search

juliandewit / kaggle_ndsb2017

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

imformation about malignancy #69

Open severous opened 4 years ago

severous commented 4 years ago

Hi juliandewit.After runing "step3_predict_nodules.py",I get nothing about malignancy.In my generated .csv file,there is only coord_x,coord_y,diameter,nodule_chance and diameter_mm.but I notice that These few lines of code in your model:

out_class = Convolution3D(1, 1, 1, 1, activation="sigmoid", name="out_class_last")(last64) out_class = Flatten(name="out_class")(out_class) out_malignancy = Convolution3D(1, 1, 1, 1, activation=None, name="out_malignancy_last")(last64) out_malignancy = Flatten(name="out_malignancy")(out_malignancy)

But I don't know if you output ‘’out_malignancy‘’ and use it as the feature of XGBOOST

I'm looking forword your reply

juliandewit commented 4 years ago

Hello.. This is a naming bug from my part. I used to use diameter_mm as a proxy for malignancy.. After that I found the malignancy labels. If I remember correctly "diameter_mm" is malignancy.