Graft-PSMNet

Graft-PSMNet copied to clipboard

An Error in retrain_CostAggregation.py.

14

adaptor.load_state_dict(torch.load(args.load_path)['net']) should it be changed to adaptor.load_state_dict(torch.load(args.load_path)['fa_net']) ?

xzjzsa

Are your training results stable?

1

Have you conducted multiple experiments and have the results of different epochs been stable?

hqyxy98

Whether to submit GraftNet to KITTI BenchMark?

2

Hi,thank you very much for your great work，Whether to submit GraftNet to KITTI BenchMark? I didn't find it on KITTI BechMark(Stereo Evaluation 2012&2015) although I have run it.

Zhaohuai-L

About the coloring method of qualitative results figures

1

Hi, can you tell me the coloring method in the paper? I usually use cv2.COLORMAP_JET. Thanks.

gangweiX

About the generalize ability of GwcNet.

2

I test generalize ability of GwcNet on KITTI and Middlebury using the official pretrained model, the result is 12.5% on KITTI 2012, 12.4% on KITTI 2015. But in your paper,...

gangweiX

@SpadeLiu , I observed that you added the following codes in DisparityRegression compared with the original function in PSMNet. Can you explain the purpose? ########### disp = torch.arange(0, self.max_disp).view(1, -1,...

MaitaYuki

About data structure

1

Hello, when i running the training with the follow command `python train_baseline.py` but i am getting the following error,would you provide any advice pls? `file ".../sceneflow_loader.py" ,line 38, in sf_loader...

Skyofshu