← Back to context Comment by jacquesm 14 hours ago The proper metric is the defect escape rate. 3 comments jacquesm Reply exidex 14 hours ago Now you have to count defects jacquesm 14 hours ago You have to do that anyway, and in fact you probably were already doing that. If you do not track this then you are leaving a lot on the table. exidex 11 hours ago I was more thinking in terms of creating a benchmark which would optimized during training. For regular projects, I agree, you have to count that anyway
exidex 14 hours ago Now you have to count defects jacquesm 14 hours ago You have to do that anyway, and in fact you probably were already doing that. If you do not track this then you are leaving a lot on the table. exidex 11 hours ago I was more thinking in terms of creating a benchmark which would optimized during training. For regular projects, I agree, you have to count that anyway
jacquesm 14 hours ago You have to do that anyway, and in fact you probably were already doing that. If you do not track this then you are leaving a lot on the table. exidex 11 hours ago I was more thinking in terms of creating a benchmark which would optimized during training. For regular projects, I agree, you have to count that anyway
exidex 11 hours ago I was more thinking in terms of creating a benchmark which would optimized during training. For regular projects, I agree, you have to count that anyway
Now you have to count defects
You have to do that anyway, and in fact you probably were already doing that. If you do not track this then you are leaving a lot on the table.
I was more thinking in terms of creating a benchmark which would optimized during training. For regular projects, I agree, you have to count that anyway