Last active
October 26, 2024 17:03
-
-
Save coccoinomane/8de713a06b0b9cb43b621197f60ecb75 to your computer and use it in GitHub Desktop.
Show an image from the MNIST dataset, and print its label
This file contains hidden or 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
""" | |
Show an image from the MNIST dataset, and print its label. | |
Usage: show-mnist-image.py <index> <split> | |
where | |
- <index> is the index of the image to show (0-59999) | |
- <split> is either 'train' or 'test' to select the specific MNIST dataset | |
Example: | |
$ python show-mnist-image.py 5 train | |
Requires the 'datasets' library: | |
$ pip install datasets | |
Github Gist available at: | |
- https://gist.github.com/coccoinomane/8de713a06b0b9cb43b621197f60ecb75 | |
""" | |
import sys | |
from datasets import load_dataset | |
usage = "Usage: show-mnist-image.py <index> <split>" | |
if len(sys.argv) != 3: | |
print(usage) | |
sys.exit(1) | |
# Parse index argument | |
index = int(sys.argv[1]) | |
if index < 0 or index >= 60000: | |
print("Index out of range, MNIST dataset has 60000 images.") | |
print(usage) | |
sys.exit(1) | |
# Parse split | |
split = sys.argv[2] | |
if split not in ["train", "test"]: | |
print("Split must be either 'train' or 'test'.") | |
print(usage) | |
sys.exit(1) | |
# Load the dataset | |
ds = load_dataset("ylecun/mnist", split=split) | |
# Print the image label | |
print("Label:", ds[index]["label"]) | |
# Get the image, in PIL format | |
image = ds[index]["image"] | |
# Show the image | |
image.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment