oconnor127

Save output depth map

1

Hey, I want to save the depth map estimated by your approach. How is that possible? Right now if I am running python3 main.py --evaluate /home/username/Downloads/model_best.pth.tar --val select I just...

Any Description?

1

Hey, your algorithm looks very nice. Is there any chance to get all the coordinates to there corresponding superpixel? So that I have an array of points for superpixel 0,...

Hey, I simply want to run your pretrained model. How is that possible? What I have done: I used your Kitti download script and modified the download path. I run:...

Hey, I cannot convert a model which uses BatchNormalization Layers, because of dimension mismatches.. Assume the input tensor for BN is 48x112x112 (CHW) the parameters (e.g. gamma) has a size...

Paper Question: Use compression idea and generate same result as multi-branch model?

1

Hey, I am just curious if I get this right. Could I just use your re-parametrization approach as a "compression approach" and thus make those multi-branch networks (e.g. ResNet, MobileNet...

Is there any recommended way to train the metric model on e.g. nyu AND ADDITIONALLY custom data (metric groundtruth values are provided) ?

Hey, at first: Awesome code! Second: I didnt figured out how to access the image directly in python? I dont want to save that image, I want to add some...

Conv2D in Stage0 (Beginning) not mentioned in paper

1

Hey, I just have a look at your implementation and the resulting reparametrized graph and see that you have a conv2D at the very beginning (stage0) of your network, which...