first commit

configs/server/server_inference_config.yaml

@@ -0,0 +1,92 @@
+
+runner:
+  general:
+    seed: 1
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: w_gf_wo_lf_full_debug
+    root_dir: "experiments"
+    epoch: 1 # -1 stands for last epoch
+
+  test:
+    dataset_list:
+      - OmniObject3d_train
+
+  blender_script_path: ""
+  output_dir: ""
+  pipeline: nbv_reconstruction_global_pts_pipeline
+  
+dataset:
+  OmniObject3d_train:
+    root_dir: "/home/data/hofee/project/nbv_rec/data/nbv_rec_data_512_preproc_npy"
+    model_dir: "/home/data/hofee/project/nbv_rec/data/scaled_object_meshes" 
+    source: seq_nbv_reconstruction_dataset 
+    split_file: "/home/data/hofee/project/nbv_rec/data/OmniObject3d_train.txt" 
+    type: test
+    filter_degree: 75
+    ratio: 1
+    batch_size: 1
+    num_workers: 12
+    pts_num: 4096
+    load_from_preprocess: True
+
+pipeline:
+  nbv_reconstruction_local_pts_pipeline:
+    modules:
+      pts_encoder: pointnet_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
+    global_scanned_feat: False
+
+  nbv_reconstruction_global_pts_pipeline:
+    modules:
+      pts_encoder: pointnet_encoder
+      pose_seq_encoder: transformer_pose_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+
+
+    
+module:
+
+  pointnet_encoder:
+    in_dim: 3
+    out_dim: 1024
+    global_feat: True
+    feature_transform: False
+
+  transformer_seq_encoder:
+    pts_embed_dim: 1024
+    pose_embed_dim: 256
+    num_heads: 4
+    ffn_dim: 256
+    num_layers: 3
+    output_dim: 2048
+
+  transformer_pose_seq_encoder:
+    pose_embed_dim: 256
+    num_heads: 4
+    ffn_dim: 256
+    num_layers: 3
+    output_dim: 1024
+
+  gf_view_finder:
+    t_feat_dim: 128
+    pose_feat_dim: 256
+    main_feat_dim: 2048
+    regression_head: Rx_Ry_and_T
+    pose_mode: rot_matrix
+    per_point_feature: False
+    sample_mode: ode
+    sampling_steps: 500
+    sde_mode: ve
+
+  pose_encoder:
+    pose_dim: 9
+    out_dim: 256

configs/server/server_inference_server_config.yaml

@@ -0,0 +1,53 @@
+
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: train_ab_global_only
+    root_dir: "experiments"
+    epoch: -1 # -1 stands for last epoch
+
+  pipeline: nbv_reconstruction_pipeline
+  voxel_size: 0.003
+
+pipeline:
+  nbv_reconstruction_pipeline:
+    modules:
+      pts_encoder: pointnet_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+
+module:
+  pointnet_encoder:
+    in_dim: 3
+    out_dim: 1024
+    global_feat: True
+    feature_transform: False
+  transformer_seq_encoder:
+    embed_dim: 256
+    num_heads: 4
+    ffn_dim: 256
+    num_layers: 3
+    output_dim: 1024
+
+  gf_view_finder:
+    t_feat_dim: 128
+    pose_feat_dim: 256
+    main_feat_dim: 2048
+    regression_head: Rx_Ry_and_T
+    pose_mode: rot_matrix
+    per_point_feature: False
+    sample_mode: ode
+    sampling_steps: 500
+    sde_mode: ve
+  pose_encoder:
+    pose_dim: 9
+    out_dim: 256
+  pts_num_encoder:
+    out_dim: 64

configs/server/server_split_dataset_config.yaml

@@ -0,0 +1,22 @@
+
+runner:
+  general:
+    seed: 0
+    device: cpu
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: debug
+    root_dir: "experiments"
+  
+  split: # 
+    root_dir: "/data/hofee/data/packed_preprocessed_data"
+    type: "unseen_instance" # "unseen_category"
+    datasets:
+      OmniObject3d_train: 
+        path: "/data/hofee/data/OmniObject3d_train.txt"
+        ratio: 0.9
+
+      OmniObject3d_test: 
+        path: "/data/hofee/data/OmniObject3d_test.txt"
+        ratio: 0.1

