Visualization of the Tiny ImageNet dataset in the Deep Lake UI
In Tiny ImageNet, there are 100,000 images divided up into 200 classes. Every image in the dataset is downsized to a 64×64 colored image. For every class, there are 500 training images, 50 validating images, and 50 test images.
Instead of downloading the Tiny ImageNet dataset in Python, you can effortlessly load it in Python via our Deep Lake open-source with just one line of code.
import deeplake
ds = deeplake.load("hub://activeloop/tiny-imagenet-train")
import deeplake
ds = deeplake.load("hub://activeloop/tiny-imagenet-test")
import deeplake
ds = deeplake.load("hub://activeloop/tiny-imagenet-validation")
Tiny ImageNet Data Fields
- image: tensor containing the image.
- labels: tensor to identify an object in the image
- boxes: tensor to identify the object using bounding boxes.
Tiny ImageNet Data Splits
- The TinyImageNet dataset training set is composed of 100,000 images.
- The TinyImageNet dataset testing set is composed of 10,000 images.
- The TinyImageNet dataset validation set is composed of 10,000 images.
Train a model on Tiny ImageNet dataset with PyTorch in Python
Let’s use Deep Lake built-in PyTorch one-line dataloader to connect the data to the compute:
dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)
Train a model on Tiny ImageNet dataset with TensorFlow in Python
dataloader = ds.tensorflow()
- Homepage: https://www.kaggle.com/c/tiny-imagenet
- Repository: https://github.com/rmccorm4/Tiny-Imagenet-200
- Paper: Introduced by Le et al. in Tiny imagenet visual recognition challenge
- Point of Contact: N/A
Tiny ImageNet Dataset Curators
Ya Le and Xuan S. Yang
Tiny ImageNet Dataset Licensing Information
Deep Lake users may have access to a variety of publicly available datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have a license to use the datasets. It is your responsibility to determine whether you have permission to use the datasets under their license.
If you’re a dataset owner and do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thank you for your contribution to the ML community!
Tiny ImageNet Dataset Citation Information
@inproceedings{Le2015TinyIV,
title={Tiny ImageNet Visual Recognition Challenge},
author={Ya Le and Xuan S. Yang},
year={2015}
}
What is the Tiny ImageNet dataset for Python?
The Tiny ImageNet dataset is a visual database often used in visual object recognition software research. The Tiny ImageNet dataset is a modified subset of the original ImageNet dataset. The Tiny ImageNet dataset has 800 fewer classes than the ImageNet dataset, with 100,000 training examples and 10,000 validation examples.
How can I use Tiny ImageNet dataset in PyTorch or TensorFlow?
You can stream the Tiny ImageNet dataset while training a model in PyTorch or TensorFlow with one line of code using the open-source package Activeloop Deep Lake in Python. See detailed instructions on how to train a model on a tiny imagenet dataset with PyTorch in Python or train a model on a tiny imagenet dataset with TensorFlow in Python.