Julian de Wit comments

Results 68 comments of


                                            Julian de Wit

Getting confused about where to keep the dataset

I read somewhere that Kaggle closed off the dataset.

Where does the data in resource.rar come from?

It's in the blog under Preprocessing and creating a trainset

Training time for step_train_nodule_detector.py

Hello, That is much longer then what could be expected.. What is a K10 simulator ? Is that much slower than a "normal" card ?

Training time for step_train_nodule_detector.py

I was on Keras 1.X. So if someone has a pull request then I can add it.

Count back to absolute slice positions after segmenting nodules

Hello, You guys are right. percentage to pixels takes a 3d volumne and finds the xyz locations given the xyz percentages. And yes.. you need to take into account flipping...

test data

The data is removed from kaggle.. You can test on luna 16 challenge data

question about the batch size in step 2 detector

Hello, That was just a conveinience thing that I used to test on smaller trainsets while experimenting. ie. I made it / 20 to train on a smaller trainset. You...

question about the batch size in step 2 detector

Hello mileyan, where is that code ? As you put it you are right but I do not see that code. Note that I wrote my own data iterator so...

step2_train_nodule_detector.py ValueError: output of generator should be a tuple

I cannot run the debugger but do you have traindata in place ?

step2_train_nodule_detector.py ValueError: output of generator should be a tuple

Please try again.. It seems to work now. [https://retinopaty.blob.core.windows.net/ndsb3/trained_models.rar](https://retinopaty.blob.core.windows.net/ndsb3/trained_models.rar)