search

meyerls / FruitNeRF

[IROS24] Offical Code for "FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework" - Inegrated into Nerfstudio
https://meyerls.github.io/fruit_nerf
GNU General Public License v3.0
250 stars 32 forks source link

The 'ns process free data' command reported an error #6

Closed Double-zh closed 1 month ago

Double-zh commented 1 month ago

**What a great and interesting job!

I am running the command 'ns protocol free data -- data/home/data/images -- output dir/home/data/FruitNeRF/output/Out1-- data_demantic/home/data/FruitNeRF/output/Out2' ”At that time, there was an error saying 'Command not found'. Did I not successfully install the environment? May I ask how to solve this problem?**

__(nerfstudio) catas@catas:~/FruitNeRF$ ns-prepocess-fruit-data --data /home/catas/images --output-dir /home/catas/FruitNeRF/output/output1 --data_semantic /home/catas/FruitNeRF/output/output2**

ns-prepocess-fruit-data：Command not found

(nerfstudio) catas@catas:~/FruitNeRF$ ns-train -h /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_fields.py:330: UserWarning: The field pipeline is annotated with type <class 'nerfstudio.pipelines.base_pipeline.VanillaPipelineConfig'>, but the default value FruitPipelineConfig: _target: <class 'fruit_nerf.fruit_pipeline.FruitPipeline'> datamanager: FruitDataManagerConfig: _target: <class 'fruit_nerf.data.fruit_datamanager.FruitDataManager'> data: None camera_optimizer: CameraOptimizerConfig: _target: <class 'nerfstudio.cameras.camera_optimizers.CameraOptimizer'> mode: SO3xR3 position_noise_std: 0.0 orientation_noise_std: 0.0 optimizer: AdamOptimizerConfig: _target: <class 'torch.optim.adam.Adam'> lr: 0.0006 eps: 1e-08 max_norm: None weight_decay: 0.01 scheduler: ExponentialDecaySchedulerConfig: _target: <class 'nerfstudio.engine.schedulers.ExponentialDecayScheduler'> lr_pre_warmup: 1e-08 lr_final: 6e-06 warmup_steps: 0 max_steps: 200000 ramp: cosine param_group: camera_opt masks_on_gpu: None dataparser: FruitNerfDataParserConfig: _target: <class 'fruit_nerf.data.fruitnerf_dataparser.FruitNerf'> data: . scale_factor: 1.0 downscale_factor: None scene_scale: 1.0 orientation_method: up center_method: poses auto_scale_poses: True train_split_fraction: 0.9 train_num_rays_per_batch: 4096 train_num_images_to_sample_from: -1 train_num_times_to_repeat_images: -1 eval_num_rays_per_batch: 4096 eval_num_images_to_sample_from: -1 eval_num_times_to_repeat_images: -1 eval_image_indices: [0] collate_fn: <function nerfstudio_collate at 0x7f32b31afca0> camera_res_scale_factor: 1.0 patch_size: 1 model: FruitNerfModelConfig: _target: <class 'fruit_nerf.fruit_nerf.FruitModel'> enable_collider: True collider_params: {'near_plane': 2.0, 'far_plane': 6.0} loss_coefficients: {'rgb_loss_coarse': 1.0, 'rgb_loss_fine': 1.0} eval_num_rays_per_chunk: 32768 prompt: None near_plane: 0.05 far_plane: 1000.0 background_color: last_sample hidden_dim: 64 hidden_dim_color: 64 hidden_dim_transient: 64 num_levels: 16 base_res: 16 max_res: 2048 log2_hashmap_size: 19 features_per_level: 2 num_proposal_samples_per_ray: [256 96] num_nerf_samples_per_ray: 48 proposal_update_every: 5 proposal_warmup: 5000 num_proposal_iterations: 2 use_same_proposal_network: False proposal_net_args_list: [{'hidden_dim': 16, 'log2_hashmap_size': 17, 'num_levels': 5, 'max_res': 128, 'use_linear': False}, {'hidden_dim': 16, 'log2_hashmap_size': 17, 'num_levels': 5, 'max_res': 256, 'use_linear': False}] proposal_initial_sampler: piecewise interlevel_loss_mult: 1.0 distortion_loss_mult: 0.002 orientation_loss_mult: 0.0001 pred_normal_loss_mult: 0.001 use_proposal_weight_anneal: True use_average_appearance_embedding: True proposal_weights_anneal_slope: 10.0 proposal_weights_anneal_max_num_iters: 1000 use_single_jitter: True predict_normals: False disable_scene_contraction: False use_gradient_scaling: False implementation: tcnn appearance_embed_dim: 32 semantic_loss_weight: 1.0 pass_semantic_gradients: False num_layers_semantic: 2 hidden_dim_semantics: 64 geo_feat_dim: 15 has type <class 'fruit_nerf.fruit_pipeline.FruitPipelineConfig'>. We'll try to handle this gracefully, but it may cause unexpected behavior. warnings.warn( /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_fields.py:1066: UserWarning: Mutable type <class 'nerfstudio.data.datamanagers.base_datamanager.DataManagerConfig'> is used as a default value for datamanager. This is dangerous! Consider using dataclasses.field(default_factory=...) or marking <class 'nerfstudio.data.datamanagers.base_datamanager.DataManagerConfig'> as frozen. warnings.warn( /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_fields.py:1066: UserWarning: Mutable type <class 'nerfstudio.models.base_model.ModelConfig'> is used as a default value for model. This is dangerous! Consider using dataclasses.field(default_factory=...) or marking <class 'nerfstudio.models.base_model.ModelConfig'> as frozen. warnings.warn( /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_resolver.py:455: UserWarning: <class 'fruit_nerf.data.fruitnerf_dataparser.FruitNerfDataParserConfig'> does not match any type in Union: [<class 'nerfstudio.data.dataparsers.nerfstudio_dataparser.NerfstudioDataParserConfig'>, <class 'nerfstudio.data.dataparsers.minimal_dataparser.MinimalDataParserConfig'>, <class 'nerfstudio.data.dataparsers.arkitscenes_dataparser.ARKitScenesDataParserConfig'>, <class 'nerfstudio.data.dataparsers.blender_dataparser.BlenderDataParserConfig'>, <class 'nerfstudio.data.dataparsers.instant_ngp_dataparser.InstantNGPDataParserConfig'>, <class 'nerfstudio.data.dataparsers.nuscenes_dataparser.NuScenesDataParserConfig'>, <class 'nerfstudio.data.dataparsers.dnerf_dataparser.DNeRFDataParserConfig'>, <class 'nerfstudio.data.dataparsers.phototourism_dataparser.PhototourismDataParserConfig'>, <class 'nerfstudio.data.dataparsers.dycheck_dataparser.DycheckDataParserConfig'>, <class 'nerfstudio.data.dataparsers.scannet_dataparser.ScanNetDataParserConfig'>, <class 'nerfstudio.data.dataparsers.sdfstudio_dataparser.SDFStudioDataParserConfig'>, <class 'nerfstudio.data.dataparsers.nerfosr_dataparser.NeRFOSRDataParserConfig'>, <class 'nerfstudio.data.dataparsers.sitcoms3d_dataparser.Sitcoms3DDataParserConfig'>] warnings.warn( /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_fields.py:330: UserWarning: The field pipeline is annotated with type <class 'nerfstudio.pipelines.base_pipeline.VanillaPipelineConfig'>, but the default value FruitPipelineConfig: _target: <class 