josedolz / semidensenet Goto Github PK

Hi, I may misread or miss some details of the paper.
But from the network, the input spatial size is 272727, the output is 999. So how do you generate the segmentation results in original size?

Thanks!

Hi Jose,

I was wondering if it is possible for you to add the part of code on evaluation the segmentation results with MHD and ASD. It will be a great help for us to evaluate the result. Thanks!

Best,
Caelyn

Hi Jose,
Recently I tried to used a model trained with SemiDenseNet for transfer learning. However, I was wondering how to save weights when I trained a SemiDenseNet as .npy file you mentioned in the README file. I want to use those weights in transfer learning. Thanks!

Traceback (most recent call last):
File "./networkTraining.py", line 83, in
networkTraining(sys.argv[1:])
File "./networkTraining.py", line 78, in networkTraining
startTraining(networkModelName,configIniName)
File "/data/zhanghang/HyperDenseNet-master/src/HyperDenseNet/startTraining.py", line 141, in startTraining
applyPadding
File "/data/zhanghang/HyperDenseNet-master/src/HyperDenseNet/Modules/IO/sampling.py", line 80, in getSamplesSubepoch
imageType
File "/data/zhanghang/HyperDenseNet-master/src/HyperDenseNet/Modules/IO/loadData.py", line 88, in load_imagesSinglePatient
[imageData, paddingValues] = applyPadding(imageData, sampleSizes, receptiveField)
File "/data/zhanghang/HyperDenseNet-master/src/HyperDenseNet/Modules/IO/ImgOperations/imgOp.py", line 57, in applyPadding
extra_padding = np.maximum(0, np.asarray(sampleSizes,dtype="int16")-(inputImg_arr+left_padding+right_padding))
ValueError: operands could not be broadcast together with shapes (4,) (3,)

Hi Jose,

Recently I am running your method on MR segmentation task. I selected a small rectangle region as ROI to segment the target into it. The DICE is not bad but it seems like there's always some fragments (some tiny spots I consider) wrongly segmented, which is obviously not belonged to my target. Is that cause by the small receptive field problem or do you have any idea what is this about? Thanks.