Skip to content

Instantly share code, notes, and snippets.

@OluwoleOyetoke
Last active December 18, 2017 22:35
Show Gist options
  • Save OluwoleOyetoke/eee86af592b61a312e532ba743807d47 to your computer and use it in GitHub Desktop.
Save OluwoleOyetoke/eee86af592b61a312e532ba743807d47 to your computer and use it in GitHub Desktop.
TFRecord Creation Find images
def _find_image_files(data_dir, labels_file):
"""
Args:
data_dir: string, path to the root directory of images.
Assumes that the image data set resides in JPEG files located in
the following directory structure.
data_dir/dog/another-image.JPEG
data_dir/dog/my-image.jpg
where 'dog' is the label associated with these images.
labels_file: string, path to the labels file.
The list of valid labels are held in this file. Assumes that the file
contains entries as such:
dog
cat
flower
where each line corresponds to a label. We map each label contained in
the file to an integer starting with the integer 0 corresponding to the
label contained in the first line.
Returns:
filenames: list of strings; each string is a path to an image file.
texts: list of strings; each string is the class, e.g. 'dog'
labels: list of integer; each integer identifies the ground truth.
"""
print('Determining list of input files and labels from %s ' % labels_file)
unique_labels = [l.strip() for l in tf.gfile.FastGFile(
labels_file, 'r').readlines()]
labels = []
filenames = []
texts = []
# Leave label index 0 empty as a background class.
label_index = 1
# Construct the list of JPEG files and labels.
for text in unique_labels:
jpeg_file_path = '%s/%s/*' % (data_dir, text)
print("File path %s \n" % jpeg_file_path);
matching_files = tf.gfile.Glob(jpeg_file_path)
labels.extend([label_index] * len(matching_files))
texts.extend([text] * len(matching_files))
filenames.extend(matching_files)
if not label_index % 100:
print('Finished finding files in %d of %d classes.' % (
label_index, len(labels)))
label_index += 1
# Shuffle the ordering of all image files in order to guarantee
# random ordering of the images with respect to label in the
# saved TFRecord files. Make the randomization repeatable.
shuffled_index = list(range(len(filenames)))
random.seed(12345)
random.shuffle(shuffled_index)
filenames = [filenames[i] for i in shuffled_index]
texts = [texts[i] for i in shuffled_index]
labels = [labels[i] for i in shuffled_index]
print('Found %d JPEG files across %d labels inside %s' %
(len(filenames), len(unique_labels), data_dir))
return filenames, texts, labels
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment