mirror of
https://github.com/facebookresearch/pytorch3d.git
synced 2025-08-02 03:42:50 +08:00
74754bbf17
Reviewed By: shapovalov Differential Revision: D40622304 fbshipit-source-id: 277515a55c46d9b8300058b439526539a7fe00a0
597 lines
17 KiB
YAML
597 lines
17 KiB
YAML
data_source_class_type: ImplicitronDataSource
|
|
model_factory_class_type: ImplicitronModelFactory
|
|
optimizer_factory_class_type: ImplicitronOptimizerFactory
|
|
training_loop_class_type: ImplicitronTrainingLoop
|
|
seed: 42
|
|
detect_anomaly: false
|
|
exp_dir: ./data/default_experiment/
|
|
hydra:
|
|
run:
|
|
dir: .
|
|
output_subdir: null
|
|
mode: RUN
|
|
data_source_ImplicitronDataSource_args:
|
|
dataset_map_provider_class_type: ???
|
|
data_loader_map_provider_class_type: SequenceDataLoaderMapProvider
|
|
dataset_map_provider_BlenderDatasetMapProvider_args:
|
|
base_dir: ???
|
|
object_name: ???
|
|
path_manager_factory_class_type: PathManagerFactory
|
|
n_known_frames_for_test: null
|
|
path_manager_factory_PathManagerFactory_args:
|
|
silence_logs: true
|
|
dataset_map_provider_JsonIndexDatasetMapProvider_args:
|
|
category: ???
|
|
task_str: singlesequence
|
|
dataset_root: ''
|
|
n_frames_per_sequence: -1
|
|
test_on_train: false
|
|
restrict_sequence_name: []
|
|
test_restrict_sequence_id: -1
|
|
assert_single_seq: false
|
|
only_test_set: false
|
|
dataset_class_type: JsonIndexDataset
|
|
path_manager_factory_class_type: PathManagerFactory
|
|
dataset_JsonIndexDataset_args:
|
|
limit_to: 0
|
|
limit_sequences_to: 0
|
|
exclude_sequence: []
|
|
limit_category_to: []
|
|
load_images: true
|
|
load_depths: true
|
|
load_depth_masks: true
|
|
load_masks: true
|
|
load_point_clouds: false
|
|
max_points: 0
|
|
mask_images: false
|
|
mask_depths: false
|
|
image_height: 800
|
|
image_width: 800
|
|
box_crop: true
|
|
box_crop_mask_thr: 0.4
|
|
box_crop_context: 0.3
|
|
remove_empty_masks: true
|
|
seed: 0
|
|
sort_frames: false
|
|
path_manager_factory_PathManagerFactory_args:
|
|
silence_logs: true
|
|
dataset_map_provider_JsonIndexDatasetMapProviderV2_args:
|
|
category: ???
|
|
subset_name: ???
|
|
dataset_root: ''
|
|
test_on_train: false
|
|
only_test_set: false
|
|
load_eval_batches: true
|
|
n_known_frames_for_test: 0
|
|
dataset_class_type: JsonIndexDataset
|
|
path_manager_factory_class_type: PathManagerFactory
|
|
dataset_JsonIndexDataset_args:
|
|
limit_to: 0
|
|
limit_sequences_to: 0
|
|
pick_sequence: []
|
|
exclude_sequence: []
|
|
limit_category_to: []
|
|
load_images: true
|
|
load_depths: true
|
|
load_depth_masks: true
|
|
load_masks: true
|
|
load_point_clouds: false
|
|
max_points: 0
|
|
mask_images: false
|
|
mask_depths: false
|
|
image_height: 800
|
|
image_width: 800
|
|
box_crop: true
|
|
box_crop_mask_thr: 0.4
|
|
box_crop_context: 0.3
|
|
remove_empty_masks: true
|
|
n_frames_per_sequence: -1
|
|
seed: 0
|
|
sort_frames: false
|
|
path_manager_factory_PathManagerFactory_args:
|
|
silence_logs: true
|
|
dataset_map_provider_LlffDatasetMapProvider_args:
|
|
base_dir: ???
|
|
object_name: ???
