Questionable results on test data

[ShnitzelKiller]

I have trained the network for 120 epochs, and tried visualizing the frames output on the test data. Here are some example results (others that I've inspected look similar, with random bits getting moved):

Is this a sign that something has gone horribly wrong in the training, or is this something that is expected to happen?

The losses reported at the final epoch of training were as follows:

**** EPOCH 120 ****
2021-08-03 18:46:09.223722
EPOCH STAT:
mean mov loss: 1.437132
mean ref loss: 0.047632
mean disp loss: 0.118962
mean mov seg loss: 0.418661
mean part seg loss: 1.015106
mov seg acc: 0.984643
part seg err: 1.312428
Model saved in file: ../output/model_rpm_2021-08-02-15-04-37_all/ckpts/model.ckpt-120

[Salingo]

Hi, slight distortion in the predicted motion can be found in our experiments since our dataset is relatively small. However, I see a large distortion in your results. There are two ways to improve the performance: setting a larger batch size during training (requires more GPU memory); increasing the training data samples by adding jitters to the point cloud. Thanks.