How to extract data/labels back from TensorFlow dataset

tensorflow tensorflow-datasets
Valentin picture Valentin · May 20, 2019 · Viewed 16.3k times · Source

there are plenty of examples how to create and use TensorFlow datasets, e.g.

dataset = tf.data.Dataset.from_tensor_slices((images, labels))

My question is how to get back the data/labels from the TF dataset in numpy form? In other words want would be reverse operation of the line above, i.e. I have a TF dataset and want to get back images and labels from it.

Answer

kawingkelvin picture kawingkelvin · Jul 9, 2020

In case your tf.data.Dataset is batched, the following code will retrieve all the y labels:

y = np.concatenate([y for x, y in ds], axis=0)

Related questions

TensorFlow: training on my own image

I am new to TensorFlow. I am looking for the help on the image recognition where I can train my own image dataset. Is there any example for training the new dataset?

Read More
Meaning of buffer_size in Dataset.map , Dataset.prefetch and Dataset.shuffle

As per TensorFlow documentation , the prefetch and map methods of tf.contrib.data.Dataset class, both have a parameter called buffer_size. For prefetch method, the parameter is known as buffer_size and according to documentation : buffer_size: A tf.…

Read More
tf.data.Dataset: how to get the dataset size (number of elements in a epoch)?

Let's say I have defined a dataset in this way: filename_dataset = tf.data.Dataset.list_files("{}/*.png".format(dataset)) how can I get the number of elements that are inside the dataset (hence, the number of single elements that …

Read More