weiyithu / pv-raft Goto Github PK

Dear all,
By loading the state_dict, the attached error is faced:

It seems that the pre-trained model uses another normalization than the original one.

Thanks in advance for your quick help

Hi, Wei. Thanks for sharing this inspiring work! When will the code be released?

thank you so much for sharing your awesome code

could you please explain how to save the flow file as .npy to visualize it as in visualize.py file

thank you in advance

Thank you very much for your code.
When I am training the dpvraft model, I will report an error when calculating the drop_loss. The dimension of the drop_conf is (2,8192), but the dimension of the drop_conf_gt is (1,16384). How can I solve this problem?

Hi, it is a great job!
Could you provide the visualization code that produces the following effect in your paper, Thank you!

Hi, thanks for your great work.
I successfully run test.py, using FT3D dataset and best_checkpoints.params model. But, I can't find the output of estimate-flow file or a folder like result/FT3D which mentioned in visual.py. How can i get these files? Do I need to save the est_flow which mentioned in test.py at 120 lines as a npy file ?

Thanks in advance for your help.

您好，我将est_flow保存后运行visual.py报错如下：
ValueError: operands could not be broadcast together with shapes (94608,) (32,3)
查看后发现某一pc1.npy和pc2.npy的维度均为（94608,3），但flow.npy的维度一直为（32,8192,3)，因此无法做运算。所以想请教您如何将est_flow顺利保存成与pc1.npy相同维度的npy文件呢？