Learn practical skills, build real-world projects, and advance your career
Updated 4 years ago
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import tensorflow_hub as hub
import tensorflow_datasets as tfds
from tensorflow.keras import layers
We are taking dataset from the link, tf_flowers which consists of 3670 records
(training_set,validation_set),dataset_info = tfds.load('tf_flowers',split=['train[:70%]','train[70%:]'],
with_info = True,as_supervised = True)
Downloading and preparing dataset tf_flowers/3.0.0 (download: 218.21 MiB, generated: Unknown size, total: 218.21 MiB) to /root/tensorflow_datasets/tf_flowers/3.0.0...
HBox(children=(IntProgress(value=1, bar_style='info', description='Dl Completed...', max=1, style=ProgressStyl…
HBox(children=(IntProgress(value=1, bar_style='info', description='Dl Size...', max=1, style=ProgressStyle(des…
HBox(children=(IntProgress(value=1, bar_style='info', description='Extraction completed...', max=1, style=Prog…
HBox(children=(IntProgress(value=1, bar_style='info', max=1), HTML(value='')))
Shuffling and writing examples to /root/tensorflow_datasets/tf_flowers/3.0.0.incompleteQ1SSUL/tf_flowers-train.tfrecord
HBox(children=(IntProgress(value=0, max=3670), HTML(value='')))
Dataset tf_flowers downloaded and prepared to /root/tensorflow_datasets/tf_flowers/3.0.0. Subsequent calls will reuse this data.
Lets Check the number of classes in the dataset
dataset_info
tfds.core.DatasetInfo(
name='tf_flowers',
version=3.0.0,
description='A large set of images of flowers',
homepage='https://www.tensorflow.org/tutorials/load_data/images',
features=FeaturesDict({
'image': Image(shape=(None, None, 3), dtype=tf.uint8),
'label': ClassLabel(shape=(), dtype=tf.int64, num_classes=5),
}),
total_num_examples=3670,
splits={
'train': 3670,
},
supervised_keys=('image', 'label'),
citation="""@ONLINE {tfflowers,
author = "The TensorFlow Team",
title = "Flowers",
month = "jan",
year = "2019",
url = "http://download.tensorflow.org/example_images/flower_photos.tgz" }""",
redistribution_info=,
)