Tseng Kuan Lun

Can you try to use Python3 to see if the problem still persists ?

The basic idea is that you convert your data into 3d numpy array. For example, you can use whatever tool to convert .raw file into the format that python can...

The file name should be {BRATS_XX}/{BRATS_XX}_t1c.nii.gz ... The modality files should have caseID as prefix. Can you try to print "data" object at line 269 to see whether the object...

Hi, You need to change final classification layer output channel and the global variable (image w, h ,c) inside Inputs.py. But seems you can run the code, I think above...

Sorry, due to various reason I only have very limited time to maintain. You can train only one image to see that if the network can overfit (changing loss weight...

HI Have you checked the path in test.txt ? In the original test.txt, the path is configured to the SegNet author's environment. You need to change to your own path...

The problem seemed to be testing label not exist. Can you show me the content of text.txt ?

Hi, You may need to change the classification layer and as well as Inputs pipeline, changing everything with 11 class to 19 class. The current codebase is hard to extend...

Three changes should be made 1. you can use --image_h=64 --image_w=64 --num_class = 2 as command-line argument 2. change the global variable defined in Inputs.py 3. In the model file,...

Hi, Usually this is caused by empt queue(wrong data path). Have you checked the datatset path? which located in SegNet-Tutorial/CamVId/train.txt and SegNet-Tutorial/CamVid/val.txt. If you downloaded the data through original author's...