Training model on REAL275 dataset

[PnthrLeo]

Recently, I have tried to reproduce results that was given in the DualPoseNet paper. Therefore, I used training_data_prepare.py script to generate necessary training data (for CAMERA25 and REAL275 datasets), which allowed me successfully reproduce results on CAMERA25 dataset.

However, results after training model on REAL275 were very far from the paper results. So, after that I began to wonder -- maybe, I do something wrong in case of training/evaluation on REAL275 dataset.

My pipeline of actions for REAL275 was:

1. Download NOCS data and run python training_data_prepare.py.
2. Run python main.py --phase train --dataset REAL275
3. Run python main.py --phase test --dataset REAL275

I did not save results of mine model evaluation on REAL275, but if you need it I can recalculate them for the issue investigation!

Thank you in advance!

[PnthrLeo]

Oh, I guess, I found where was the problem. Last time I trained model for REAL275 dataset without CAMERA25_*.pkl files. So this time I will try to put CAMERA25_*.pkl files with REAL275.pkl file together and run the training pipeline on REAL275 dataset again. I will write about my new results as soon as I calculate them!

[PnthrLeo]

In the end, seems like my last suggestion was correct (I achieved results close to the one shown in the original paper).

[Ysh1n3]

Hello, may I know what environment you are using to implement this code?

[Ysh1n3]

I am using the same environment as the author, but I cannot implement this error.

libcublas.so.9.0: cannot open shared object file: No such file or directory

I am using RTX 3060