'fruit_nerf.fruit_pipeline.FruitPipeline'> datamanager: FruitDataManagerConfig: _target: <class 'fruit_nerf.data.fruit_datamanager.FruitDataManager'> data: None camera_optimizer: CameraOptimizerConfig: _target: <class 'nerfstudio.cameras.camera_optimizers.CameraOptimizer'> mode: SO3xR3 position_noise_std: 0.0 orientation_noise_std: 0.0 optimizer: RAdamOptimizerConfig: _target: <class 'torch.optim.radam.RAdam'> lr: 0.0006 eps: 1e-08 max_norm: None weight_decay: 0.001 scheduler: ExponentialDecaySchedulerConfig: _target: <class 'nerfstudio.engine.schedulers.ExponentialDecayScheduler'> lr_pre_warmup: 1e-08 lr_final: None warmup_steps: 0 max_steps: 10000 ramp: cosine param_group: camera_opt masks_on_gpu: None dataparser: FruitNerfDataParserConfig: _target: <class 'fruit_nerf.data.fruitnerf_dataparser.FruitNerf'> data: . scale_factor: 1.0 downscale_factor: None scene_scale: 1.0 orientation_method: up center_method: poses auto_scale_poses: True train_split_fraction: 0.9 train_num_rays_per_batch: 8192 train_num_images_to_sample_from: -1 train_num_times_to_repeat_images: -1 eval_num_rays_per_batch: 4096 eval_num_images_to_sample_from: -1 eval_num_times_to_repeat_images: -1 eval_image_indices: [0] collate_fn: <function nerfstudio_collate at 0x7f32b31afca0> camera_res_scale_factor: 1.0 patch_size: 1 model: FruitNerfModelConfig: _target: <class 'fruit_nerf.fruit_nerf.FruitModel'> enable_collider: True collider_params: {'near_plane': 2.0, 'far_plane': 6.0} loss_coefficients: {'rgb_loss_coarse': 1.0, 'rgb_loss_fine': 1.0} eval_num_rays_per_chunk: 32768 prompt: None near_plane: 0.05 far_plane: 1000.0 background_color: last_sample hidden_dim: 128 hidden_dim_color: 128 hidden_dim_transient: 64 num_levels: 16 base_res: 16 max_res: 4096 log2_hashmap_size: 21 features_per_level: 2 num_proposal_samples_per_ray: [512 256] num_nerf_samples_per_ray: 128 proposal_update_every: 5 proposal_warmup: 5000 num_proposal_iterations: 2 use_same_proposal_network: False proposal_net_args_list: [{'hidden_dim': 16, 'log2_hashmap_size': 17, 'num_levels': 5, 'max_res': 128, 'use_linear': False}, {'hidden_dim': 16, 'log2_hashmap_size': 17, 'num_levels': 5, 'max_res': 256, 'use_linear': False}] proposal_initial_sampler: piecewise interlevel_loss_mult: 1.0 distortion_loss_mult: 0.002 orientation_loss_mult: 0.0001 pred_normal_loss_mult: 0.001 use_proposal_weight_anneal: True use_average_appearance_embedding: True proposal_weights_anneal_slope: 10.0 proposal_weights_anneal_max_num_iters: 5000 use_single_jitter: True predict_normals: False disable_scene_contraction: False use_gradient_scaling: False implementation: tcnn appearance_embed_dim: 128 semantic_loss_weight: 1.0 pass_semantic_gradients: False num_layers_semantic: 3 hidden_dim_semantics: 128 geo_feat_dim: 30 has type <class 'fruit_nerf.fruit_pipeline.FruitPipelineConfig'>. We'll try to handle this gracefully, but it may cause unexpected behavior. warnings.warn( /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_fields.py:330: UserWarning: The field pipeline is annotated with type <class 'nerfstudio.pipelines.base_pipeline.VanillaPipelineConfig'>, but the default value FruitPipelineConfig: _target: <class 'fruit_nerf.fruit_pipeline.FruitPipeline'> datamanager: FruitDataManagerConfig: _target: <class 'fruit_nerf.data.fruit_datamanager.FruitDataManager'> data: None camera_optimizer: CameraOptimizerConfig: _target: <class 'nerfstudio.cameras.camera_optimizers.CameraOptimizer'> mode: SO3xR3 position_noise_std: 0.0 orientation_noise_std: 0.0 optimizer: RAdamOptimizerConfig: _target: <class 'torch.optim.radam.RAdam'> lr: 0.0006 eps: 1e-08 max_norm: None weight_decay: 0.001 scheduler: ExponentialDecaySchedulerConfig: _target: <class 'nerfstudio.engine.schedulers.ExponentialDecayScheduler'> lr_pre_warmup: 1e-08 lr_final: 6e-05 warmup_steps: 0 max_steps: 50000 ramp: cosine param_group: camera_opt masks_on_gpu: None dataparser: FruitNerfDataParserConfig: _target: <class 'fruit_nerf.data.fruitnerf_dataparser.FruitNerf'> data: . scale_factor: 1.0 downscale_factor: None scene_scale: 1.0 orientation_method: up center_method: poses auto_scale_poses: True train_split_fraction: 0.9 train_num_rays_per_batch: 16384 train_num_images_to_sample_from: -1 train_num_times_to_repeat_images: -1 eval_num_rays_per_batch: 4096 eval_num_images_to_sample_from: -1 eval_num_times_to_repeat_images: -1 eval_image_indices: [0] collate_fn: <function nerfstudio_collate at 0x7f32b31afca0> camera_res_scale_factor: 1.0 patch_size: 1 model: FruitNerfModelConfig: _target: <class 'fruit_nerf.fruit_nerf.FruitModel'> enable_collider: True collider_params: {'near_plane': 2.0, 'far_plane': 6.0} loss_coefficients: {'rgb_loss_coarse': 1.0, 'rgb_loss_fine': 1.0} eval_num_rays_per_chunk: 32768 prompt: None near_plane: 0.05 far_plane: 1000.0 background_color: last_sample hidden_dim: 256 hidden_dim_color: 256 hidden_dim_transient: 64 num_levels: 16 base_res: 16 max_res: 8192 log2_hashmap_size: 21 features_per_level: 2 num_proposal_samples_per_ray: [512 512] num_nerf_samples_per_ray: 64 proposal_update_every: 5 proposal_warmup: 5000 num_proposal_iterations: 2 use_same_proposal_network: False proposal_net_args_list: [{'hidden_dim': 16, 'log2_hashmap_size': 17, 'num_levels': 5, 'max_res': 512, 'use_linear': False}, {'hidden_dim': 16, 'log2_hashmap_size': 17, 'num_levels': 7, 'max_res': 2048, 'use_linear': False}] proposal_initial_sampler: piecewise interlevel_loss_mult: 1.0 distortion_loss_mult: 0.002 orientation_loss_mult: 0.0001 pred_normal_loss_mult: 0.001 use_proposal_weight_anneal: True use_average_appearance_embedding: True proposal_weights_anneal_slope: 10.0 proposal_weights_anneal_max_num_iters: 5000 use_single_jitter: True predict_normals: False disable_scene_contraction: False use_gradient_scaling: False implementation: tcnn appearance_embed_dim: 32 semantic_loss_weight: 1.0 pass_semantic_gradients: False num_layers_semantic: 3 hidden_dim_semantics: 128 geo_feat_dim: 30 has type <class 'fruit_nerf.fruit_pipeline.FruitPipelineConfig'>. We'll try to handle this gracefully, but it may cause unexpected behavior. warnings.warn( usage: ns-train [-h] {depth-nerfacto,dnerf,fruit_nerf,fruit_nerf_big,fruit_nerf_huge,generfacto,instant-ngp,instant-ngp-bounded,mipnerf,nerf acto,nerfacto-big,nerfacto-huge,neus,neus-facto,phototourism,semantic-nerfw,tensorf,vanilla-nerf,volinga,in2n,in2n-small,in2n-tiny,kpla nes,kplanes-dynamic,lerf,lerf-big,lerf-lite,nerfplayer-nerfacto,nerfplayer-ngp,tetra-nerf,tetra-nerf-original}

