 3px solid #f6f8fa;" /></a>
+
+---
+
+### KMNIST-K49
+
+```
+from extra_keras_datasets import kmnist
+(input_train, target_train), (input_test, target_test) = kmnist.load_data(type='k49')
+```
+
+<a href="./assets/kmnist-k49.png"><img src="./assets/kmnist-k49.png" width="500" style="border: 3px solid #f6f8fa;" /></a>
+
+---
+
 ## Contributors and other references
 * **[tlindbloom](https://stackoverflow.com/users/4008755/tlindbloom) on StackOverflow:** [loading EMNIST-letters dataset](https://stackoverflow.com/questions/51125969/loading-emnist-letters-dataset/53547262#53547262) in [emnist.py](./emnist.py).
 

assets/kmnist-k49.png

@@ -0,0 +1,53 @@
+'''
+  Import the KMNIST dataset
+  Source: https://arxiv.org/abs/1812.01718
+  Description: Japanese character MNIST dataset.
+
+  ~~~ Important note ~~~
+  Please cite the following paper when using or referencing the dataset:
+  Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., & Ha, D. (2018). Deep learning for classical Japanese literature. arXiv preprint arXiv:1812.01718. Retrieved from https://arxiv.org/abs/1812.01718
+
+'''
+
+from keras.utils.data_utils import get_file
+import numpy as np
+
+def load_data(path='kmnist.npz', type='kmnist'):
+  """Loads the KMNIST dataset.
+  # Arguments
+      path: path where to cache the dataset locally
+          (relative to ~/.keras/datasets).
+      type: any of kmnist, k49
+  # Returns
+      Tuple of Numpy arrays: `(input_train, target_train), (input_test, target_test)`.
+  """
+  # Load training images
+  path_train = get_file(
+    f'{path}_{type}_train_imgs',
+    origin=f'http://codh.rois.ac.jp/kmnist/dataset/{type}/{type}-train-imgs.npz'
+  )
+  input_train = np.load(path_train)['arr_0']
+
+  # Load training labels
+  path_train_labels = get_file(
+    f'{path}_{type}_train_labels',
+    origin=f'http://codh.rois.ac.jp/kmnist/dataset/{type}/{type}-train-labels.npz'
+  )
+  target_train = np.load(path_train_labels)['arr_0']
+
+  # Load testing images
+  path_test = get_file(
+    f'{path}_{type}_test_imgs',
+    origin=f'http://codh.rois.ac.jp/kmnist/dataset/{type}/{type}-test-imgs.npz'
+  )
+  input_test = np.load(path_test)['arr_0']
+
+  # Load testing labels
+  path_test_labels = get_file(
+    f'{path}_{type}_test_labels',
+    origin=f'http://codh.rois.ac.jp/kmnist/dataset/{type}/{type}-test-labels.npz'
+  )
+  target_test = np.load(path_test_labels)['arr_0']
+
+  # Return data
+  return (input_train, target_train), (input_test, target_test)