search

facebookresearch / robust-dynrf

An algorithm for reconstructing the radiance field of a dynamic scene from a casually-captured video.
MIT License
219 stars 11 forks source link

when training i met a problem #5

Open weiya-89 opened 1 year ago

weiya-89 commented 1 year ago

hi，nice work. when training i met a problem

Traceback (most recent call last): File "/home/vision/work/lzw/robust-dynrf-main/train.py", line 2675, in reconstruction(args) File "/home/vision/work/lzw/robust-dynrf-main/train.py", line 2447, in reconstruction ) = render( File "/home/vision/work/anaconda3/envs/RoDynRF/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/vision/work/lzw/robust-dynrf-main/renderer.py", line 488, in render scene_flow_f, scene_flow_b = tensorf.module.get_forward_backward_scene_flow( File "/home/vision/work/anaconda3/envs/RoDynRF/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1265, in getattr raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'TensorVMSplit_TimeEmbedding' object has no attribute 'module'

xiazhi1 commented 1 year ago

Same Bug for me,have you solved it?

weiya-89 commented 1 year ago

i delete the module in renderer.py in line 488 like this and it works, But I don't know if this will affect the results

scene_flow_f, scene_flow_b = tensorf.get_forward_backward_scene_flow( pts_ref, ts_chunk )

xiazhi1 commented 1 year ago

i delete the module in renderer.py in line 488 like this and it works, But I don't know if this will affect the results scene_flow_f, scene_flow_b = tensorf.get_forward_backward_scene_flow( pts_ref, ts_chunk )

Thanks a lot ! It works for me!

Gloryseven commented 1 year ago

i delete the module in renderer.py in line 488 like this and it works, But I don't know if this will affect the results scene_flow_f, scene_flow_b = tensorf.get_forward_backward_scene_flow( pts_ref, ts_chunk )

Do you mean to delete lines from 488 to 503?