search

MIC-DKFZ / nnDetection

nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.
Apache License 2.0
553 stars 97 forks source link

[Question]Can you provide the best weight file #104

Open BelieferQAQ opened 2 years ago

BelieferQAQ commented 2 years ago

:question: Question

Hello, I'd like to see the performance of the best weight of the ribfrac dataset, the FROC and other indicators. Can you provide them? Thank you very much!

mibaumgartner commented 2 years ago

Hi, since nndetection does not use the best model checkpoint per default I don't have the results right now. Since I'm on vacation during this week I can not run the prediction. I can do so when I'm back.

Best, Michael

BelieferQAQ commented 2 years ago

Hi, since nndetection does not use the best model checkpoint per default I don't have the results right now. Since I'm on vacation during this week I can not run the prediction. I can do so when I'm back.

Best, Michael

Thank you very much. You mean nndet uses model_ Last.ckpt predicts the verification set and test set, right？