Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improve Test Vector Generation #8

Merged
merged 4 commits into from
Nov 4, 2024
Merged

Improve Test Vector Generation #8

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
06dcbf6
[fix] Fix wrong bitwidth of weights
Xeratec Oct 30, 2024
5942086
[feature] Print warnings for problematic vectors
Xeratec Oct 30, 2024
93c3986
[change] Reduce calculated bit width of AV
Xeratec Oct 30, 2024
9f5eb55
[change] Remove outdated comment
Xeratec Oct 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
[change] Remove outdated comment
  • Loading branch information
@Xeratec
Xeratec committed Oct 30, 2024
commit 9f5eb559138a10c6a04af85ee647c4ee63ae7a9f
2 changes: 0 additions & 2 deletions PyITA/softmax.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,8 +157,6 @@ def streamingPartialSoftmax(x, integerize = True):

## STAGE 2: Calculate the softmax activation
# Invert the partial sum
# WIESEP: Scale Softmax to 127
# The Softmax values are maximum 127 as sumdotp modules can only do signed-signed operations for now. This is a temporary fix until sumdotp is fixed.
if integerize:
exp_partial_sum_inverse = np.floor((2**8 - 1) * 2**8 / exp_partial_sum).astype(np.int32)
else:
Expand Down
Loading