rginpan

Thanks for your quick response, I would like to know what is the difference between GMM and DUQ to estimate uncertainty? > Comapred with "What Uncertainties Do We Need in...

for example if `batch size` = 1, the `y_pred` is [0.1,0.2], `y` is[0,1]. - Does y_pred represent the distance to class 1 is 0.1 and to class 2 is 0.2?...

Sorry, my questions is how can I use modal-type embedding to know which feature is belong to which modal in the output? Thanks in advance!!

It is very common, just imagine if the GPU memory is still left in 2060 case, no matter how much the memory is increased with new GPU, the speed will...

I used only one sequence to train and valid (I know it will overfit), through the loss curve, it already convergenced, however the trajectory is still very bad... Could you...

@ArashJavan sorry for disturbing, if you did not know the reason, could you please give me your training hyper parameters.

@ArashJavan Thanks for your reply, I think "sequences" means images numbers, for example, sequences:3 represents 3 continuous frames I0, I1 and I2. I remember you explain in other close issue,...

@ArashJavan Thanks for your quick reply. Right now I understand, I already used [0,1],[0,2],[1,2] to get good result in only lidar network, so then I thought it will work on...

After I change the combinations and training 100 epochs, the result is still not good. What shoud I do, increasing the epochs numbers ? What is the ideal convergenced loss??...

config.yaml datasets: sequence-size: 3 # must be >= 1 combinations: [ [ 0, 1 ], [1,2], [2,3]] kitti: root-path-sync: "datasets/KITTI/sync" root-path-unsync: "datasets/KITTI/extract" image-width: 720 image-height: 57 crop-factors: [0, 0] #...