Closed MarioCavero closed 2 years ago
After changing the complete PC (.pcd
) to a (.ply
), it works fine. For some reason, partial PCs are okay to be (.pcd
) but the network messes up with (.pcd
) complete PCs.
(Images of first, second and third epoch with shuffled dataset).
.
I modified
_load_data(self)
in order to load my data. At the moment I have a small dataset to test the learning, 280 per object in train, 120 in test, partial and completes). Names of the files just go from0
to279
in train (0.pcd
,1.pcd
, etc), and280
to399
(280.pcd
,281.pcd
, etc). I'm not using right nowmodel_id
fromline.split
.On the first epoch, everything runs smoothly. But after the first epoch, the loss goes up, and looking in the log, the ground truth point cloud is for some reason, just a point, regardless of the one I am loading. (Yes, I checked them, they are good pointclouds). [First picture, epoch 1, second, epoch 2, of a run I made].
![epoch_002](https://user-images.githubusercontent.com/23640690/173523593-c746e255-3e62-430b-9a28-ba92dc548447.png)
My guess is that it has something to do with either
_load_data
or with__getitem__
, but trying to get my head around it, the loading of the data seems correct. Maybe a modification in__getitem__
needs to be done for my specific type of data. I did a test on just loading the same complete PC per object, and it happens the same, first epoch is okay, after the first one, the Ground Truth get's interpreted by a point.