search

juliandewit / kaggle_ndsb2017

Kaggle datascience bowl 2017
MIT License
624 stars 290 forks source link

I have some problems with the csv. #30

Open jy2lhz opened 7 years ago

jy2lhz commented 7 years ago

Hi, julian, thank you for your sharing. I am reading and running your code. I have some problems with the csv files in the resource folder. You had answered similar problems. You said that the luna16_falsepos_labels folder was automatically generated. Can you tell me how? thank you very much.

juliandewit commented 7 years ago

It should be in the resources.rar It is generated by training a on LUNA and predicting on luna. Nodules that were false positives were stored.

jy2lhz commented 7 years ago

thank you for you answer. After reading the codes, i have some more problems. 1.In the ndsb3_manual_labels,I find the label 'mal' in the csv files not used in the code but the label 'id' used. Do the label 'mal' and label 'id' represent the same meaning but their value are opposite?

2.And in the step1_preprocess_luna16.py, you give the label 'malscore' 1 for_annos_pos.csv but also give the label 'malscore' 1 for the _annos_excluded.csv. Why giving 1 for the _annos_excluded.csv?

3.In the step2_train_nodule_detector.py, what is the meaning of the "1" in the first parameter of the function get_net ? def get_net(input_shape=(CUBE_SIZE, CUBE_SIZE, CUBE_SIZE, 1), load_weight_path=None, features=False, mal=False) -> Model:

thank you very much.

severous commented 4 years ago

@jy2lhz Hi I also have the same question 2 .please tell me if you know what is "malsore" and why giving 1 for _annos_excluded.csv? Thanks for your reply