Closed icemiliang closed 5 years ago
I have a trained model myself on half of the kitti data and got mae=0.36 and rmse=1.08. Exact same parameters as the repo but using my own training script with only depth supervision (no photometric stuff)
I have a trained model myself on half of the kitti data and got mae=0.36 and rmse=1.08. Exact same parameters as the repo but using my own training script with only depth supervision (no photometric stuff)
Thanks for the reply. I just found it could be because I mixed the self-supervised training model with the supervised training model. I'll do some more experiments. Closing the issue for now.
Hi @fangchangma Thanks for sharing the code. I evaluated the pretrained model provided in readme. The result is not as good as reported in the paper (rmse 1343 vs 814). It was a clean clone and I followed the data folder structure. I attached the command and the screenshot of the results. Please let me know if there is an error or if I missed something here. Thank you.
python main.py --evaluate pretrain/mode=sparse+photo.w1=0.1.w2=0.1.input=gd.resnet34.criterion=l2.lr=1e-05.bs=16.wd=0.pretrained=False.jitter=0.1.time=2019-02-26@07-50/model_best.pth.tar