You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am training a custom model for my electric meter which uses black pointers on the analog counters. 2 of the 5 counters spin in a counter clockwise pattern. Looking at the files generated from the readout, it doesn't seem that any sort of distinction is being made between images from CCW dials vs CW. The dials are marked with numbers 0-9, in the CCW counters the location of each number is mirrored.
After we load the images from the meter they need to be classified. Are CCW images supposed to be classified according to the CW value represented by the position of the pointer on the circle or do we take into account that it's CCW and classify it with the CCW value.
In this image should the value be classified as 1.7 (CCW) or 8.3 (CW)
The text was updated successfully, but these errors were encountered:
I am training a custom model for my electric meter which uses black pointers on the analog counters. 2 of the 5 counters spin in a counter clockwise pattern. Looking at the files generated from the readout, it doesn't seem that any sort of distinction is being made between images from CCW dials vs CW. The dials are marked with numbers 0-9, in the CCW counters the location of each number is mirrored.
After we load the images from the meter they need to be classified. Are CCW images supposed to be classified according to the CW value represented by the position of the pointer on the circle or do we take into account that it's CCW and classify it with the CCW value.
In this image should the value be classified as 1.7 (CCW) or 8.3 (CW)
The text was updated successfully, but these errors were encountered: