dxjundersky

mIoU about "rn18_single_scale.py".

4

Thank you for sharing the train. I tried "python train.py configs/rn18_single_scale.py --store_dir=/path/to/store/experiments" but only get "Best mIoU: 69.45% (epoch 240)". The paper says the mIoU is 75.4% SwiftNetRN-18† val 75.4...

swiftnet

3

Thanks for sharing. I just trained the model with default parameters on Cityscape dataset.(1024*2048) The mIoU is 0.711 after 200 epochs. But the paper "In Defense of Pre-trained ImageNet Architectures...

Hi, Thanks for your code. I found that the functions erfnetA and erfnet B didn't use the parameter dropout (dropout = 0.3,always). (erfnet_segmentation/erfnet.py) So, the dropout doesn't be closed when...