The settings of training parameters for red excavator

[0101zsj]

Hello!First of all,congratulations on such an amazing paper and thank you very much for making the code public.I have a question regarding the training parameters settings for the red excavator.I set use_alpha,use_feature and use_view parameters. sample_scale=45. I loaded the model you gave with the trained model and trained to 250000 iterations with a single 2080Ti GPU.But the results are not ideal, could you please share the training parameters of red excavator. Thanks you for your attention.

[cassiePython]

I also allow more layers to be optimized , but use a larger patch size (sample_scale=60).

[tmrnvcome]

i came to this state with 210,000 iterations. what parameters to modify to achieve the ideal results of a red excavator shown in your examples?

[tmrnvcome]

Hihi! @0101zsj How many hours did u take for 250,000 iterations? And what parameters did u use?

Hello!First of all,congratulations on such an amazing paper and thank you very much for making the code public.I have a question regarding the training parameters settings for the red excavator.I set use_alpha,use_feature and use_view parameters. sample_scale=45. I loaded the model you gave with the trained model and trained to 250000 iterations with a single 2080Ti GPU.But the results are not ideal, could you please share the training parameters of red excavator. Thanks you for your attention.

[yunchao-ding]

Hi, how did you train to achieve this result? Why can I only get the following picture from my training results?