|
|
path_manager_factory_class_type: PathManagerFactory
|
|
n_known_frames_for_test: null
|
|
path_manager_factory_PathManagerFactory_args:
|
|
silence_logs: true
|
|
downscale_factor: 4
|
|
dataset_map_provider_RenderedMeshDatasetMapProvider_args:
|
|
num_views: 40
|
|
data_file: null
|
|
azimuth_range: 180.0
|
|
resolution: 128
|
|
use_point_light: true
|
|
path_manager_factory_class_type: PathManagerFactory
|
|
path_manager_factory_PathManagerFactory_args:
|
|
silence_logs: true
|
|
data_loader_map_provider_SequenceDataLoaderMapProvider_args:
|
|
batch_size: 1
|
|
num_workers: 0
|
|
dataset_length_train: 0
|
|
dataset_length_val: 0
|
|
dataset_length_test: 0
|
|
train_conditioning_type: SAME
|
|
val_conditioning_type: SAME
|
|
test_conditioning_type: KNOWN
|
|
images_per_seq_options: []
|
|
sample_consecutive_frames: false
|
|
consecutive_frames_max_gap: 0
|
|
consecutive_frames_max_gap_seconds: 0.1
|
|
data_loader_map_provider_SimpleDataLoaderMapProvider_args:
|
|
batch_size: 1
|
|
num_workers: 0
|
|
dataset_length_train: 0
|
|
dataset_length_val: 0
|
|
dataset_length_test: 0
|
|
model_factory_ImplicitronModelFactory_args:
|
|
resume: true
|
|
model_class_type: GenericModel
|
|
resume_epoch: -1
|
|
force_resume: false
|
|
model_GenericModel_args:
|
|
log_vars:
|
|
- loss_rgb_psnr_fg
|
|
- loss_rgb_psnr
|
|
- loss_rgb_mse
|
|
- loss_rgb_huber
|
|
- loss_depth_abs
|
|
- loss_depth_abs_fg
|
|
- loss_mask_neg_iou
|
|
- loss_mask_bce
|
|
- loss_mask_beta_prior
|
|
- loss_eikonal
|
|
- loss_density_tv
|
|
- loss_depth_neg_penalty
|
|
- loss_autodecoder_norm
|
|
- loss_prev_stage_rgb_mse
|
|
- loss_prev_stage_rgb_psnr_fg
|
|
- loss_prev_stage_rgb_psnr
|
|
- loss_prev_stage_mask_bce
|
|
- objective
|
|
- epoch
|
|
- sec/it
|
|
mask_images: true
|
|
mask_depths: true
|
|
render_image_width: 400
|
|
render_image_height: 400
|
|
mask_threshold: 0.5
|
|
output_rasterized_mc: false
|
|
bg_color:
|
|
- 0.0
|
|
- 0.0
|
|
- 0.0
|
|
num_passes: 1
|
|
chunk_size_grid: 4096
|
|
render_features_dimensions: 3
|
|
tqdm_trigger_threshold: 16
|
|
n_train_target_views: 1
|
|
sampling_mode_training: mask_sample
|
|
sampling_mode_evaluation: full_grid
|
|
global_encoder_class_type: null
|
|
raysampler_class_type: AdaptiveRaySampler
|
|
renderer_class_type: MultiPassEmissionAbsorptionRenderer
|
|
image_feature_extractor_class_type: null
|
|
view_pooler_enabled: false
|
|
implicit_function_class_type: NeuralRadianceFieldImplicitFunction
|
|
view_metrics_class_type: ViewMetrics
|
|
regularization_metrics_class_type: RegularizationMetrics
|
|
loss_weights:
|
|
loss_rgb_mse: 1.0
|
|
loss_prev_stage_rgb_mse: 1.0
|
|
loss_mask_bce: 0.0
|
|
loss_prev_stage_mask_bce: 0.0
|
|
global_encoder_HarmonicTimeEncoder_args:
|
|
n_harmonic_functions: 10
|
|
append_input: true
|
|
time_divisor: 1.0
|
|
global_encoder_SequenceAutodecoder_args:
|
|
autodecoder_args:
|
|
encoding_dim: 0
|
|
n_instances: 1
|
|
init_scale: 1.0
|
|
ignore_input: false
|
|
raysampler_AdaptiveRaySampler_args:
|
|
n_pts_per_ray_training: 64
|
|
n_pts_per_ray_evaluation: 64
|
|
n_rays_per_image_sampled_from_mask: 1024
|
|
n_rays_total_training: null
|
|
stratified_point_sampling_training: true
|
|
stratified_point_sampling_evaluation: false
|
|
