Difference between pretrained models

HarshayuGirase / Human-Path-Prediction

State-of-the-art methods for human trajectory forecasting. Contains code for papers published at ECCV 2020 and ICCV 2021.

MIT License

348 stars 81 forks source link

Difference between pretrained models #19

Closed os1a closed 3 years ago

os1a commented 3 years ago

Hi,

I am wondering if you can give some explanation about the different pretrained models on SDD. When running the test script on these models, I got different results (the best are for the first model PECNET_social_model1.pt)

Thanks in advance,

Best,

HarshayuGirase commented 3 years ago

Hi,

I believe there's no major difference aside from maybe a couple of hyperparameter changes such as LR or loss function coefficients. The difference is due to variance while training but the results should be within 1-2% of each other.

karttikeya commented 3 years ago

Hope this answers your questions. I'm closing this issue for now. Please feel free to open another issue for other questions, star the repo if you found it helpful and thanks for interest in our code.