lfz

Guided-Denoise/Exps/sample/model.py

config['output_feature'] is a deprecated configuration I'm not sure about your problem, please give more info?

load the pbb, nms it, and you can get the coordinate, see data_classifier

Yes, it is variable, but recently we found that the changing of shape may lead to unwanted changing of output. Please be careful about this

it is not a pure end-to-end model: the preprocessing is not end-to-end the detector must be trained at the first step the classifier used the crop info provided by detector,...

Hi, we have noticed this problem too. We are really sorry that the codes are not finalized yet. The reason is that the score on the leader board is the...

@shu-hai @hflyzju that's strange, because the test model has been confirmed by us and several other people, please provide more info? About the framework you use and please provide some...

@shu-hai @hflyzju @m-wei @mileyan Oh, I see, 0.61244 is the correct output of this model, what you see is the public leader board score, which is highly noisy. You should...

@m-wei to get the probability of every nodule, refer to the variable "out" in Casenet

that is cool, could you share the training script 2017年5月25日星期四，hflyzju 写道： > [image: default] > > i can get a score = 0.38992，the detect model is after myself training >...