Evaluate your training model

[szgy66]

Thank you for your great work! According to your guidance, I have completed the training the brandenburg data. I follow your orders: python prepare_phototourism.py --root_dir ./**/**/brandenburg_gate/ --img_downscale 8 and python train.py --root_dir /home/ubuntu/data/IMC-PT/brandenburg_gate/ --dataset_name phototourism --img_downscale 8 --use_cache --N_importance 64 --N_samples 64 --encode_a --encode_t --beta_min 0.03 --N_vocab 1500 --N_emb_xyz 15 --num_epochs 20 --batch_size 1024 --optimizer adam --lr 5e-4 --lr_scheduler cosine --exp_name brandenburg_scale8_nerfw. I successfully completed the training and saved 20 relevant .ckpt files. When I run the instruction test training model: python eval.py --root_dir ./**/**/brandenburg_gate/ --dataset_name phototourism --scene_name brandenburg_test --split test --N_samples 256 --N_importance 256 --N_vocab 1500 --encode_a --encode_t --ckpt_pat ./**/**/ckpts/brandenburg_scale8_nerfw/epoch=19.ckpt --chunk 16384 --img_wh 320 240 . There is a error: This error also occurs in testing the scale8_epoch.19.ckpt model you provided. But when I tested the scale2_epoch.29.ckpt you supplied, it worked fine. I don't understand why this is happening, can you help me? Thanks!

[Linya-Peng]

Hi! I‘m facing the same issue. May I know how you fix it? Thanks!