About test performance about graphcmr HOT 6 CLOSED

These are losses and training renders.
Meanwhile I tried several different hyperparamters, but it didn't work much.

from graphcmr.

We did not use any special tricks. I can see from the plots that the camera scale and ty are the same in all images. I've seen this collapse happen a few times, and when this happens I restarted the training and it worked. Usually you can see if this is the case in the first few thousand iterations. Can you try that?

from graphcmr.

Thanks for replying.
'Restart' means resuming or starting from epoch 1?

from graphcmr.

Start training from scratch.
Can you try to finetune one of the pretrained models? If something is wrong with the data then the metrics should start to become worse.

from graphcmr.

I use h36m and up3d to train the vertices part ( graph_cnn.gc + graph_cnn.shape ), it seems well.

Then fix the parameters, train the camera part ( graph_cnn.camera ) several times, it always collapses to around (0.85, 0.001, 0.2).

from graphcmr.

Start training from scratch.
Can you try to finetune one of the pretrained models? If something is wrong with the data then the metrics should start to become worse.

Thanks for replying, I will try the pretrained model today.

from graphcmr.