yilundu
yilundu
Hi, You can find the interpretation of softplus here (appendix): https://arxiv.org/pdf/1811.02486.pdf If you assume that negative samples are drawn from the uniform distribution as opposed from the model distribution than...
How for testing the model, you can add the --render_test flag to your command. The flow model is slow due to the fact that the flow field becomes non-smooth over...
Hi, the HDR file contains the depth of each pixel in the image -- each element of the ".npy" represents the optical flow from one image to the subsequent one.
Hi the ground truth segmentation masks and test dataset can be found here: https://www.dropbox.com/s/ox1trjl4u9q7pyx/images_clevr.tar.gz?dl=0
Hi sorry about that -- does this link work? https://www.dropbox.com/s/0s3ti5i1y8aa85p/clevr_seg.tar.gz?dl=0
Hi, In the model, the --mem flag should add a computational scratchpad to models, so that that not only is an output optimization, but also an intermediate latent "scratchpad". Best,...
I believe so -- it should only do something on the MLP models
Hi, sorry about the above issue -- I am a bit busy with an upcoming conference deadline currently but will push a change later tonight
I just pushed a change -- can you see if it resolves your issue?
Can you install the torchdiffeq package found in https://github.com/yilundu/nerflow/tree/main/lib/torchdiffeq? Its a modified version of the official torchdiffeq package.