Coursera

TFRecords

#@title Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

Good to run this to ensure you are using TF2.x

try:
  # %tensorflow_version only exists in Colab.
  %tensorflow_version 2.x
except Exception:
  pass

Colab only includes TensorFlow 2.x; %tensorflow_version has no effect.

import tensorflow as tf
import tensorflow_datasets as tfds
data, info = tfds.load("mnist", with_info=True)

Downloading and preparing dataset 11.06 MiB (download: 11.06 MiB, generated: 21.00 MiB, total: 32.06 MiB) to /root/tensorflow_datasets/mnist/3.0.1...



Dl Completed...:   0%|          | 0/5 [00:00<?, ? file/s]


Dataset mnist downloaded and prepared to /root/tensorflow_datasets/mnist/3.0.1. Subsequent calls will reuse this data.

# if you are running the notebook on your local machine, specify the path to the dowloaded file, and also change the version you are using
# for example, this is my file path, and the version I have is 3.0.1
# %cd ~
# filename="./tensorflow_datasets/mnist/3.0.1/mnist-test.tfrecord-00000-of-00001"

# if you are running the notebook on Colab. Change the dataset version accordingly.
filename="/root/tensorflow_datasets/mnist/3.0.1/mnist-test.tfrecord-00000-of-00001"

raw_dataset = tf.data.TFRecordDataset(filename)
for raw_record in raw_dataset.take(1):
    print(repr(raw_record))

<tf.Tensor: shape=(), dtype=string, numpy=b"\n\x85\x03\n\xf2\x02\n\x05image\x12\xe8\x02\n\xe5\x02\n\xe2\x02\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x1c\x00\x00\x00\x1c\x08\x00\x00\x00\x00Wf\x80H\x00\x00\x01)IDAT(\x91\xc5\xd2\xbdK\xc3P\x14\x05\xf0S(v\x13)\x04,.\x82\xc5Aq\xac\xedb\x1d\xdc\n.\x12\x87n\x0e\x82\x93\x7f@Q\xb2\x08\xba\tbQ0.\xe2\xe2\xd4\xb1\xa2h\x9c\x82\xba\x8a(\nq\xf0\x83Fh\x95\n6\x88\xe7R\x87\x88\xf9\xa8Y\xf5\x0e\x8f\xc7\xfd\xdd\x0b\x87\xc7\x03\xfe\xbeb\x9d\xadT\x927Q\xe3\xe9\x07:\xab\xbf\xf4\xf3\xcf\xf6\x8a\xd9\x14\xd29\xea\xb0\x1eKH\xde\xab\xea%\xaba\x1b=\xa4P/\xf5\x02\xd7\\\x07\x00\xc4=,L\xc0,>\x01@2\xf6\x12\xde\x9c\xde[t/\xb3\x0e\x87\xa2\xe2\xc2\xe0A<\xca\xb26\xd5(\x1b\xa9\xd3\xe8\x0e\xf5\x86\x17\xceE\xdarV\xae\xb7_\xf3AR\r!I\xf7(\x06m\xaaE\xbb\xb6\xac\r*\x9b$e<\xb8\xd7\xa2\x0e\x00\xd0l\x92\xb2\xd5\x15\xcc\xae'\x00\xf4m\x08O'+\xc2y\x9f\x8d\xc9\x15\x80\xfe\x99[q\x962@CN|i\xf7\xa9!=\xd7 \xab\x19\x00\xc8\xd6\xb8\xeb\xa1\xf0\xd8l\xca\xfb]\xee\xfb]*\x9fV\xe1\x07\xb7\xc9\x8b55\xe7M\xef\xb0\x04\xc0\xfd&\x89\x01<\xbe\xf9\x03*\x8a\xf5\x81\x7f\xaa/2y\x87ks\xec\x1e\xc1\x00\x00\x00\x00IEND\xaeB`\x82\n\x0e\n\x05label\x12\x05\x1a\x03\n\x01\x02">

# Create a description of the features.
feature_description = {
    'image': tf.io.FixedLenFeature([], dtype=tf.string),
    'label': tf.io.FixedLenFeature([], dtype=tf.int64),
}

def _parse_function(example_proto):
  # Parse the input `tf.Example` proto using the dictionary above.
  return tf.io.parse_single_example(example_proto, feature_description)

parsed_dataset = raw_dataset.map(_parse_function)
for parsed_record in parsed_dataset.take(1):
    print((parsed_record))

{'image': <tf.Tensor: shape=(), dtype=string, numpy=b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x1c\x00\x00\x00\x1c\x08\x00\x00\x00\x00Wf\x80H\x00\x00\x01)IDAT(\x91\xc5\xd2\xbdK\xc3P\x14\x05\xf0S(v\x13)\x04,.\x82\xc5Aq\xac\xedb\x1d\xdc\n.\x12\x87n\x0e\x82\x93\x7f@Q\xb2\x08\xba\tbQ0.\xe2\xe2\xd4\xb1\xa2h\x9c\x82\xba\x8a(\nq\xf0\x83Fh\x95\n6\x88\xe7R\x87\x88\xf9\xa8Y\xf5\x0e\x8f\xc7\xfd\xdd\x0b\x87\xc7\x03\xfe\xbeb\x9d\xadT\x927Q\xe3\xe9\x07:\xab\xbf\xf4\xf3\xcf\xf6\x8a\xd9\x14\xd29\xea\xb0\x1eKH\xde\xab\xea%\xaba\x1b=\xa4P/\xf5\x02\xd7\\\x07\x00\xc4=,L\xc0,>\x01@2\xf6\x12\xde\x9c\xde[t/\xb3\x0e\x87\xa2\xe2\xc2\xe0A<\xca\xb26\xd5(\x1b\xa9\xd3\xe8\x0e\xf5\x86\x17\xceE\xdarV\xae\xb7_\xf3AR\r!I\xf7(\x06m\xaaE\xbb\xb6\xac\r*\x9b$e<\xb8\xd7\xa2\x0e\x00\xd0l\x92\xb2\xd5\x15\xcc\xae'\x00\xf4m\x08O'+\xc2y\x9f\x8d\xc9\x15\x80\xfe\x99[q\x962@CN|i\xf7\xa9!=\xd7 \xab\x19\x00\xc8\xd6\xb8\xeb\xa1\xf0\xd8l\xca\xfb]\xee\xfb]*\x9fV\xe1\x07\xb7\xc9\x8b55\xe7M\xef\xb0\x04\xc0\xfd&\x89\x01<\xbe\xf9\x03*\x8a\xf5\x81\x7f\xaa/2y\x87ks\xec\x1e\xc1\x00\x00\x00\x00IEND\xaeB`\x82">, 'label': <tf.Tensor: shape=(), dtype=int64, numpy=2>}