Reed.Z

When the data is preprocessed, the images containing the occluded and incomplete tracking objects are removed, yes? How does this affect the training effect?

Ask for dataset

5

Well, I can't download the datasets. How can I get?

Why is the hyper-parameter, 'opt.prior_bias' set to -4.6?

Fail to load pth model files

15

I have encountered a problem： Traceback (most recent call last): File "demo.py", line 5, in dex.eval() File "/home/zyd/Reed/DL/age-estimation/code/pytorch-DEX/dex/api.py", line 23, in _eval gender_model.load_state_dict(torch.load(gender_model_path)) File "/home/zyd/anaconda3/envs/pytorch/lib/python3.5/site-packages/torch/serialization.py", line 367, in load return...

How can I train the network using my own datasets?

6

I used your model file, but got an error of about 8-10 years old. I want to re-use the data set for training. What should I do?

I have recently read your NIPS18 paper, MetaReg: Towards Domain Generalization using Meta-Regularization. Could you kindly share me the source code of your paper?

About the performance

5

Sorry for the inconvenience。 I trained and tested on the PACS dataset. The accuracy of the model trained by myself was 58%, and the accuracy of your trained model was...

Thank you for your useful code I am confused about how to get the `partern_3x3.png`? Does it differ among different depth cameras, like Kinect, intel D435?