search

brandleyzhou / DIFFNet

[BMVC 2021] ''Self-Supervised Monocular Depth Estimation with Internal Feature Fusion''
111 stars 21 forks source link

Saved trained models #18

Closed MohsenMoradiArt closed 2 years ago

MohsenMoradiArt commented 2 years ago

Hi, Thank you for sharing your amazing code. I run the training code and it was trained for 20 epochs but I don't know where the models are saved? also your code save each epoch results separately or only save the last epoch? and the last question, where can I change the number of epochs for training?

brandleyzhou commented 2 years ago

You can change training configs in options.py.(e.g. save path, training epoch.). And a model is saved per epoch.

MohsenMoradiArt commented 2 years ago

You can change training configs in options.py.(e.g. save path, training epoch.). And a model is saved per epoch.

Thank you for your prompt response. However, I cannot find any single epoch saved on my pc. If I don't have a folder (by default is "mdp") and also in the "start2train.sh" file the model name is set to "mono_model", then the code is not creating a folder automatically to save the epochs?

MohsenMoradiArt commented 2 years ago

You can change training configs in options.py.(e.g. save path, training epoch.). And a model is saved per epoch.

Thank you for your prompt response. However, I cannot find any single epoch saved on my pc. If I don't have a folder (by default is "mdp") and also in the "start2train.sh" file the model name is set to "mono_model", then the code is not creating a folder automatically to save the epochs?

brandleyzhou commented 2 years ago

you can print the save path by adding 'print(save_path)' after line 596 in trainer.py. and see the save_model function for details

MohsenMoradiArt commented 2 years ago

Thank you so much, it was saving in a different drive, I found them.