scene_extent: 8.0
|
|
scene_center:
|
|
- 0.0
|
|
- 0.0
|
|
- 0.0
|
|
raysampler_NearFarRaySampler_args:
|
|
n_pts_per_ray_training: 64
|
|
n_pts_per_ray_evaluation: 64
|
|
n_rays_per_image_sampled_from_mask: 1024
|
|
n_rays_total_training: null
|
|
stratified_point_sampling_training: true
|
|
stratified_point_sampling_evaluation: false
|
|
min_depth: 0.1
|
|
max_depth: 8.0
|
|
renderer_LSTMRenderer_args:
|
|
num_raymarch_steps: 10
|
|
init_depth: 17.0
|
|
init_depth_noise_std: 0.0005
|
|
hidden_size: 16
|
|
n_feature_channels: 256
|
|
bg_color: null
|
|
verbose: false
|
|
renderer_MultiPassEmissionAbsorptionRenderer_args:
|
|
raymarcher_class_type: EmissionAbsorptionRaymarcher
|
|
n_pts_per_ray_fine_training: 64
|
|
n_pts_per_ray_fine_evaluation: 64
|
|
stratified_sampling_coarse_training: true
|
|
stratified_sampling_coarse_evaluation: false
|
|
append_coarse_samples_to_fine: true
|
|
density_noise_std_train: 0.0
|
|
return_weights: false
|
|
raymarcher_CumsumRaymarcher_args:
|
|
surface_thickness: 1
|
|
bg_color:
|
|
- 0.0
|
|
replicate_last_interval: False
|
|
background_opacity: 0.0
|
|
density_relu: true
|
|
blend_output: false
|
|
raymarcher_EmissionAbsorptionRaymarcher_args:
|
|
surface_thickness: 1
|
|
bg_color:
|
|
- 0.0
|
|
replicate_last_interval: False
|
|
background_opacity: 10000000000.0
|
|
density_relu: true
|
|
blend_output: false
|
|
renderer_SignedDistanceFunctionRenderer_args:
|
|
ray_normal_coloring_network_args:
|
|
feature_vector_size: 3
|
|
mode: idr
|
|
d_in: 9
|
|
d_out: 3
|
|
dims:
|
|
- 512
|
|
- 512
|
|
- 512
|
|
- 512
|
|
weight_norm: true
|
|
n_harmonic_functions_dir: 0
|
|
pooled_feature_dim: 0
|
|
bg_color:
|
|
- 0.0
|
|
soft_mask_alpha: 50.0
|
|
ray_tracer_args:
|
|
sdf_threshold: 5.0e-05
|
|
line_search_step: 0.5
|
|
line_step_iters: 1
|
|
sphere_tracing_iters: 10
|
|
n_steps: 100
|
|
n_secant_steps: 8
|
|
image_feature_extractor_ResNetFeatureExtractor_args:
|
|
name: resnet34
|
|
pretrained: true
|
|
stages:
|
|
- 1
|
|
- 2
|
|
- 3
|
|
- 4
|
|
normalize_image: true
|
|
image_rescale: 0.16
|
|
first_max_pool: true
|
|
proj_dim: 32
|
|
l2_norm: true
|
|
add_masks: true
|
|
add_images: true
|
|
global_average_pool: false
|
|
feature_rescale: 1.0
|
|
view_pooler_args:
|
|
feature_aggregator_class_type: AngleWeightedReductionFeatureAggregator
|
|
view_sampler_args:
|
|
masked_sampling: false
|
|
sampling_mode: bilinear
|
|
feature_aggregator_AngleWeightedIdentityFeatureAggregator_args:
|
|
exclude_target_view: true
|
|
exclude_target_view_mask_features: true
|
|
concatenate_output: true
|
|
weight_by_ray_angle_gamma: 1.0
|
|
min_ray_angle_weight: 0.1
|
|
feature_aggregator_AngleWeightedReductionFeatureAggregator_args:
|
|
exclude_target_view: true
|
|
exclude_target_view_mask_features: true
|
|
concatenate_output: true
|
|
reduction_functions:
|
|
- AVG
|
|
- STD
|
|
weight_by_ray_angle_gamma: 1.0
|
|
min_ray_angle_weight: 0.1
|
|
feature_aggregator_IdentityFeatureAggregator_args:
|
|
exclude_target_view: true
|
|
exclude_target_view_mask_features: true
|
|
concatenate_output: true
|
|
feature_aggregator_ReductionFeatureAggregator_args:
|
|
exclude_target_view: true
|
|
exclude_target_view_mask_features: true
|
|
concatenate_output: true
|
|
reduction_functions:
|
|
- AVG
|
|
- STD
|
|
implicit_function_IdrFeatureField_args:
|
|
d_in: 3
|
|
d_out: 1
|
|
dims:
|
|
- 512
|
|
- 512
|
|
- 512
|
|
- 512
|
|
- 512
|
|
- 512
|
|
- 512
|
|
- 512
|
|
geometric_init: true
|
|
bias: 1.0
|
|
skip_in: []
|
|
weight_norm: true
|
|
n_harmonic_functions_xyz: 0
|
|
pooled_feature_dim: 0
|
|
implicit_function_NeRFormerImplicitFunction_args:
|
|
n_harmonic_functions_xyz: 10
|
|
n_harmonic_functions_dir: 4
|
|
n_hidden_neurons_dir: 128
|
|
input_xyz: true
|
|
xyz_ray_dir_in_camera_coords: false
|
|
transformer_dim_down_factor: 2.0
|
|
n_hidden_neurons_xyz: 80
|
|
n_layers_xyz: 2
|
|
append_xyz:
|
|
- 1
|
|
implicit_function_NeuralRadianceFieldImplicitFunction_args:
|
|
n_harmonic_functions_xyz: 10
|
|
n_harmonic_functions_dir: 4
|
|
n_hidden_neurons_dir: 128
|
|
input_xyz: true
|
|
xyz_ray_dir_in_camera_coords: false
|
|
transformer_dim_down_factor: 1.0
|
|
n_hidden_neurons_xyz: 256
|
|
n_layers_xyz: 8
|
|
append_xyz:
|
|
- 5
|
|
implicit_function_SRNHyperNetImplicitFunction_args:
|
|
hypernet_args:
|
|
n_harmonic_functions: 3
|
|
n_hidden_units: 256
|
|
n_layers: 2
|
|
n_hidden_units_hypernet: 256
|
|
n_layers_hypernet: 1
|
|
in_features: 3
|
|
out_features: 256
|
|
xyz_in_camera_coords: false
|
|
pixel_generator_args:
|
|
n_harmonic_functions: 4
|
|
n_hidden_units: 256
|
|
n_hidden_units_color: 128
|
|
n_layers: 2
|
|
in_features: 256
|
|
out_features: 3
|
|
ray_dir_in_camera_coords: false
|
|
implicit_function_SRNImplicitFunction_args:
|
|
raymarch_function_args:
|
|
n_harmonic_functions: 3
|
|
n_hidden_units: 256
|
|
n_layers: 2
|
|
in_features: 3
|
|
out_features: 256
|
|
xyz_in_camera_coords: false
|
|
raymarch_function: null
|
|
pixel_generator_args:
|
|
n_harmonic_functions: 4
|
|
n_hidden_units: 256
|
|
n_hidden_units_color: 128
|
|
n_layers: 2
|
|
in_features: 256
|
|
out_features: 3
|
|
ray_dir_in_camera_coords: false
|
|
implicit_function_VoxelGridImplicitFunction_args:
|
|
harmonic_embedder_xyz_density_args:
|
|
n_harmonic_functions: 6
|
|
omega_0: 1.0
|
|
logspace: true
|
|
append_input: true
|
|
harmonic_embedder_xyz_color_args:
|
|
n_harmonic_functions: 6
|
|
omega_0: 1.0
|
|
logspace: true
|
|
append_input: true
|
|
harmonic_embedder_dir_color_args:
|
|
n_harmonic_functions: 6
|
|
omega_0: 1.0
|
|
logspace: true
|
|
append_input: true
|
|
decoder_density_class_type: MLPDecoder
|
|
decoder_color_class_type: MLPDecoder
|
|
use_multiple_streams: true
|
|
xyz_ray_dir_in_camera_coords: false
|
|
scaffold_calculating_epochs: []
|
|
scaffold_resolution:
|
|
- 128
|
|
- 128
|
|
- 128
|
|
scaffold_empty_space_threshold: 0.001
|
|
scaffold_occupancy_chunk_size: 'inf'
|
|
scaffold_max_pool_kernel_size: 3
|
|
scaffold_filter_points: true
|
|
volume_cropping_epochs: []
|
|
voxel_grid_density_args:
|
|
voxel_grid_class_type: FullResolutionVoxelGrid
|
|
extents:
|
|
- 2.0
|
|
- 2.0
|
|
- 2.0
|
|
translation:
|
|
- 0.0
|
|
- 0.0
|
|
- 0.0
|
|
init_std: 0.1
|
|
init_mean: 0.0
|
|
hold_voxel_grid_as_parameters: true
|
|
param_groups: {}
|
|
voxel_grid_CPFactorizedVoxelGrid_args:
|
|
align_corners: true
|
|
padding: zeros
|
|
mode: bilinear
|
|
n_features: 1
|
|
resolution_changes:
|
|
0:
|
|
- 128
|
|
- 128
|
|
- 128
|
|
n_components: 24
