HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Add Hindi हिन्दी and Arabic العربية Docs translations (#6428)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2023-11-18 21:51:47 +01:00 • committed by GitHub
parent b6baae584c
commit 02bf8003a8
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
337 changed files with 6584 additions and 777 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/en/hub/app/android.md
View file

@ -43,7 +43,7 @@ FP16 (or half-precision) quantization converts the model's 32-bit floating-point
INT8 (or 8-bit integer) quantization further reduces the model's size and computation requirements by converting its 32-bit floating-point numbers to 8-bit integers. This quantization method can result in a significant speedup, but it may lead to a slight reduction in mean average precision (mAP) due to the lower numerical precision.
!!! tip "mAP Reduction in INT8 Models"
!!! Tip "mAP Reduction in INT8 Models"
The reduced numerical precision in INT8 models can lead to some loss of information during the quantization process, which may result in a slight decrease in mAP. However, this trade-off is often acceptable considering the substantial performance gains offered by INT8 quantization.