Comments (6)
Data was dropped in the UART path. If you look at the code here you can see that a byte was dropped.
} else {
size_t numbytes;
char test[3];
long res;
/* Two hexdigits per byte */
numbytes = th_strnlen(p_next, EE_CMD_SIZE);
if ((numbytes & 1) != 0) {
th_printf("e-[Insufficent number of hex digits]\r\n");
return EE_ARG_CLAIMED;
}
test[2] = 0;
This can be cause by too high a baud rate, or an error in the Rx code, or an issue with the Host<>UART hardware driver (e.g., the Prolific USB<>TTL, SiLabs USB<>TTL, and STM VCP driver could be the issue).
Peter
from tiny.
Also, the latest 3.0.6 version has a setting in the ini file called disable-mute
. Set that to true to disable muting the bload messages. This can help you identify when/where it is failing.
from tiny.
Using baudrate of 115200 during compilation of the bin and for the runs solved the issue , though it is recommended in the reference submission's Readme that 921600 is the desirable baudrate.
from tiny.
Thanks @shijay01 . 921600 is recommended to speed up the accuracy test that downloads lots of data over serial. However, it seems the higher baud rate is not working on all systems. I'm glad 115200 solved it for you. I'm adding a note on this in the README #82
from tiny.
@shijay01 That is good news. Please close the issue if resolved. Cheers, Peter
from tiny.
Thankyou @cskiraly and @petertorelli . Closing the issue.
from tiny.
Related Issues (20)
- User guide for submitter/internally implemented was never published
- addQuantize and addDequantize in th_final_initialize of anamoly detection submitter_implemented.cpp HOT 7
- need clarification on the pre-processing rules in open division
- Measure performance and accuracy on customized dataset
- Anomaly detection - AUC for quantized model with INT8 input/output HOT 2
- Loss is negative and accuracy=0.006 when tried to prune anamoly detection HOT 1
- Cannot get anomaly_detection to run, memory issues
- Model from visual wake word does not work for Harvard tinyMLx course arduino code
- Reference keyword recognition. Compilation error in ws_bootstrap_ffn.c HOT 1
- EEMBC runner input binary files
- Where is the Visual Wake Word test set? HOT 5
- Changelog
- Confusing unused batch_size Variable in train_vww.py
- Totally off accuracies for anomaly detection with quantized I/O model HOT 3
- keyword spotting: linker error
- Inconsistency with bias enabled in the pytorch model (Conv2d) for image classification HOT 1
- Environment setup for Streaming WakeWord HOT 2
- Anomaly Detection get_datasets.sh not working HOT 1
- Inclusion of a LICENSE file. HOT 2
- Add paper reference
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tiny.