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 tried to use this code for the segmentation of VOC dataset. It has about 2900 images, I use the deeplabV2 model.
The loss hardly decreases after 2k steps (I use 3 as batch size ), and it's around 0.7-1.
I don't know why.
The text was updated successfully, but these errors were encountered:
Did you switch all the batch norm to eval mode? I received the report the model could be trained on Pascal VOC 2012, although the result was 1 point lower (here). Basically, I think you only have to replace the COCO-Stuff data loader with a third-party one for VOC. Anyway, please try with a default setting (10 samples as a batch, 20k steps)
Thank you for your reply. It works really well. I have another question, the init model, deeplabv2_resnet101_VOC2012.pth, is it trained on resnet for image classification or something?
An init model is actually deeplabv2_resnet101_COCO_init.pth, which is "ResNet-101 + ASPP" model trained on MSCOCO segmentation set. The "ResNet" part was pre-trained on ImageNet.
The deeplabv2_resnet101_VOC2012.pth that you mentioned is a model which was initialized with MSCOCO parameters above and trained on Pascal VOC 2012.
I tried to use this code for the segmentation of VOC dataset. It has about 2900 images, I use the deeplabV2 model.
The loss hardly decreases after 2k steps (I use 3 as batch size ), and it's around 0.7-1.
I don't know why.
The text was updated successfully, but these errors were encountered: