Ozan Sener
Ozan Sener
This is a confirmed bug. Will be fixed in an update
We will update the code in a few days with `depth_mean.npy` and config files. But, in the mean time here are the config files if you do not want to...
@r0456230 Can you tell me what exactly you are trying to reproduce? The config files I put as a comment should give exact results of mgda w/ and w/o approximation....
@maria8899 Although we are planning to support pytorch 1.0, I am not sure when will it be. I will also update the ReadMe with the exact versions of each Python...
@kilsenp First let me answer the 2. - 2: You are right if you apply MGDA directly, it should be gradients with respect to parameters. However, one of the main...
@liyangliu @youandeme How are you evaluating the MultiMNIST? We did not release any test set, actually there is no test set. The code generates random test set every time you...
@liyangliu For MultiMNIST, I think there are issues since we did not release a test. Everyone reports slightly different numbers. In hindsight, we should have released the test set but...
@liyangliu Instance segmentation one looks strange. Are you using the hyper-params I posted for both single task and multi-task. Also, are the tasks uniformly scaled or are you doing any...
Thanks I will try to make an update sometime next week.
We are reporting disparity in the pixel space after normalization. I know it is not a standard metric and has no real practical meaning especially since it is normalized, but...