ImageNet
ImageNet is a large-scale labeled image dataset organized into semantic categories and widely used for visual-recognition research and benchmarking.
Sutskever's List
ImageNet is a large-scale image dataset organized according to a hierarchical set of semantic categories for visual recognition research.
- How it is used
- Positions ImageNet as a large-scale benchmark for testing whether neural networks can advance visual recognition.
- How deep it goes
- Traces the dataset’s origins and competition results, but does not detail its construction or annotation procedures.
- Examples
- Uses tables, lamps, and mugs to illustrate object categories, then contrasts early SVM results with AlexNet’s error reduction.
- What you can do after
- Understand how ImageNet’s competition helped demonstrate the impact of CNNs on visual recognition.
Inside Deep Learning: Math, Algorithms, Models
A large image classification dataset with 1,000 classes used here as the pretraining source domain for ResNet.
- How it is used
- Provides pretrained source-domain weights for transferring ResNet to a new image-classification task.
- How deep it goes
- Identifies a 1,000-class dataset with one million training images and explains its pretraining role, but not its construction.
- Examples
- Uses pretrained ResNet-18 for cat-versus-dog classification after replacing its final fully connected layer.
- What you can do after
- Apply it via torchvision.models.resnet18(pretrained=True) to initialize ResNet-18 before replacing its classifier.
Read how Inside Deep Learning: Math, Algorithms, Models explains ImageNet →
Also covered in
- Introduction to Generative AI, Second Edition
- Designing Deep Learning Systems: A guide for software engineers
- Deep Learning with Python, Third Edition
- Deep Learning with R, Third Edition
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- computer visionComputer vision is the field of computing concerned with extracting and interpreting information from images, video, and other visual data.
- GPT modelA GPT model is a generative, autoregressive Transformer language model in the family developed by OpenAI.
Related concepts
- datasetkind of · A dataset is an organized collection of related data items, records, observations, or examples treated as a unit for storage, processing, or analysis.
- foundation modelused by · A foundation model is a broadly trained machine-learning model whose learned capabilities can be reused or adapted for a range of downstream tasks.
- ResNet50used by · ResNet50 is a 50-layer residual convolutional neural network architecture commonly used for image recognition and visual feature extraction.
- transfer learningused by · Transfer learning is a machine-learning technique that reuses knowledge learned from one task, dataset, or domain to improve learning or performance on another.
Questions about ImageNet
What is ImageNet?
ImageNet is a large-scale labeled image dataset organized into semantic categories and widely used for visual-recognition research and benchmarking.
Which Manning books explain ImageNet?
Sutskever's List and Inside Deep Learning: Math, Algorithms, Models.
What should I know before learning ImageNet?
Manning books that teach ImageNet usually introduce language model, computer vision and GPT model first.
What is ImageNet a kind of?
ImageNet is a kind of dataset. A dataset is an organized collection of related data items, records, observations, or examples treated as a unit for storage, processing, or analysis.
What are the parts of ImageNet?
ImageNet includes ImageNet-1k.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

