Created
May 29, 2021 08:42
-
-
Save housecricket/9b524a8fa95f61e9e5421b225d827c46 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def load_az_dataset(dataset_path): | |
# initialize the list of data and labels | |
data = [] | |
labels = [] | |
# loop over the rows of the A-Z handwritten digit dataset | |
for row in open(dataset_path): | |
# parse the label and image from the row | |
row = row.split(",") | |
label = int(row[0]) | |
image = np.array([int(x) for x in row[1:]], dtype="uint8") | |
# images are represented as single channel (grayscale) images | |
# that are 28x28=784 pixels -- we need to take this flattened | |
# 784-d list of numbers and reshape them into a 28x28 matrix | |
image = image.reshape((28, 28)) | |
# update the list of data and labels | |
data.append(image) | |
labels.append(label) | |
# convert the data and labels to NumPy arrays | |
data = np.array(data, dtype="float32") | |
labels = np.array(labels, dtype="int") | |
# return a 2-tuple of the A-Z data and labels | |
return (data, labels) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment