Evaluation of Volumetric Model

[sunwonlikeyou]

I simulated pretrained volumetric model with pretrained backbone.
and i got these result.
'S11': {'Average': 158.4710789766407, 'Directions': 13.81251708984375, 'Discussion': 20.87702763545049, 'Eating': 107.31265129841549, 'Greeting': 104.50263323102679, 'Phoning': 249.43584526909723, 'Posing': 33.8868872601053, 'Purchases': 160.68772977941177, 'Sitting': 87.17900390625, 'SittingDown': 264.5645211641906, 'Smoking': 240.20394674161585, 'TakingPhoto': 190.77657277960526, 'Waiting': 58.71925354003906, 'Walking': 307.15990271935095, 'WalkingDog': 243.03764997209822, 'WalkingTogether': 201.88863716873468}

and also i checked heatmap from backbone in volumetric model

but heatmap from backbone in algebraic model is

is there problem or mistake on evaluation??

[shrubb]

Looks like you caught a bug. These heatmaps seem unnatural to me, as if the network is underfit or overfit. For example, I believe there shouldn't be such checkerboard patterns. You probably messed up .requires_grad, .eval() vs .train() or something like that.

[sunwonlikeyou]

Backbones were all eval() and also all tensors' requires_grad were also False.
And That plottings are heatmap of 'Directions-1' which shows good quantitative result but i can check poor heatmap result.
And also I checked Loading pretrained weights for backbone and whole model.
can you show me your log files??

[shrubb]

Hi, unfortunately I don't have logs :( I still bet you have a bug somewhere in the backbone. I suggest that you try checking activations and gradients layer-wise.