thepate94227
thepate94227
Oh ok, thank you for your answer. > > > currently the coco format does not support holes in object annotations
It would be great if you could answer here, if the coco format supports holes in object annotations.
> I think your PATH to the dataset is incorrect Thank you for your answer. But my PATH to the dataset is like yours. My Path is ..../datasets/VOCdevkit/VOC2012/' And the...
Thank you for your answer. Hm, thats weird. I downloaded it from the official site: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/#devkit I don't know why there are 17K Input Images, but only 2.9K Segmentation Images....
An another question: how can i save the model after the training? I don't know how to use google Colab with my own data, which are on my PC. Therfore...
> Hey @thepate94227 I think this is a related issue: #35 > > I have a similar problem but not on the output (classes) side, rather than input side. >...
@blaxe05 Hi, I am sorry, but because of this problem and other problems i didn't use Deeplab. In my case i used Mask R-CNN. So unfortunately i don't know the...
Can somebody help me? I just need an mAP for my testset. I splited my Data into Trainingset, Validationset and Testset and trained my network for a long time. Now...