Issue with training - Githubissues

yashbhalgat / Contrastive-Lift

[NeurIPS 2023 Spotlight] Code for "Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion"

59 stars 1 forks source link

Open gtangg12 opened 7 months ago

gtangg12 commented 7 months ago

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 commented 7 months ago

I disabled probabilistic_ce_mode: "TTAConf"

Is this param important?

What do these images mean?