Konstantin Gulin comments

Results 8 comments of


                                            Konstantin Gulin

Let modifiers implement epoch adjustment when composing recipes

@anmarques from my inspection this PR seems to cover all the desirable old behavior and avoids the error prone behavior of trying to catch attributes with "epoch" in their name...

model size became bigger after pruning model

@kuonumber `"training_results"` is the one field in the model dict that's expected to grow over time. In my experience I've seen it grow by ~.2MB per epoch. Which doesn't fully...

model size became bigger after pruning model

@kuonumber thanks for checking. It's not obvious from those printouts where the size difference comes from, but it's not the training results. Can you try running the commands below to...

The Trained yolov5 Weights didn't Load to Model

Hi @miladlink this was an issue with an earlier version of our yolov5 fork, where the `best` model was loaded for validation, but `best` may not fall within the range...

getting low fps & inference issue

@akashAD98 the low fps you're seeing may be a result of low computational resources offered by google colab. If you run the same annotation with a baseline model (with the...

model size became bigger after pruning model

Closing out as this is a stale issue and the YOLOv5 integration has been heavily reworked since. If a similar issue comes up, please feel free to open a new...

The Trained yolov5 Weights didn't Load to Model

This issue is now resolved. Closing out the ticket, but if the issue persists feel free to re-open the issue.

Add variable bit width support to ONNXToDeepsparse

@bfineran good callout. Updated the array quantization routine and propagated the `bit_width` args to address this