Train a radiance field with nerfstudio. For real captures, we recommend using the nerfacto model.

Nerfstudio allows for customizing your training and eval configs from the CLI in a powerful way, but there are some things to understand.

The most demonstrative and helpful example of the CLI structure is the difference in output between the following commands:

ns-train -h
ns-train nerfacto -h nerfstudio-data
ns-train nerfacto nerfstudio-data -h

In each of these examples, the -h applies to the previous subcommand (ns-train, nerfacto, and nerfstudio-data).

In the first example, we get the help menu for the ns-train script. In the second example, we get the help menu for the nerfacto model. In the third example, we get the help menu for the nerfstudio-data dataparser.

With our scripts, your arguments will apply to the preceding subcommand in your command, and thus where you put your arguments matters! Any optional arguments you discover from running

ns-train nerfacto -h nerfstudio-data

need to come directly after the nerfacto subcommand, since these optional arguments only belong to the nerfacto subcommand:

ns-train nerfacto {nerfacto optional args} nerfstudio-data

╭─ options ───────────────────────────────────────────────────────╮ ╭─ subcommands ───────────────────────────────────────────────────╮ │ -h, --help show this help message and exit │ │ {depth-nerfacto,dnerf,fruit_nerf,fruit_nerf_big,fruit_nerf_hug… │ ╰─────────────────────────────────────────────────────────────────╯ │ depth-nerfacto │ │ Nerfacto with depth supervision. │ │ dnerf Dynamic-NeRF model. (slow) │ │ fruit_nerf Base config for FruitNeRF │ │ fruit_nerf_big │ │ Base config for FruitNeRF-Big │ │ fruit_nerf_huge │ │ Base config for FruitNeRF-Huge │ │ generfacto Generative Text to NeRF model │ │ instant-ngp Implementation of Instant-NGP. Recommended │ │ real-time model for unbounded scenes. │ │ instant-ngp-bounded │ │ Implementation of Instant-NGP. Recommended │ │ for bounded real and synthetic scenes │ │ mipnerf High quality model for bounded scenes. (slow) │ │ nerfacto Recommended real-time model tuned for real │ │ captures. This model will be continually │ │ updated. │ │ nerfacto-big │ │ nerfacto-huge │ │ neus Implementation of NeuS. (slow) │ │ neus-facto Implementation of NeuS-Facto. (slow) │ │ phototourism Uses the Phototourism data. │ │ semantic-nerfw │ │ Predicts semantic segmentations and filters │ │ out transient objects. │ │ tensorf tensorf │ │ vanilla-nerf Original NeRF model. (slow) │ │ volinga Real-time rendering model from Volinga. │ │ Directly exportable to NVOL format at │ │ https://volinga.ai/ │ │ in2n [External] Instruct-NeRF2NeRF. Full model, │ │ used in paper │ │ in2n-small [External] Instruct-NeRF2NeRF. Half precision │ │ model │ │ in2n-tiny [External] Instruct-NeRF2NeRF. Half prevision │ │ with no LPIPS │ │ kplanes [External] K-Planes model tuned to static │ │ blender scenes │ │ kplanes-dynamic │ │ [External] K-Planes model tuned to dynamic │ │ DNeRF scenes │ │ lerf [External] LERF with OpenCLIP ViT-B/16, used │ │ in paper │ │ lerf-big [External] LERF with OpenCLIP ViT-L/14 │ │ lerf-lite [External] LERF with smaller network and less │ │ LERF samples │ │ nerfplayer-nerfacto │ │ [External] NeRFPlayer with nerfacto backbone │ │ nerfplayer-ngp │ │ [External] NeRFPlayer with │ │ instang-ngp-bounded backbone │ │ tetra-nerf [External] Tetra-NeRF. Different sampler - │ │ faster and better │ │ tetra-nerf-original │ │ [External] Tetra-NeRF. Official │ │ implementation from the paper │ Segmentation Fault (core dumped)

meyerls commented 1 month ago

The command ns protocol free data is not available. But it is strange that ns-process-fruit-data is not found.

