search

3DCVdeveloper / BGNet

Xuyuhua works
118 stars 23 forks source link

Error when using your pretrained Sceneflow-BGNet.pth Model ! #7

Open wuzhongwulidong opened 3 years ago

wuzhongwulidong commented 3 years ago

Great work! However there is a mistake when using your pretrained Sceneflow-BGNet.pth Model ! As when all know, SceneFlow dataset consists of color images of 3 channels ,but in your code: self.feature_extraction = feature_extraction(image_planes) self.firstconv = nn.Sequential(convbn_relu(1, 32, 3, 2, 1, 1), that is to say your model only accept one channel images. Also, I find that your pretrained Sceneflow-BGNet.pth just exactly accept one channel images. So how can I reproduce the EPE result of CUBG on SceneFlow using your pretrained model, as your paper report CUBG EPE=1.17 in Table 1?

leaf0793 commented 3 years ago

You should read the code more carefully, if you have check the dataloader for kitti under folder dataset. you would see the image has been transferred to Gray image (line 37). PS. If you have solved this problem, are you able to reproduce the result of kitti with the provided pretrained model?