ChristianEschen

Line 456 in voc.py defines the metric function "_get_metric()" Currently, it uses a custem metric function "CustomMetric" defined in line 336-346 in voc.py The F1 metric function is suitable for...

it was related to programming issues. ________________________________ Fra: Matthias Stumpp Sendt: 3. april 2017 14:33:43 Til: itijyou/ademxapp Cc: ChristianEschen; Mention Emne: Re: [itijyou/ademxapp] Training a model with two classes only...

I will be glad to here about your outcome ________________________________ Fra: Christian Eschen Sendt: 3. april 2017 14:53:17 Til: itijyou/ademxapp Emne: Sv: [itijyou/ademxapp] Training a model with two classes only...

I would agree that one should use the .eval() function during testing

I have seen the same kind of artifacts. I try to translate one rgb image into another rgb image. (so no label maps and instance maps). If anyone can interpret...

I have the same problem. Using random_contrast destroys the categorical ground truth image