Daniel Ji

How to split train and test data?

1

I got 300 scans at all, and how can I split them into training and testing sets?

When you trian your custom dataset from scratch. Have you use any Image-Net pretrained model?

How to output last hidden state during inference?

1

Hi, Bunny team, Thanks for providing such a nice project. I am trying to extract the last hidden state of bunny-phi, and I add an extra parameter [here](https://github.com/BAAI-DCAI/Bunny/blob/b3dd0f768bd970c33685480207e8225fc810bdc1/bunny/eval/model_vqa.py#L63), like this:...

运行main.py出错

7

RuntimeError: Error(s) in loading state_dict for DataParallel: Unexpected key(s) in state_dict: "module.feature.features.norm0.num_batches_tracked", "module.feature.features.denseblock1.0.norm1.num_batches_tracked", "module.feature.features.denseblock1.0.norm2.num_batches_tracked", "module.feature.features.denseblock1.1.norm1.num_batches_tracked", "module.feature.features.denseblock1.1.norm2.num_batches_tracked", "module.feature.features.denseblock1.2.norm1.num_batches_tracked", "module.feature.features.denseblock1.2.norm2.num_batches_tracked", "module.feature.features.denseblock1.3.norm1.num_batches_tracked", "module.feature.features.denseblock1.3.norm2.num_batches_tracked", "module.feature.features.denseblock1.4.norm1.num_batches_tracked", "module.feature.features.denseblock1.4.norm2.num_batches_tracked", "module.feature.features.denseblock1.5.norm1.num_batches_tracked", "module.feature.features.denseblock1.5.norm2.num_batches_tracked", "module.feature.features.transition1.0.num_batches_tracked", "module.feature.features.denseblock2.0.norm1.num_batches_tracked", "module.feature.features.denseblock2.0.norm2.num_batches_tracked", "module.feature.features.denseblock2.1.norm1.num_batches_tracked", "module.feature.features.denseblock2.1.norm2.num_batches_tracked", "module.feature.features.denseblock2.2.norm1.num_batches_tracked",...

What's meaning of 'prostate/uterus'? It means "prostate and uterus" or "prostate or uterus"?