I'm trying to convert my Jpeg image set into to TFrecords. But TFrecord file is taking almost 5x more space than the image set. After a lot of googling, I learned that when JPEG are written into TFrecords, they aren't JPEG anymore. However I haven't come across an understandable code solution to this problem. Please tell me what changes ought to be made in the code below to write JPEG to Tfrecords.
def print_progress(count, total):
pct_complete = float(count) / total
msg = "\r- Progress: {0:.1%}".format(pct_complete)
sys.stdout.write(msg)
sys.stdout.flush()
def wrap_int64(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=value))
def wrap_bytes(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def convert(image_paths , labels, out_path):
# Args:
# image_paths List of file-paths for the images.
# labels Class-labels for the images.
# out_path File-path for the TFRecords output file.
print("Converting: " + out_path)
# Number of images. Used when printing the progress.
num_images = len(image_paths)
# Open a TFRecordWriter for the output-file.
with tf.python_io.TFRecordWriter(out_path) as writer:
# Iterate over all the image-paths and class-labels.
for i, (path, label) in enumerate(zip(image_paths, labels)):
# Print the percentage-progress.
print_progress(count=i, total=num_images-1)
# Load the image-file using matplotlib's imread function.
img = imread(path)
# Convert the image to raw bytes.
img_bytes = img.tostring()
# Create a dict with the data we want to save in the
# TFRecords file. You can add more relevant data here.
data = \
{
'image': wrap_bytes(img_bytes),
'label': wrap_int64(label)
}
# Wrap the data as TensorFlow Features.
feature = tf.train.Features(feature=data)
# Wrap again as a TensorFlow Example.
example = tf.train.Example(features=feature)
# Serialize the data.
serialized = example.SerializeToString()
# Write the serialized data to the TFRecords file.
writer.write(serialized)
Edit: Can someone please answer this ?!!
Instead of converting image to array and back to bytes, we can just use inbuilt open function to get the bytes. That way, compressed image will be written into TFRecord.
Replace these two lines
img = imread(path)
img_bytes = img.tostring()
with
img_bytes = open(path,'rb').read()
Reference :