AutoML
VEGA
Introduced by Wang et al. in VEGA: Towards an End-to-End Configurable AutoML PipelineVEGA is an AutoML framework that is compatible and optimized for multiple hardware platforms. It integrates various modules of AutoML, including Neural Architecture Search (NAS), Hyperparameter Optimization (HPO), Auto Data Augmentation, Model Compression, and Fully Train. To support a variety of search algorithms and tasks, it involves a fine-grained search space and a description language to enable easy adaptation to different search algorithms and tasks.
Source: VEGA: Towards an End-to-End Configurable AutoML Pipeline
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Continual Learning | 1 | 25.00% |
| Quantization | 1 | 25.00% |
| BIG-bench Machine Learning | 1 | 25.00% |
| Model Compression | 1 | 25.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
