search

wentaozhu / DeepLung

WACV18 paper "DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification"
Apache License 2.0
312 stars 143 forks source link

some error about 'forcwrtdetpepchluna16.py' #99

Closed hengliang8 closed 4 years ago

hengliang8 commented 4 years ago

Traceback (most recent call last): File "/media/omnisky/1F4F46694A801839/zhl/DeepLung-master/evaluationScript/frocwrtdetpepchluna16.py", line 164, in getfroc(detp, eps) File "/media/omnisky/1F4F46694A801839/zhl/DeepLung-master/evaluationScript/frocwrtdetpepchluna16.py", line 153, in getfroc froclist = p.map(getfrocvalue, predannofnamalist) File "/home/omnisky/anaconda3/envs/zhl2/lib/python2.7/multiprocessing/pool.py", line 253, in map return self.map_async(func, iterable, chunksize).get() File "/home/omnisky/anaconda3/envs/zhl2/lib/python2.7/multiprocessing/pool.py", line 572, in get raise self._value ValueError: Data is not binary and pos_label is not specified ./annotations/annotations.csv

expecting your reply.

wentaozhu commented 4 years ago

Did you train your model?

In the readme, "After training and test are done, use the ./evaluationScript/frocwrtdetpepchluna16.py to validate the epoch used for test. After that, collect all the 10 folds' prediction, use ./evaluationScript/noduleCADEvaluationLUNA16.py to get the FROC for all 10 folds. You can directly run noduleCADEvaluationLUNA16.py, and get the performance in the paper."

hengliang8 commented 4 years ago

thanks for you help, I find the solution. I fill in the wrong path in 'result'.It should be the path of test result.

3learning12340 commented 4 years ago

@hengliang8 hello, I meet the same question, but I don't understand your meaning. test results? can you help me to explain it in detail? thank you very much

ljk1072911239 commented 4 years ago

thanks for you help, I find the solution. I fill in the wrong path in 'result'.It should be the path of test result.

How can you solve this issue? I encounter it. Thanks.