remove tensorf model (#660)

* remove tensorf model

* lint

.vscode/launch.json

@@ -86,23 +86,7 @@
       ]
     },
     {
-      "name": "Python: train tensorf",
-      "type": "python",
-      "request": "launch",
-      "program": "scripts/train.py",
-      "console": "integratedTerminal",
-      "args": ["tensorf"]
-    },
-    {
-      "name": "Python: train nerfw",
-      "type": "python",
-      "request": "launch",
-      "program": "scripts/train.py",
-      "console": "integratedTerminal",
-      "args": ["nerfw"]
-    },
-    {
-      "name": "Python: train semantic_nerf",
+      "name": "Python: train semantic_nerfw",
       "type": "python",
       "request": "launch",
       "program": "scripts/train.py",

docs/developer_guides/pipelines/creating_new_methods.ipynb

@@ -12,7 +12,7 @@
                 "\n",
                 "Here we explain how to create custom pipelines with nerfstudio. Pipelines are composed of two components, namely a DataManager and a Model. The pipeline is responsible for routing RayBundle instances returned from the DataManager into the Model.\n",
                 "\n",
-                "A NeRF method is implemented as a Pipeline. Users can create a Pipeline with a DataManager and Model. We provide default implementations for these components prefixed with the name Vanilla (e.g., `VanillaPipeline`, `VanillaDataManager` which inherit from the `Pipeline` and `DataManager` class, respectively) and specific Models (e.g., `InstantNGPModel` or `TensoRFModel` which inherit from the `Model` class). With most NeRF methods, `VanillaPipeline` and `VanillaDataManager` can be used and only the model needs to be changed. We provide many already implmented Models for people to get started with 3D reconstruction. However, in this tutorial we will demonstrate how to customize each of the Pipeline, DataManager, and Model with an example.\n",
+                "A NeRF method is implemented as a Pipeline. Users can create a Pipeline with a DataManager and Model. We provide default implementations for these components prefixed with the name Vanilla (e.g., `VanillaPipeline`, `VanillaDataManager` which inherit from the `Pipeline` and `DataManager` class, respectively) and specific Models (e.g., `InstantNGPModel` which inheritw from the `Model` class). With most NeRF methods, `VanillaPipeline` and `VanillaDataManager` can be used and only the model needs to be changed. We provide many already implmented Models for people to get started with 3D reconstruction. However, in this tutorial we will demonstrate how to customize each of the Pipeline, DataManager, and Model with an example.\n",
                 "\n",
                 "We'll show how to make an incremental DataManager where we progressively add cameras to train with from multiple scenes and importance sample rays from pixels with a high loss. The extensible features that we show in this tutorial are the following:\n",
                 "- a DataManager that incrementally adds cameras\n",
@@ -324,7 +324,7 @@
     ],
     "metadata": {
         "kernelspec": {
-            "display_name": "Python 3.8.13 ('nerfactory')",
+            "display_name": "Python 3.8.12 ('nerfactory')",
             "language": "python",
             "name": "python3"
         },
@@ -338,11 +338,11 @@
             "name": "python",
             "nbconvert_exporter": "python",
             "pygments_lexer": "ipython3",
-            "version": "3.8.13"
+            "version": "3.8.12"
         },
         "vscode": {
             "interpreter": {
-                "hash": "b7b86c17c0dfd6b313529972d424f2e075cc198a46cda005757126afe8133c7b"
+                "hash": "34c28001ff35fb390494047002768a8182dcf55b1b11415165e62ea61557ab83"
             }
         }
     },

docs/index.md

@@ -85,7 +85,6 @@ This documentation is organized into 3 parts:
 - [Mipnerf](https://jonbarron.info/mipnerf/): A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
 - [NerfW](https://nerf-w.github.io/): Neural Radiance Fields for Unconstrained Photo Collections
 - [Semantic NeRF](https://shuaifengzhi.com/Semantic-NeRF/): In-Place Scene Labelling and Understanding with Implicit Scene Representation
-- [TensoRF](https://apchenstu.github.io/TensoRF/): Tensorial Radiance Fields
 
 We'll be constantly growing this list! So make sure to check back in to see our updates.
 

docs/reference/api/models.rst

@@ -24,13 +24,6 @@ Semantic NeRF-W
    :members:
    :show-inheritance:
 
-TensoRF
-----------------
-
-.. automodule:: nerfstudio.models.tensorf
-   :members:
-   :show-inheritance:
-
 NeRF
 ----------------
 

nerfstudio/configs/method_configs.py

@@ -28,13 +28,11 @@
 from nerfstudio.data.dataparsers.friends_dataparser import FriendsDataParserConfig
 from nerfstudio.data.dataparsers.nerfstudio_dataparser import NerfstudioDataParserConfig
 from nerfstudio.engine.optimizers import AdamOptimizerConfig, RAdamOptimizerConfig
-from nerfstudio.engine.schedulers import SchedulerConfig
 from nerfstudio.models.base_model import VanillaModelConfig
 from nerfstudio.models.instant_ngp import InstantNGPModelConfig
 from nerfstudio.models.mipnerf import MipNerfModel
 from nerfstudio.models.nerfacto import NerfactoModelConfig
 from nerfstudio.models.semantic_nerfw import SemanticNerfWModelConfig
-from nerfstudio.models.tensorf import TensoRFModelConfig
 from nerfstudio.models.vanilla_nerf import NeRFModel
 from nerfstudio.pipelines.base_pipeline import VanillaPipelineConfig
 from nerfstudio.pipelines.dynamic_batch import DynamicBatchPipelineConfig
@@ -47,7 +45,6 @@
     "mipnerf": "High quality model for bounded scenes. [red]*slow*",
     "semantic-nerfw": "Predicts semantic segmentations and filters out transient objects.",
     "vanilla-nerf": "Original NeRF model. [red]*slow*",
-    "tensorf": "Fast model designed for bounded scenes.",
 }
 
 method_configs["nerfacto"] = Config(
@@ -149,31 +146,6 @@
     },
 )
 
-method_configs["tensorf"] = Config(
-    method_name="tensorf",
-    trainer=TrainerConfig(mixed_precision=True),
-    pipeline=VanillaPipelineConfig(
-        datamanager=VanillaDataManagerConfig(
-            dataparser=BlenderDataParserConfig(),
-        ),
-        model=TensoRFModelConfig(),
-    ),
-    optimizers={
-        "fields": {
-            "optimizer": RAdamOptimizerConfig(lr=0.001),
-            "scheduler": SchedulerConfig(lr_final=0.00005, max_steps=15000),
-        },
-        "position_encoding": {
-            "optimizer": RAdamOptimizerConfig(lr=0.02),
-            "scheduler": SchedulerConfig(lr_final=0.005, max_steps=15000),
-        },
-        "direction_encoding": {
-            "optimizer": RAdamOptimizerConfig(lr=0.02),
-            "scheduler": SchedulerConfig(lr_final=0.005, max_steps=15000),
-        },
-    },
-)
-
 
 AnnotatedBaseConfigUnion = dcargs.extras.subcommand_type_from_defaults(
     defaults=method_configs, descriptions=descriptions