Train Configs for BLEFF #34

Activity

1. ziruiw-dev commented on Jan 6, 2023

   

   ziruiw-dev

   on Jan 6, 2023

   Collaborator

   More actions

   Sorry about the delay. I have to dig into our old logs. We use this config for most BLEFF experiments:

   alias='',
   dir_enc_inc_in=True, 
   dir_enc_levels=4, 
   epoch=10000, 
   eval_cam_interval=5, 
   eval_img_interval=100, 
   eval_img_num=1, 
   eval_skip=1,
   focal_lr=0.001, 
   focal_lr_gamma=0.9, 
   focal_milestones=range(0, 10000, 100), 
   focal_order=2, 
   fx_only=True, 
   gpu_id=0, 
   hidden_dims=128, 
   learn_R=True, 
   learn_focal=True, 
   learn_t=True, 
   multi_gpu=False, 
   num_relu_epoch=0, 
   num_rows_eval_img=10, 
   num_sample=128, 
   optimizer='Adam', 
   pos_enc_inc_in=True, 
   pos_enc_levels=10, 
   pose_lr=0.001, 
   pose_lr_gamma=0.9, 
   pose_milestones=range(0, 10000, 100), 
   rand_seed=17, 
   res_dims=512, 
   resize_ratio=2, 
   scene_name='mix_rt/t005r005/bed1', 
   sigmoid_density=False, 
   start_refine_focal_epoch=-1, 
   start_refine_pose_epoch=-1, 
   static_lr=0.001, 
   static_lr_gamma=0.9954, 
   static_milestones=range(0, 10000, 10),
   store_pose_history=True, 
   train_img_num=-1, 
   train_rand_cols=32, 
   train_rand_rows=32, 
   train_skip=1, 
   true_rand=False, 
   use_dir_enc=True, 
   use_ndc=True, 
   white_bkgd=False, 
   
2. ziruiw-dev

   closed this as completedon Jan 6, 2023
3. HannahHaensen commented on Jan 9, 2023

   

   HannahHaensen

   on Jan 9, 2023

   Author

   More actions

   Thanks! @ziruiw-dev
   another question is the refine_nerfmm file always used after training?
4. ziruiw-dev commented on Jan 11, 2023

   

   ziruiw-dev

   on Jan 11, 2023

   Last edited by ziruiw-dev

   Collaborator

   More actions

   @HannahHaensen nope