Issue with training

[gtangg12]

Hello, thank you for this great work!

for this line running on an itw dataset:

loss_semantics = (self.loss_semantics(output_semantics, probs) * confs).mean()

gives the error:

RuntimeError: 0D or 1D target tensor expected, multi-target not supported

Also requirements.txt has duplicate packages and is not complete i believe

[gtangg12]

I disabled probabilistic_ce_mode: "TTAConf"

Is this param important?

What do these images mean?