25,000 labeled images of dogs and cats partitioned for binary classification tasks. The collection provides a standard benchmark for training convolutional neural networks to distinguish between two common pet species in diverse real-world settings.
Use Cases
- Train a convolutional neural network (CNN) to predict the class label based on raw image pixel values
- Benchmark transfer learning performance using pre-trained models like ResNet or VGG on the dog and cat image files
- Test image preprocessing pipelines including resizing and color normalization on the JPEG source files
Strengths
- 25,000 total JPEG images split between training and testing directories
- Binary classification labels for 'dog' and 'cat' categories
- Varied image resolutions and orientations requiring preprocessing and normalization