t_net.alpha_noise

[wtj-zhong]

wonderful job But when I run your code I encounter a problem KeyError: 't_net.alpha_noise' I want to know the reason of this problem? Is this parameter defined by myself? Here is my error: python train.py\ --dataset_name phototourism \ --config ./configs/phototourism.yaml Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off] /home/wtj/anaconda3/envs/sfnerf/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings. warn( /home/wtj/anaconda3/envs/sfnerf/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights. warnings. warn(msg) Loading model from: /home/wtj/anaconda3/envs/sfnerf/lib/python3.9/site-packages/lpips/weights/v0.1/alex.pth Traceback (most recent call last): File "/home/wtj/desktop/nerfw/SF-NeRF/train.py", line 69, in main(parse_args(parser)) File "/home/wtj/desktop/nerfw/SF-NeRF/train.py", line 33, in main system = NeRFSystem(hparams) File "/home/wtj/desktop/nerfw/SF-NeRF/models/nerf_system.py", line 73, in init alpha_noise=hparams['t_net.alpha_noise'], KeyError: 't_net.alpha_noise'

[2j1ejyu]

Thank you for your interest. It seems that the code is not the latest version. The parameter "t_net.alpha_noise" is not used in the latest version, thus it should be erased. I apologize for the confusion and I'll update the code later as soon as possible.

-----Original Message----- From: @.> To: @.>; Cc: @.***>; Sent: 2023. 6. 23. (금) 23:15 (GMT+09:00) Subject: [2j1ejyu/SF-NeRF] t_net.alpha_noise (Issue #1)

wonderful job But when I run your code I encounter a problem KeyError: 't_net.alpha_noise' I want to know the reason of this problem? Is this parameter defined by myself? Here is my error: python train.py --dataset_name phototourism --config ./configs/phototourism.yaml Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off] /home/wtj/anaconda3/envs/sfnerf/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings. warn( /home/wtj/anaconda3/envs/sfnerf/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights. warnings. warn(msg) Loading model from: /home/wtj/anaconda3/envs/sfnerf/lib/python3.9/site-packages/lpips/weights/v0.1/alex.pth Traceback (most recent call last): File "/home/wtj/desktop/nerfw/SF-NeRF/train.py", line 69, in main(parse_args(parser)) File "/home/wtj/desktop/nerfw/SF-NeRF/train.py", line 33, in main system = NeRFSystem(hparams) File "/home/wtj/desktop/nerfw/SF-NeRF/models/nerf_system.py", line 73, in init alpha_noise=hparams['t_net.alpha_noise'], KeyError: 't_net.alpha_noise' — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>

[wtj-zhong]

Thank you for your work. Wishing you academic progress and a happy mood

[3D-A]

Thank you for your wonderful job! could you share the pretrained checkpoint? Thank you very much