Munan Ning

thanks a lot. i am still trying to train my segan. i found only send the predict labels can not work, so i am trying sending both the labels and...

Sorry for the delay. @zhijiew @sharat29ag The result on DeeplabV2 is implemented. Beyond expectation, the final result is 65.16 (mIoU), better than 64.89 (mIoU) with DeeplabV3+. Here is the origin...

> For the warmup you have used AdaptNet which uses DeeplabV2 as the Segmentation model, was that also changed to DeeplabV3+? If yes can you please report the initial result...

> @sharat29ag The answer is 'the same'. The weight can be found in Adaptset (https://github.com/wasidennis/AdaptSegNet). The list is the same as the V3 version.