search

Xt-Chen / SARPN

Structure-Aware Residual Pyramid Network for Monocular Depth Estimation IJCAI 2019
86 stars 15 forks source link

About Reproducible results #9

Closed cvgogogo closed 4 years ago

cvgogogo commented 4 years ago

Hi Xt-Chen,

Thanks for your nice work. I find it interesting, so I cloned the code and re-trained on my PC without any changes except the dataset path. However, I tried several times, the results varies a lot. Take the ABS metric as an example, the results were 0.2%-0.4% worse than the reported results in your paper. I checked the code and could not find any operations to fix the rand seeds. I thought this might be the main potential issue that I could not reproduce the result. As above, Would you please help me to cross the problem and I wonder if you tried many times and chosen the best one? or you just trained one time?

Thanks again.

Cheers, cvgogogo

Xt-Chen commented 4 years ago

Hi, Since the parameters in the adff and rpd modules in the network are initialized randomly, the results of each training may be slightly different. During the training process, I also used the early stopping to avoid overfitting. Hope it helps you

cvgogogo commented 4 years ago

Hi, Since the parameters in the adff and rpd modules in the network are initialized randomly, the results of each training may be slightly different. During the training process, I also used the early stopping to avoid overfitting. Hope it helps you Thank you for your reply.