Stochastic Optimization
Gradient Checkpointing
Introduced by Chen et al. in Training Deep Nets with Sublinear Memory CostGradient Checkpointing is a method used for reducing the memory footprint when training deep neural networks, at the cost of having a small increase in computation time.
Source: Training Deep Nets with Sublinear Memory Cost
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 2 | 20.00% |
| MRI Reconstruction | 1 | 10.00% |
| Classification | 1 | 10.00% |
| Zero-Shot Transfer Image Classification | 1 | 10.00% |
| Language Modelling | 1 | 10.00% |
| Text Generation | 1 | 10.00% |
| Self-Supervised Image Classification | 1 | 10.00% |
| Self-Supervised Learning | 1 | 10.00% |
| Semi-Supervised Image Classification | 1 | 10.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
