github-starred/cs249r_book
2
0
Fork 0
mirror of https://github.com/harvard-edge/cs249r_book.git synced 2025-12-05 19:17:28 -06:00
Code Issues Packages Projects Releases Wiki Activity

Fixing typos in 3 files (#1055)

Browse Source
This commit is contained in:
Didier Durand
2025-11-28 18:06:54 +01:00
committed by GitHub
parent 15c2b8df46
commit 3c196d681c
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
quarto/contents/core/data_engineering/data_engineering.qmd
View File

@@ -325,7 +325,7 @@ pics/target/.style = {
\node[Box,below right=1 and 1.5 of CI1,draw=OrangeLine](){};
%governance
\pic[shift={(0,0.05)}] at (S1){vaga={scalefac=0.25,picname=1,filllcolor=BlueLine, Linewidth=0.75pt,filllcirclecolor=orange}};
%arrwos
%arrows
\tikzset{Text/.style={,font=\usefont{T1}{phv}{m}{n}\small,align=center}}
\draw[LineD](B1)--node[above,Text]{Validation overhead vs.\\ throughput}(B2);
\draw[LineD](B1)--node[left,Text]{Bias mitigation vs.\\ data availability}(B3);

2
quarto/contents/core/ml_systems/ml_systems.qmd
View File

@@ -80,7 +80,7 @@ These physical constraints are not temporary engineering challenges but permanen
% Parameters
\def\angle{10} % angle
\def\length{18} % Lengths (cm)
\def\npoints{5} % number of poihnts
\def\npoints{5} % number of points
\def\startfrac{0.13} % start (e.g.. 0.2 = 20%)
\def\endfrac{0.87} % end (e.g.. 0.8 = 80%)

2
quarto/contents/labs/seeed/grove_vision_ai_v2/image_classification/image_classification.qmd
View File

@@ -166,7 +166,7 @@ Taking advantage of this opportunity, a similarly trained model, MobilenetV2 96x
![](./images/png/benchmark.png){width=80% fig-align="center"}
> The Grove Vision AI V2 with an **ARM Ethus-U55** was approximately 14 times faster than devices with an ARM-M7, and more than 100 times faster than an Xtensa LX6 (ESP-CAM). Even when compared to a Raspberry Pi, with a much more powerful CPU, the U55 reduces latency by almost half. Additionally, the power consumption is lower than that of other devices (see the [full](https://www.hackster.io/limengdu0117/2024-mcu-ai-vision-boards-performance-comparison-998505) article here for power consumption comparison).
> The Grove Vision AI V2 with an **ARM Ethos-U55** was approximately 14 times faster than devices with an ARM-M7, and more than 100 times faster than an Xtensa LX6 (ESP-CAM). Even when compared to a Raspberry Pi, with a much more powerful CPU, the U55 reduces latency by almost half. Additionally, the power consumption is lower than that of other devices (see the [full](https://www.hackster.io/limengdu0117/2024-mcu-ai-vision-boards-performance-comparison-998505) article here for power consumption comparison).
### Postprocessing {#sec-image-classification-postprocessing-9610}