BelieferQAQ

this function： def singletest(data,net,config,splitfun,combinefun,n_per_run,margin = 64,isfeat=False): z, h, w = data.size(2), data.size(3), data.size(4) print(data.size()) data = splitfun(data,config['max_stride'],margin) data = Variable(data.cuda(async = True), volatile = True,requires_grad=False) splitlist = range(0,args.split+1,n_per_run) outputlist =...

i use RibFrac Dataset,i have same issues, my qq 318831418

> Hi, Dear @mibaumgartner, > > Thanks a lot for your reply. I have tried the option suggested and I often got out sensible segmentations. However in some cases the...

Thank you very much for your answer. Hello, I'm doing the 5-type detection and classification of rib fracture of ribfrac. I have three questions to ask you for help: 1....

> Hi @BelieferQAQ , which repository did you try ? UNETR, Using the default values for hyper-parameters, the following command can be used to initiate training using PyTorch native AMP...

In addition, I train the model myself and get the weight model Pt, then use the following command: python test. py --infer_ overlap=0.5 --data_ dir=/data1/dataset/wdDATASET/BTCV/abdomen/ --pretrained_ dir='./ pretrained_ models/' --saved_...

> Hello! Thank you for your answer. There are five fracture types in the ribfrac dataset. With the background, it should be set to six types in the JSON file....

> > Dear @BelieferQAQ , > > the entire training on a RTX2080TI usually takes around 2 days. One epoch should take around 1-2 hours (depending on hardware while 2...

> The training time shouldn't increase over time, maybe there are some other factors influencing that as well (e.g. other users running jobs on the machine). Please check, the readme...

> > The best model is automatically saved in training directory. Please be aware that shortening the training on RibFrac will decrease results. Since it is the largest dataset in...