Initial commit

lenet5.py

@@ -0,0 +1,113 @@
+"""
+LeNet-5 example
+"""
+import gzip
+import numpy as np
+from requests import get
+import matplotlib.pyplot as plt
+import pandas as pd
+from sklearn.model_selection import train_test_split
+
+def download_file(url, file_name):
+    """
+    Download files and stores them locally.
+    """
+    with open(file_name, "wb") as file:
+        response = get(url)
+        file.write(response.content)
+
+def read_mnist(images_path: str, labels_path: str):
+    """
+    Read data and labels of the MNIST dataset.
+    """
+    with gzip.open(labels_path, 'rb') as labels_file:
+        labels = np.frombuffer(labels_file.read(), dtype=np.uint8, offset=8)
+
+    with gzip.open(images_path,'rb') as images_file:
+        length = len(labels)
+        # Load flat 28x28 px images (784 px), and convert them to 28x28 px
+        features = np.frombuffer(images_file.read(), dtype=np.uint8, offset=16) \
+                        .reshape(length, 784)                                   \
+                        .reshape(length, 28, 28, 1)
+
+    return features, labels
+
+def display_image(dataset, position):
+    """
+    Display image at position of the given dataset.
+    """
+    image = dataset['features'][position].squeeze()
+    plt.title('Example %d. Label: %d' % (position, dataset['labels'][position]))
+    plt.imshow(image, cmap=plt.get_cmap('gray_r'))
+    plt.show()
+
+def main():
+    """
+    Defined starting point of source code.
+    """
+
+    # Step 1:
+    # Download the MNIST dataset with consist of labeled handwritten images (28x28 px).
+
+    # train-images-idx3-ubyte.gz: training set images (9912422 bytes)
+    download_file('http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz',
+                  'train-images-idx3-ubyte.gz')
+    # train-labels-idx1-ubyte.gz: training set labels (28881 bytes)
+    download_file('http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz',
+                  'train-labels-idx1-ubyte.gz')
+    # t10k-images-idx3-ubyte.gz: test set images (1648877 bytes)
+    download_file('http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz',
+                  't10k-images-idx3-ubyte.gz')
+    # t10k-labels-idx1-ubyte.gz: test set labels (4542 bytes)
+    download_file('http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz',
+                  't10k-labels-idx1-ubyte.gz')
+
+    train = {}
+    test = {}
+
+    # Step 2:
+    # Read MNIST dataset (training and testing)
+    train['features'], train['labels'] = read_mnist('train-images-idx3-ubyte.gz',
+                                                    'train-labels-idx1-ubyte.gz')
+    test['features'], test['labels'] = read_mnist('t10k-images-idx3-ubyte.gz',
+                                                  't10k-labels-idx1-ubyte.gz')
+
+    # Step 3:
+    # Explore the dataset
+    print('Number of training images:', train['features'].shape[0])
+    print('Number of test images:', test['features'].shape[0])
+
+    # Step 4:
+    # Dispan some images
+    # display_image(train, 0)
+    # display_image(train, 1)
+    # display_image(train, 2)
+
+    # Step 5:
+    # Plot information about the training data
+    train_labels_count = np.unique(train['labels'], return_counts=True)
+    dataframe_train_labels = pd.DataFrame({'Label':train_labels_count[0],
+                                           'Count':train_labels_count[1]})
+    print(dataframe_train_labels)
+
+    # Step 5:
+    # Split training data into training and validation
+    validation = {}
+    train['features'], validation['features'], train['labels'], validation['labels'] \
+        = train_test_split(train['features'], train['labels'], test_size=0.2, random_state=0)
+
+    print('Number of training images:', train['features'].shape[0])
+    print('Number of validation images:', validation['features'].shape[0])
+
+    # Step 6:
+    # Prepare our input features.
+    # The LeNet architecture accepts 32x32 pixel images as input, but MNIST data is 28x28 pixels.
+    # We simply pad the imges with zeros to overcome that.
+    train['features']      = np.pad(train['features'], ((0,0),(2,2),(2,2),(0,0)), 'constant')
+    validation['features'] = np.pad(validation['features'], ((0,0),(2,2),(2,2),(0,0)), 'constant')
+    test['features']       = np.pad(test['features'], ((0,0),(2,2),(2,2),(0,0)), 'constant')
+
+    print("Updated Image Shape: {}".format(train['features'][0].shape))
+
+if __name__ == "__main__":
+    main()