configs/server/server_train_config.yaml

@@ -0,0 +1,167 @@
+
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "2"
+    parallel: False
+    
+  experiment:
+    name: newtrain_mlp
+    root_dir: "experiments"
+    use_checkpoint: False
+    epoch: -1 # -1 stands for last epoch
+    max_epochs: 5000
+    save_checkpoint_interval: 1
+    test_first: False  
+
+  train:
+    optimizer:
+      type: Adam
+      lr: 0.0001
+    losses:   
+      - mse_loss
+    dataset: OmniObject3d_train
+  test:
+    frequency: 3 # test frequency
+    dataset_list:
+      - OmniObject3d_test
+      - OmniObject3d_val
+
+  pipeline: nbv_reconstruction_pipeline_mlp
+  
+dataset:
+  OmniObject3d_train:
+    root_dir: "/data/hofee/data/new_full_data"
+    model_dir: "../data/scaled_object_meshes"
+    source: nbv_reconstruction_dataset
+    split_file: "/data/hofee/data/new_full_data_list/new_OmniObject3d_train.txt"
+    type: train
+    cache: True
+    ratio: 1
+    batch_size: 24
+    num_workers: 128
+    pts_num: 8192
+    load_from_preprocess: True
+
+  OmniObject3d_test:
+    root_dir: "/data/hofee/data/new_full_data"
+    model_dir: "../data/scaled_object_meshes"
+    source: nbv_reconstruction_dataset
+    split_file: "/data/hofee/data/new_full_data_list/new_OmniObject3d_test.txt"
+    type: test
+    cache: True
+    filter_degree: 75
+    eval_list:
+      - pose_diff
+    ratio: 1
+    batch_size: 32
+    num_workers: 12
+    pts_num: 8192
+    load_from_preprocess: True
+
+  OmniObject3d_val:
+    root_dir: "/data/hofee/data/new_full_data"
+    model_dir: "../data/scaled_object_meshes"
+    source: nbv_reconstruction_dataset
+    split_file: "/data/hofee/data/new_full_data_list/new_OmniObject3d_train.txt"
+    type: test
+    cache: True
+    filter_degree: 75
+    eval_list:
+      - pose_diff
+    ratio: 0.1
+    batch_size: 32
+    num_workers: 12
+    pts_num: 8192
+    load_from_preprocess: True
+
+
+pipeline:
+  nbv_reconstruction_pipeline_local:
+    modules:
+      pts_encoder: pointnet++_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+  nbv_reconstruction_pipeline_global:
+    modules:
+      pts_encoder: pointnet++_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+  nbv_reconstruction_pipeline_local_only:
+    modules:
+      pts_encoder: pointnet++_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+  nbv_reconstruction_pipeline_global_only:
+    modules:
+      pts_encoder: pointnet++_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+  nbv_reconstruction_pipeline_mlp:
+    modules:
+      pts_encoder: pointnet++_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: mlp_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+
+module:
+
+  pointnet_encoder:
+    in_dim: 3
+    out_dim: 1024
+    global_feat: True
+    feature_transform: False
+
+  pointnet++_encoder:
+    in_dim: 3
+
+  transformer_seq_encoder:
+    embed_dim: 1280
+    num_heads: 4
+    ffn_dim: 256
+    num_layers: 3
+    output_dim: 1024
+
+  gf_view_finder:
+    t_feat_dim: 128
+    pose_feat_dim: 256
+    main_feat_dim: 2048
+    regression_head: Rx_Ry_and_T
+    pose_mode: rot_matrix
+    per_point_feature: False
+    sample_mode: ode
+    sampling_steps: 500
+    sde_mode: ve
+
+  pose_encoder:
+    pose_dim: 9
+    out_dim: 256
+    
+
+  pts_num_encoder:
+    out_dim: 64
+
+
+loss_function:
+  gf_loss:
+  mse_loss:
+
+evaluation_method:
+  pose_diff:
+  coverage_rate_increase: 
+    renderer_path: "../blender/data_renderer.py"