google-deepmind / google-deepmind/deepmind-research
"contribution_scores" (gradient * input) outside the middle 896 bins in Enformer
Open
- Dominant language
- Jupyter Notebook
- Stars
- 15.2k
- Forks
- 2.9k
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I appreciate for developing this great tool, Enformer.
I am using it according to the enformer-usage.ipynb.
The length of input sequence is 393,216 bp (128 bp * 3072 bin).
The length of "contribution_scores" is also 393,216.
But, the "contribution_scores" outside the middle part (128 bp * 896 bin) are all zero.
Does this mean the outside part (1088 bin on each side) doesn't contribute to prediction results?
Is there any way to calculate the contribution scores of the outside part?
I am sorry to bother you.
Contributor guide
Assessment
This issue has not been assessed yet.