Table 1 Computational resources and cost associated with training and sampling the model and annotating a 2B sample
From: Exploring the GDB-13 chemical space using deep generative models
| Operation | CPUs | RAM | GPU | Time |
|---|---|---|---|---|
| Training a model | 4 | 32 GB | 1 | 8 min/epoch |
| Sampling molecules | 4 | 32 GB | 1 | 33 million/h |
| Annotating 2B molecules | 32 | 256 GB | 0 | 24 h |