search

ldkong1205 / RoboDepth

[NeurIPS 2023] RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
https://ldkong.com/RoboDepth
254 stars 31 forks source link

[Competition] ValueError: operands could not be broadcast together with shapes (17281,) (17281,640) #13

Closed xhqi0109 closed 1 year ago

xhqi0109 commented 1 year ago

Hello, my disp.npy shape is (500, 1, 192, 640): but after submitting it it is an error that ValueError: operands could not be broadcast together with shapes (17281,) (17281,640) , what is the reason?

ldkong1205 commented 1 year ago

Hi @xiaohua990109, as discussed in this issue, you can try squeezing your predictions into (500, 192, 640) before saving them into the .npy file.