Closed sazippe closed 5 years ago
You can use the StereoNoFt model to pretrain the monocular model on Cityscapes. Remember to cut off the bottom part for the Cityscapes dataset.
I want to know the flow of the following training. StereoUnsupFt→Mono pt No S,K→C,K
Is this flow correct? First, train stereo model on scenflow and then finetune with KITTI. Next, train mono model (pt with VGG) on Cityspace and then finetune with KITTI.
Yes
Thank you! Training list is 'list/cityscapes_train_list.txt', right?
Yes. Note that you should supervise the mono model (pt with VGG) on Cityscapes with StereoNoFt and then finetune on KITTI with StereoUnsup/SupFt model. The learning rate is not changed for finetuning.
Thank you for your advice.
Table 1 StereoUnsupFt→Mono pt No S,K→K 0.099 0.745 4.424 0.182 0.884 0.963 0.983 StereoUnsupFt→Mono pt No S,K→C,K 0.095 0.703 4.316 0.177 0.892 0.966 0.984
From the result in Table1, i can see that using Cityscapes datasets will improve overall performance.
I want to know how to use Cityscapes datasets on training. After training mono network by KITTI datasets, then finetune its network by Cityscapes datasets? Or training mono network by both KITTI and Cityscapes datasets?