How to create train, test and validation splits in tensorflow 2.0

4
votes

I am new to tensorflow, and I have started to use tensorflow 2.0

I have built a tensorflow dataset for a multi-class classification problem. Let's call this labeled_ds. I have prepared this dataset by loading all the image files from their respective class wise directories. I have followed along the tutorial here : tensorflow guide to load image dataset

Now, I need to split labeld_ds into three disjoint pieces : train, validation and test. I was going through the tensorflow API, but there was no example which allows to specify the split percentages. I found something in the load method, but I am not sure how to use it. Further, how can I get splits to be stratified ?

# labeled_ds contains multi class data, which is unbalanced.
train_ds, val_ds, test_ds = tf.data.Dataset.tfds.load(labeled_ds, split=["train", "validation", "test"])

I am stuck here, would appreciate any advice on how to progress from here. Thanks in advance.

3
pythontensorflowtensorflow-datasetstensorflow2.0
Refer this answer to split tf.data dataset - Swapnil Masurekar
@SWAPNILMASUREKAR the solution provided to there will work for splitting data into multiple subsets. The problem is, the resulting splits will still not be stratified. - Swaroop
I came accross the same problem, and didn't seem to find a solution in tensorflow that makes sure the dataset is in fact stratified. The solution I ended up using is this. It's a function that splits your dataset into subdirectories of train and validation - then you can create train and validation tensorflow datasets from each directory - ofir dubi
@ofirdubi thanks for sharing the link to the code. I too did something similar since TensorFlow does not provide such a functionality out of the box. - Swaroop

3 Answers

2
votes

Please refer below code to create train, test and validation splits using tensorflow dataset "oxford_flowers102" 

!pip install tensorflow==2.0.0

import tensorflow as tf
print(tf.__version__)
import tensorflow_datasets as tfds

labeled_ds, summary = tfds.load('oxford_flowers102', split='train+test+validation', with_info=True)

labeled_all_length = [i for i,_ in enumerate(labeled_ds)][-1] + 1

train_size = int(0.8 * labeled_all_length)
val_test_size = int(0.1 * labeled_all_length)

df_train = labeled_ds.take(train_size)
df_test = labeled_ds.skip(train_size)
df_val = df_test.skip(val_test_size)
df_test = df_test.take(val_test_size)

df_train_length = [i for i,_ in enumerate(df_train)][-1] + 1
df_val_length = [i for i,_ in enumerate(df_val)][-1] + 1
df_test_length = [i for i,_ in enumerate(df_test)][-1] + 1

print('Original: ', labeled_all_length)
print('Train: ', df_train_length)
print('Validation :', df_val_length)
print('Test :', df_test_length)
1
votes

I had the same problem

It depends on the dataset, most of which have a train and test set. In this case you can do the following (assuming 80-10-10 split):

splits, info = tfds.load('fashion_mnist', with_info=True, as_supervised=True,
split=['train+test[:80]','train+test[80:90]', 'train+test[90:]'],
data_dir=filePath)
0
votes

Francesco Boi Soultion works good for me.

splits, info = tfds.load('fashion_mnist', with_info=True, as_supervised=True, split=['train+test[:80]','train+test[80:90]', 'train+test[90:]'])

(train_examples, validation_examples, test_examples) = splits