search

ChiWeiHsiao / DeepVO-pytorch

PyTorch Implementation of DeepVO
358 stars 106 forks source link

Problem about performance #36

Open BrianWayland opened 3 years ago

BrianWayland commented 3 years ago

As is shown in the result, the performance of trained model is very unsatisfying. Actually, after 100 epochs valid loss and train loss is so close, simply improving number of epoch can do nothing to performance. My problem is are there any solutions to promote the performance of the model? route_03_gradient route_04_gradient route_05_gradient route_06_gradient route_07_gradient loss

knsjoon commented 3 years ago

@BrianWayland My valid loss is also very low but when I test them, I get very bad results as well. Have you solved this issue?

quanqhow commented 3 years ago

Hello, I also got the same bad result as shown below, so can anyone solve this problem? route_04 route_05 route_07 route_09 route_10

mariakalimeri commented 2 years ago

I was not even able to reproduce these results. I trained a model with the same data and the loss definition and hyperparameters in the current commit, which seem to be the ones used to train the for the provided model in the README, but my results after 250 epochs are way worst than this.