search

alexklwong / unsupervised-depth-completion-visual-inertial-odometry

Tensorflow and PyTorch implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)
Other
192 stars 24 forks source link

About FLOPS #7

Closed Thermaloo closed 1 year ago

Thermaloo commented 1 year ago

Hello, Alex. Thank you for your excellent work. Could you tell me how much FLOPS is required?

Thermaloo commented 1 year ago

Hi, This is the evaluation result obtained by using the void_1500 pretrained model: Evaluation results: MAE RMSE iMAE iRMSE 75.782 142.760 39.399 71.805 +/- +/- +/- +/- 45.686 87.255 34.138 69.372 Is it a reasonable result?

alexklwong commented 1 year ago

Hi,

Unfortunately, we don't have numbers for flops.

The evaluation results are correct.