As a quick hack you can simply try to run the file python debug/process_data.py and parse the same arguments.

Double-zh commented 1 month ago

Hello. I followed your instructions and got the following error.

(nerfstudio) catas@catas:~/FruitNeRF$ python debug/process_data.py --data /home/catas/FruitNeRF/images/teaser_github.mp4 --output-dir /home/catas/FruitNeRF/output3/output1 --data_semantic /home/catas/FruitNeRF/output3/output2 ['/home/catas/FruitNeRF/debug', '/home/catas/realsense_catkin_ws/devel/lib/python2.7/dist-packages', '/home/catas/catkin_ws/devel/lib/python2.7/dist-packages', '/opt/ros/melodic/lib/python2.7/dist-packages', '/home/catas/anaconda3/envs/nerfstudio/lib/python38.zip', '/home/catas/anaconda3/envs/nerfstudio/lib/python3.8', '/home/catas/anaconda3/envs/nerfstudio/lib/python3.8/lib-dynload', '/home/catas/.local/lib/python3.8/site-packages', '/home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages', 'editable.fruit_nerf-0.0.1.finder.__path_hook__', '/home/catas/FruitNeRF/segmentation/grounded_sam/segment_anything'] /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_fields.py:330: UserWarning: The field segmentation_class is annotated with type <class 'str'>, but the default value None has type <class 'NoneType'>. We'll try to handle this gracefully, but it may cause unexpected behavior. warnings.warn( [23:51:16] 💀 No usable images in the data folder. process_data_utils.py:309 Segmentation Fault (core dumped)

Double-zh commented 1 month ago

The same error still occurred. (nerfstudio) catas@catas:~/FruitNeRF$ ns-prepocess-fruit-data --data /home/catas/images --output-dir /home/catas/FruitNeRF/output3/output1 --data_semantic /home/catas/FruitNeRF/output3/output2 ns-prepocess-fruit-data：未找到命令

(nerfstudio) catas@catas:~/FruitNeRF$ ns-install-cli [23:58:04] 🔍 Detected conda environment /home/catas/anaconda3/envs/nerfstudio! install.py:364 ✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-install-cli.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-dev-test.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-install-cli.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-dev-test.
[23:58:05] ✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-dev-sync-viser-message-defs.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-process-data.
[23:58:06] ✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-dev-sync-viser-message-defs.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-download-data.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-download-data.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-process-data.
[23:58:08] ✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-viewer.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-eval.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-viewer.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-render.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-render.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-eval.
[23:58:09] ✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-train.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-train.
[23:58:10] ✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/bash/_ns-export.
✔ Nothing to do for install.py:139 /home/catas/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/completio
ns/zsh/_ns-export.
🙆 Completions installed to /home/catas/anaconda3/envs/nerfstudio. Cool! Reactivate the install.py:275 environment to try them out.
All done!

meyerls commented 1 month ago

I found two issues relating your problem.

  1. Processing data includes only images and no video (you tried a mp4). In the original nerfstudio implementation you can also pose the images in the video. But our implementations supports only images.

  2. The images/teaser_github.mp4 video does not work for the reconstruction. It is a low resolution video and counting different modalities such as segmentation heat maps and binary masks. If you want to try out FruitNeRF I highly recommend you to look at the Dataset we provide. You can find the in the Readme or here: https://zenodo.org/records/10869455

FavorMylikes commented 5 days ago

@Double-zh That should be a typo, ns-prepocess-fruit-data should be ns-process-fruit-data