Edge Impulse Experts / Pharma Pills Defects Public
Target: Nvidia Jetson Nano Clone this project

Test data

Set confidence thresholds
Model variants
Test 'Unoptimized (float32)' model Test 'Quantized (int8)' model
Set the 'expected outcome' for each sample to the desired outcome to automatically score the impulse.
Sample name Expected outcome F1 score Result
sample.3lfgim19 defect, defect, defect, defect 100%
Show classification Show in data acquisition
sample.3lancsv9 defect, defect, defect 80%
Show classification Show in data acquisition
sample.3lanab4o defect, defect, defect, defect, defect, defect 90%
Show classification Show in data acquisition
sample.3lan7k91 defect, defect, defect 100%
Show classification Show in data acquisition
sample.3lan4nck defect, defect 100%
Show classification Show in data acquisition
sample.3lan2p24 defect, defect 100%
Show classification Show in data acquisition
sample.3lan1kov defect, defect, defect, defect, defect, defect 100%
Show classification Show in data acquisition
sample.3lan0bsv defect, defect, defect, defect, defect, defect, defect, defect, defect 100%
Show classification Show in data acquisition
sample.3lamtnl7 defect, defect, defect, defect, defect 74%
Show classification Show in data acquisition
sample.3lamsior defect, defect, defect, defect, defect 88%
Show classification Show in data acquisition
sample.3lamqd0c defect 0%
Show classification Show in data acquisition
sample.3lammm72 defect 100%
Show classification Show in data acquisition
sample.3lamjluc defect 100%
Show classification Show in data acquisition
sample.3lamj8vj defect 100%
Show classification Show in data acquisition
sample.3lamh6i9 defect, defect, defect, defect, defect 88%
Show classification Show in data acquisition
sample.3l8namv9 defect, defect, defect, defect 100%
Show classification Show in data acquisition
sample.3l8btn9k defect, defect, defect, defect, defect, defect, defect, defect 100%
Show classification Show in data acquisition
sample.3l8bncfg - 0%
Show classification Show in data acquisition
sample.3l8bkkep defect 100%
Show classification Show in data acquisition
sample.3l8bdud7 defect, defect, defect 100%
Show classification Show in data acquisition
sample.3l8bdj4v defect, defect, defect 85%
Show classification Show in data acquisition
sample.3l8balqq defect, defect 80%
Show classification Show in data acquisition
sample.3l8b9e8u defect 100%
Show classification Show in data acquisition
sample.3l8b96no defect 100%
Show classification Show in data acquisition
sample.3l8b59d2 - 100%
Show classification Show in data acquisition
sample.3l8b098h defect, defect, defect 100%
Show classification Show in data acquisition
sample.3l8arafi defect, defect, defect 100%
Show classification Show in data acquisition
sample.3l8aofgg defect, defect, defect 85%
Show classification Show in data acquisition
sample.3l8alt49 defect 66%
Show classification Show in data acquisition
sample.3l8aj619 defect, defect 100%
Show classification Show in data acquisition
sample.3l8af6j9 defect, defect, defect 100%
Show classification Show in data acquisition
sample.3l8adj8p defect 100%
Show classification Show in data acquisition
sample.3l8a9q6t - 100%
Show classification Show in data acquisition
sample.3l8a8ugr - 100%
Show classification Show in data acquisition
sample.3l8a89tv - 100%
Show classification Show in data acquisition
sample.3l8a6ist defect 100%
Show classification Show in data acquisition
sample.3l8a5eli defect 100%
Show classification Show in data acquisition
sample.3l8a0fg7 defect, defect 100%
Show classification Show in data acquisition
sample.3l89u14c - 100%
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
89.74%

Confusion matrix

Loading...

Feature explorer

Loading...
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy