14,493 images in 224x224x3 JPG format categorized into 100 distinct sports classes. The collection is partitioned into 13,493 training, 500 testing, and 500 validation samples for supervised learning tasks.
Use Cases
- Train a multi-class image classifier to identify specific sports using the 13,493 training images
- Benchmark computer vision model performance using the standardized 500-image test set
- Optimize model weights and prevent overfitting by monitoring performance on the 500-image validation split
Strengths
- 14,493 total images distributed across 100 sports categories
- Uniform image dimensions of 224x224 pixels in RGB (3-channel) JPG format
- Pre-defined data splits consisting of 13,493 training, 500 testing, and 500 validation samples