From 14f07db52cb591c5ce60794ed0647460391cd979 Mon Sep 17 00:00:00 2001
From: Connor Olding <cloningdonor@gmail.com>
Date: Thu, 15 Mar 2018 01:44:40 +0100
Subject: [PATCH] add README shape-dumping to main

---
 README.md          | 53 +++++++++++++++++++++++++++++++++++++++-------
 mnists/__main__.py | 11 ++++++++--
 2 files changed, 54 insertions(+), 10 deletions(-)

diff --git a/README.md b/README.md
index 99c2ac8..725515f 100644
--- a/README.md
+++ b/README.md
@@ -38,20 +38,57 @@ in alphabetical order:
 
 ### [emnist][emnist]
 
-* `emnist_balanced`
-* `emnist_byclass`
-* `emnist_bymerge`
-* `emnist_digits`
-* `emnist_letters`
-* `emnist_mnist`
+ *  `emnist_balanced`  
+    train images shape: (112800, 1, 28, 28)  
+    train labels shape: (112800, 47)  
+    test images shape: (18800, 1, 28, 28)  
+    test labels shape: (18800, 47)  
+
+ *  `emnist_byclass`  
+    train images shape: (697932, 1, 28, 28)  
+    train labels shape: (697932, 62)  
+    test images shape: (116323, 1, 28, 28)  
+    test labels shape: (116323, 62)  
+
+ *  `emnist_bymerge`  
+    train images shape: (697932, 1, 28, 28)  
+    train labels shape: (697932, 47)  
+    test images shape: (116323, 1, 28, 28)  
+    test labels shape: (116323, 47)  
+
+ *  `emnist_digits`  
+    train images shape: (240000, 1, 28, 28)  
+    train labels shape: (240000, 10)  
+    test images shape: (40000, 1, 28, 28)  
+    test labels shape: (40000, 10)  
+
+ *  `emnist_letters`  
+    train images shape: (124800, 1, 28, 28)  
+    train labels shape: (124800, 26)  
+    test images shape: (20800, 1, 28, 28)  
+    test labels shape: (20800, 26)  
+
+ *  `emnist_mnist`  
+    train images shape: (60000, 1, 28, 28)  
+    train labels shape: (60000, 10)  
+    test images shape: (10000, 1, 28, 28)  
+    test labels shape: (10000, 10)  
 
 ### [fashion-mnist][fashion-mnist]
 
-* `fashion_mnist`
+ *  `fashion_mnist`  
+    train images shape: (60000, 1, 28, 28)  
+    train labels shape: (60000, 10)  
+    test images shape: (10000, 1, 28, 28)  
+    test labels shape: (10000, 10)  
 
 ### [mnist][mnist]
 
-* `mnist`
+ *  `mnist`  
+    train images shape: (60000, 1, 28, 28)  
+    train labels shape: (60000, 10)  
+    test images shape: (10000, 1, 28, 28)  
+    test labels shape: (10000, 10)  
 
 [emnist]: //www.nist.gov/itl/iad/image-group/emnist-dataset
 [fashion-mnist]: //github.com/zalandoresearch/fashion-mnist
diff --git a/mnists/__main__.py b/mnists/__main__.py
index e64dbce..168f382 100644
--- a/mnists/__main__.py
+++ b/mnists/__main__.py
@@ -1,6 +1,13 @@
 from . import metadata, prepare
 
 
+names = ("train images", "train labels", "test images", "test labels")
+
 for name in metadata.keys():
-    print(name)
-    prepare(name)
+    # verify every dataset, downloading if necessary.
+    # print out the shapes for use in the README.
+    print(f" *  `{name}`  ")
+    data = prepare(name)
+    for name, dat in zip(names, data):
+        print(f"    {name} shape: {dat.shape}  ")
+    print()