metadata
datasets:
- imagenet-1k
pipeline_tag: image-classification
Model Architecture Details
Architecture Overview
- Architecture: ViT Small
Configuration
| Attribute | Value |
|---|---|
| Patch Size | 32 |
| Image Size | 224 |
| Num Layers | 3 |
| Attention Heads | 4 |
| Objective Function | CrossEntropy |
Performance
- Validation Accuracy (Top 5): 0.4179
- Validation Accuracy: 0.2148
Additional Resources
The model was trained using the library: ViT-Prisma.
For detailed metrics, plots, and further analysis of the model's training process, refer to the training report.