facebookresearch / facebookresearch/perception_models
How to find the best layer in downstream task?
Open
PE
question
- Dominant language
- Jupyter Notebook
- Stars
- 2.4k
- Forks
- 162
- PR merge metrics
- No merged PRs in 30d
Description
In the paper `Perception Encoder: The best visual embeddings are not at the output of the network`, Figure 13 presents the language alignment performance of features extracted from different layers.
For PElang-G, were 47 experiments (through 1M pretraining + 70M finetuning each) conducted to find out the best layer? What would be the recommended approach to find out the best layer when I am facing a new downstream task?
Contributor guide
Assessment
This issue has not been assessed yet.