brats17
brats17 copied to clipboard
taigw
Brain tumor segmentation for MICCAI 2017 BraTS challenge
Hi, Thank you for this code ! I am trying to reproduce this work for a vessel segmentation project without using nifty net command line and eager execution. The training...
Hello, thank you very much for your code. I am a beginner. I want to know what path does data_root represent if I put Brats training set into data_root? Is...
@taigw in the config file, data_shape= [19, 144, 144, 4], label_shape= [11, 144, 144, 1],why the label has different shape with the data, shouldn't the label shape=[19,144,144,1] ? Thanks for...
When I run "python train config/*", how do I judge wheather its overfitting or under-fitting?
In file `MSNet.py` while creating (or defining) the graph for the model, I noticed that in the function that creates a [residual block](https://github.com/taigw/brats17/blob/db069aae0c510bb66326441d84adf19f16aab782/util/MSNet.py#L407) the activation layer is being applied before...
Hi, In test.py, specifically, [here](https://github.com/taigw/brats17/blob/master/test.py#L327), I find that the variable `data_shape1ax` has been referenced, but if I am using the single network (i.e., `if(config_net1)` is True) for whole tumor (similarly...
Hello, senior fellow apprentice. I have heard a lot about you！ I changed the model structure on the basis of your model, and the training process was smooth. However, a...
I have tested your given models under the model17 directory on the validation data by submitting the segmentation results to the CBICA Image Processing Portal. However, I didn't get the...
Iterator is not present anymore. Fortunately, It seems it is not even used in the code. Might be possible to remove it and therefore gain compatibility with latest TF.
@taigw What is the use of flip in __get_one_batch function of data_loader.py? ``` if(flip): sub_data_moda = np.flip(sub_data_moda, -1) ``` I do see that its default value is set to False....
