Last active
February 19, 2020 19:26
-
-
Save ResidentMario/f934504ecb70a87879661c1c0170f533 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
import sys | |
import os | |
import pandas as pd | |
import requests | |
from tqdm import tqdm | |
import ratelim | |
from checkpoints import checkpoints | |
checkpoints.enable() | |
def download(categories): | |
# Download the metadata | |
kwargs = {'header': None, 'names': ['LabelID', 'LabelName']} | |
orig_url = "https://storage.googleapis.com/openimages/2018_04/class-descriptions-boxable.csv" | |
class_names = pd.read_csv(orig_url, **kwargs) | |
orig_url = "https://storage.googleapis.com/openimages/2018_04/train/train-annotations-bbox.csv" | |
train_boxed = pd.read_csv(orig_url) | |
orig_url = "https://storage.googleapis.com/openimages/2018_04/train/train-images-boxable-with-rotation.csv" | |
image_ids = pd.read_csv(orig_url) | |
# Get category IDs for the given categories and sub-select train_boxed with them. | |
label_map = dict(class_names.set_index('LabelName').loc[categories, 'LabelID'] | |
.to_frame().reset_index().set_index('LabelID')['LabelName']) | |
label_values = set(label_map.keys()) | |
relevant_training_images = train_boxed[train_boxed.LabelName.isin(label_values)] | |
# Start from prior results if they exist and are specified, otherwise start from scratch. | |
relevant_flickr_urls = (relevant_training_images.set_index('ImageID') | |
.join(image_ids.set_index('ImageID')) | |
.loc[:, 'OriginalURL']) | |
relevant_flickr_img_metadata = (relevant_training_images.set_index('ImageID').loc[relevant_flickr_urls.index] | |
.pipe(lambda df: df.assign(LabelValue=df.LabelName.map(lambda v: label_map[v])))) | |
remaining_todo = len(relevant_flickr_urls) if checkpoints.results is None else\ | |
len(relevant_flickr_urls) - len(checkpoints.results) | |
# Download the images | |
with tqdm(total=remaining_todo) as progress_bar: | |
relevant_image_requests = relevant_flickr_urls.safe_map(lambda url: _download_image(url, progress_bar)) | |
progress_bar.close() | |
# Write the images to files, adding them to the package as we go along. | |
if not os.path.isdir("temp/"): | |
os.mkdir("temp/") | |
for ((_, r), (_, url), (_, meta)) in zip(relevant_image_requests.iteritems(), relevant_flickr_urls.iteritems(), | |
relevant_flickr_img_metadata.iterrows()): | |
image_name = url.split("/")[-1] | |
image_label = meta['LabelValue'] | |
_write_image_file(r, image_name) | |
@ratelim.patient(5, 5) | |
def _download_image(url, pbar): | |
"""Download a single image from a URL, rate-limited to once per second""" | |
r = requests.get(url) | |
r.raise_for_status() | |
pbar.update(1) | |
return r | |
def _write_image_file(r, image_name): | |
"""Write an image to a file""" | |
filename = f"temp/{image_name}" | |
with open(filename, "wb") as f: | |
f.write(r.content) | |
if __name__ == '__main__': | |
categories = sys.argv[1:] | |
download(categories) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment