Orsai comments

Repositories
Issues
Comments

Results 3 comments of


                                            Orsai

smooth_L1_loss_layer.cpp:19] Check failed: bottom.size() == 4 (3 vs. 4) If weights are used, must specify both inside and outside weights.

I am facing the same problem. @Stark123 Could you please explain how train_faster_rcnn_alt_opt.py solved your problem?

"OutOfBoundsDatetime: Out of bounds nanosecond timestamp" error.

In transform.py, the starting date is computed as ``` if start is None: # py datetime min/max are out of range of pd.Timestamp min/max start_target = pytz.UTC.localize(pd.Timestamp.min) + timedelta(days=1) start_inf...

FingerTip Dataset Format

Thanks a lot for your fast response. I did not mean to share your dataset, I was just curious on how to annotate a "background" image in COCO format. I...