search

CAMMA-public / rendezvous

A transformer-inspired neural network for surgical action triplet recognition from laparoscopic videos.
Other
24 stars 8 forks source link

HELP! A error when testing #13

Closed csEylLee closed 1 year ago

csEylLee commented 1 year ago

Test weight used: ./checkpoint/run_2/rendezvous_l8_cholectcholect50_k0_batchnorm_lowres.pth Traceback (most recent call last): File "/home/cv5/rendezvous_code/pytorch/run_update.py", line 464, in mAP_i = mAPi.compute_video_AP(ignore_null=set_chlg_eval) File "/home/cv5/anaconda3/envs/torch110/lib/python3.8/site-packages/ivtmetrics/recognition.py", line 189, in compute_video_AP classwise = average_precision_score(targets, predicts, average=None) File "/home/cv5/anaconda3/envs/torch110/lib/python3.8/site-packages/sklearn/metrics/_ranking.py", line 234, in average_precision_score return _average_binary_score( File "/home/cv5/anaconda3/envs/torch110/lib/python3.8/site-packages/sklearn/metrics/_base.py", line 72, in _average_binary_score raise ValueError("{0} format is not supported".format(y_type)) ValueError: multiclass-multioutput format is not supported

TheBlackCat22 commented 1 year ago

Are you using the CholecT50 dataloader ?

csEylLee commented 1 year ago

Are you using the CholecT50 dataloader ?

Yes. I've solved it now.