Code in README.md doesn't work in other multi_dsprites_dataset

Code in 'README.md' works well in 'multi_dsprites_colored_on_colored.tfrecords'.
However, it doesn't work well in 'multi_dsprites_binarized.tfrecords' and 'multi_dsprites_colored_on_grayscale.tfrecords'.
In the code
```python
from multi_object_datasets import multi_dsprites
import tensorflow as tf

tf_records_path = 'path/to/multi_dsprites_binarized.tfrecords'
batch_size = 32

dataset = multi_dsprites.dataset(tf_records_path, 'binarized')
batched_dataset = dataset.batch(batch_size) # optional batching
iterator = batched_dataset.make_one_shot_iterator()
data = iterator.get_next()

with tf.train.SingularMonitoredSession() as sess:
d = sess.run(data)
```

, 'd=sess.run(data)' generates error,

```
tensorflow.python.framework.errors_impl.DataLossError: inflate() failed with error -3: incorrect header check
[[node IteratorGetNext ]]
```

The version of tensorflow is 1.14 as in README.md.

Thank you!!

Same error occurs in CLEVR code.