Raaj
Raaj
inverse_warp2 What is difference between projected_depth and computed_depth. Is the transformed depth map the projected depth? Also, for projected depth why are you not using nearest neighbour interpolation. depthmaps must...
I just ran some of my own datasets on the CPP version. It worked great, but it was very noisy (keypoints detected all over) in the python version. Why might...
I noted that in your model, everywhere that BatchNorm is used (track_running_stats) is False! But in this one part here, it is True. https://github.com/JiaRenChang/PSMNet/blob/master/models/submodule.py#L108 Why is this the case??
I refer to this section of the code: ``` cost = Variable(torch.FloatTensor(refimg_fea.size()[0], refimg_fea.size()[1]*2, self.maxdisp/4, refimg_fea.size()[2], refimg_fea.size()[3]).zero_()).cuda() for i in range(self.maxdisp/4): if i > 0 : cost[:, :refimg_fea.size()[1], i, :,i:] =...
What is it doing internally?
Is somebody able to create a visualziation for me to see the model structure? I am not able to make it work.
If I already have a calibrated Stereo Camera Pair and IMU, is it possible to use this software? I understand that it attempts to calibrate the camera internally, but perhaps...
Do you have a pretrained model on the CIFAR dataset?
Adding it from the repo threw errors also
Does this code require that the transformations between these multiple cameras are fixed? or can they be independant and be solved for