Open MOMOANNIE opened 1 year ago
Hi, thank you for your interest. The problem occurred here is related to the cropping. You can see there is a warning "N forground 0, background #######, unable to generate class balanced samples". Please double check your label input and the foreground region within the label. Seems like there is no foreground within the label region for them to crop.
Hi, thank you for your interest. The problem occurred here is related to the cropping. You can see there is a warning "N forground 0, background #######, unable to generate class balanced samples". Please double check your label input and the foreground region within the label. Seems like there is no foreground within the label region for them to crop.
Thank you for answering my question in time, I checked the image and label of the training data. The following two pictures are the corresponding image and label. There will be multiple foregrounds in the label image, but some foregrounds will be very small. Will this affect it?
您好,想请教一下如何换成自己的数据集
Hello, the dataset I use is also small target binary segmentation, does this model work reasonably on your dataset?
Hello, when I train my own data, I set
dataset == 'flare', out_classes = 2
, when the training reaches 10,000 steps, why the loss does not drop? The loss curve is as follows: