search

bingykang / Fewshot_Detection

Few-shot Object Detection via Feature Reweighting
https://arxiv.org/abs/1812.01866
530 stars 112 forks source link

Dimension problem in test() #16

Open m10507323 opened 4 years ago

m10507323 commented 4 years ago

Hi, thanks for your sharing, Because I want to evaluate training results each epoch, so I uncomment test(epoch) in the train_meta.py. But I got the error like this. 1233 And I found the shape of output from model(data, metax, mask).data is (480,30,13,13) and the shape for target is (32,15,250) , so the index error happened. (I changed batch_size to 32) Do you know how to solve this error? Thanks

infrontofme commented 4 years ago

@m10507323 I met the same problem, have you solved it ?

infrontofme commented 4 years ago

target = target.view(-1, target.size(2)) solves the problem, but the test results are extremely worse.

wangyanfu123 commented 4 years ago

I have the the same problem: test results are extremely worse,have you solved it ? @infrontofme