Failed to train self dataset with nerf_w

[ucbq466]

Thanks for your repo! There comes an issue when I train my own dataset with nerf_w. It seems like the torch has something wrong, but I don't have an idea about why, could you help me with that? Many thanks!

python train.py --root_dir F:\NeRF\cenotaph --dataset_name phototourism --img_downscale 8 --use_cache --N_importance 64 --N_samples 64 --encode_a --encode_t --beta_min 0.03 --N_vocab 150 --N_emb_xyz 15 --num_epochs 20 --batch_size 1024 --optimizer adam --lr 5e-4 --lr_scheduler cosine --exp_name cenotaph_scale8_nerfw

Traceback (most recent call last): File "train.py", line 215, in main(hparams) File "train.py", line 184, in main system = NeRFSystem(hparams) File "train.py", line 31, in init self.hparams = hparams File "F:\NeRF\Anaconda3\envs\nerf_pl\lib\site-packages\torch\nn\modules\module.py", line 1225, in setattr object.setattr(self, name, value) AttributeError: can't set attribute

[JNH-LD]

self.save_hyperparameters(hparams)

[szgy66]

Thanks for your repo! There comes an issue when I train my own dataset with nerf_w. It seems like the torch has something wrong, but I don't have an idea about why, could you help me with that? Many thanks!

python train.py --root_dir F:\NeRF\cenotaph --dataset_name phototourism --img_downscale 8 --use_cache --N_importance 64 --N_samples 64 --encode_a --encode_t --beta_min 0.03 --N_vocab 150 --N_emb_xyz 15 --num_epochs 20 --batch_size 1024 --optimizer adam --lr 5e-4 --lr_scheduler cosine --exp_name cenotaph_scale8_nerfw

Traceback (most recent call last): File "train.py", line 215, in main(hparams) File "train.py", line 184, in main system = NeRFSystem(hparams) File "train.py", line 31, in init self.hparams = hparams File "F:\NeRF\Anaconda3\envs\nerf_pl\lib\site-packages\torch\nn\modules\module.py", line 1225, in setattr object.setattr(self, name, value) AttributeError: can't set attribute

Hello, I also plan to use Nerf_w to train my own data set recently, but I don't know how to prepare my data, any suggestions please? thank you!

[jinhyunk]

I have same issue with you. I'm still waiting for solutions..

[wtj-zhong]

I also have same issue with you. I'm still waiting for solutions..