Jonas Pirner comments

Results 15 comments of


                                            Jonas Pirner

Missing explanation for implementation logic lesson 5

I just found that in the next [section](https://github.com/microsoft/IoT-For-Beginners/tree/main/2-farm/lessons/5-migrate-application-to-the-cloud#task---send-a-direct-method-request-to-a-device) the implementation of the logic is explained. Maybe it would be nice to add a disclaimer that soil moisture output logic will...

fix: formatting in notebook.md

Thanks for the hint @onuralpszr. Accepted CLA

Add ensembling methods for tiling to Anomalib

we are also very much looking forward to this 👍

[Bug]: Visualizer in for loop increases RAM successively

Hi @blaz-r, FYI based on your message I thought I give the `OpenVINOInferencer` a try but also there memory increases..

[Bug]: Visualizer only adding anomalous label

thanks for the hint @DiagoAlaraviz I just edited my answer

Clicking onto pane disallows readjusting of PolygonLabels

For me switching from Chrome to Microsoft Edge solved the issue.

[Bug]: EfficientAd training via API slower than via CLI

Thanks @alexriedel1! I tested again and made sure both use category bottle by running CLI version like: ``` anomalib train --model EfficientAd --data anomalib.data.MVTec --data.category bottle --data.train_batch_size 1 ``` After...

[Bug]: EfficientAd training via API slower than via CLI

@ashwinvaidya17 which python version did you use?

[Bug]: EfficientAd training via API slower than via CLI

I again tested this time with Python 3.11.9 and with your cli and api scripts you provided @ashwinvaidya17 I only changed number of epochs to 5 ### API ``` 25406833...

[Bug]: EfficientAd training via API slower than via CLI

Seems to be a windows related problem... just created the same env under ubuntu via WSL and I get much faster training times: ### CLI ``` 33759240 function calls (32844378...