|
|
basis_matrix: true
|
|
voxel_grid_FullResolutionVoxelGrid_args:
|
|
align_corners: true
|
|
padding: zeros
|
|
mode: bilinear
|
|
n_features: 1
|
|
resolution_changes:
|
|
0:
|
|
- 128
|
|
- 128
|
|
- 128
|
|
voxel_grid_VMFactorizedVoxelGrid_args:
|
|
align_corners: true
|
|
padding: zeros
|
|
mode: bilinear
|
|
n_features: 1
|
|
resolution_changes:
|
|
0:
|
|
- 128
|
|
- 128
|
|
- 128
|
|
n_components: null
|
|
distribution_of_components: null
|
|
basis_matrix: true
|
|
voxel_grid_color_args:
|
|
voxel_grid_class_type: FullResolutionVoxelGrid
|
|
extents:
|
|
- 2.0
|
|
- 2.0
|
|
- 2.0
|
|
translation:
|
|
- 0.0
|
|
- 0.0
|
|
- 0.0
|
|
init_std: 0.1
|
|
init_mean: 0.0
|
|
hold_voxel_grid_as_parameters: true
|
|
param_groups: {}
|
|
voxel_grid_CPFactorizedVoxelGrid_args:
|
|
align_corners: true
|
|
padding: zeros
|
|
mode: bilinear
|
|
n_features: 1
|
|
resolution_changes:
|
|
0:
|
|
- 128
|
|
- 128
|
|
- 128
|
|
n_components: 24
|
|
basis_matrix: true
|
|
voxel_grid_FullResolutionVoxelGrid_args:
|
|
align_corners: true
|
|
padding: zeros
|
|
mode: bilinear
|
|
n_features: 1
|
|
resolution_changes:
|
|
0:
|
|
- 128
|
|
- 128
|
|
- 128
|
|
voxel_grid_VMFactorizedVoxelGrid_args:
|
|
align_corners: true
|
|
padding: zeros
|
|
mode: bilinear
|
|
n_features: 1
|
|
resolution_changes:
|
|
0:
|
|
- 128
|
|
- 128
|
|
- 128
|
|
n_components: null
|
|
distribution_of_components: null
|
|
basis_matrix: true
|
|
decoder_density_ElementwiseDecoder_args:
|
|
scale: 1.0
|
|
shift: 0.0
|
|
operation: IDENTITY
|
|
decoder_density_MLPDecoder_args:
|
|
param_groups: {}
|
|
network_args:
|
|
n_layers: 8
|
|
output_dim: 256
|
|
skip_dim: 39
|
|
hidden_dim: 256
|
|
input_skips:
|
|
- 5
|
|
skip_affine_trans: false
|
|
last_layer_bias_init: null
|
|
last_activation: RELU
|
|
use_xavier_init: true
|
|
decoder_color_ElementwiseDecoder_args:
|
|
scale: 1.0
|
|
shift: 0.0
|
|
operation: IDENTITY
|
|
decoder_color_MLPDecoder_args:
|
|
param_groups: {}
|
|
network_args:
|
|
n_layers: 8
|
|
output_dim: 256
|
|
skip_dim: 39
|
|
hidden_dim: 256
|
|
input_skips:
|
|
- 5
|
|
skip_affine_trans: false
|
|
last_layer_bias_init: null
|
|
last_activation: RELU
|
|
use_xavier_init: true
|
|
view_metrics_ViewMetrics_args: {}
|
|
regularization_metrics_RegularizationMetrics_args: {}
|
|
optimizer_factory_ImplicitronOptimizerFactory_args:
|
|
betas:
|
|
- 0.9
|
|
- 0.999
|
|
breed: Adam
|
|
exponential_lr_step_size: 250
|
|
gamma: 0.1
|
|
lr: 0.0005
|
|
lr_policy: MultiStepLR
|
|
momentum: 0.9
|
|
multistep_lr_milestones: []
|
|
weight_decay: 0.0
|
|
linear_exponential_lr_milestone: 200
|
|
linear_exponential_start_gamma: 0.1
|
|
foreach: true
|
|
group_learning_rates: {}
|
|
training_loop_ImplicitronTrainingLoop_args:
|
|
evaluator_class_type: ImplicitronEvaluator
|
|
evaluator_ImplicitronEvaluator_args:
|
|
is_multisequence: false
|
|
camera_difficulty_bin_breaks:
|
|
- 0.97
|
|
- 0.98
|
|
eval_only: false
|
|
max_epochs: 1000
|
|
store_checkpoints: true
|
|
store_checkpoints_purge: 1
|
|
test_interval: -1
|
|
test_when_finished: false
|
|
validation_interval: 1
|
|
clip_grad: 0.0
|
|
metric_print_interval: 5
|
|
visualize_interval: 1000
|
|
visdom_env: ''
|
|
visdom_port: 8097
|
|
visdom_server: http://127.0.0.1
|