Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
RoboOrchardLab
Light Logo Dark Logo
RoboOrchardLab
  • Getting Started
    • Installation
  • Overview
    • Framework Architecture
    • Hook Based Trainer Architecture
  • RoboOrchard Dataset Tutorials
    • Why RoboOrchard Dataset
    • Dataset Overview
    • Accessing and Visualizing Datasets
    • Integrating with PyTorch DataLoader
    • Creating a RoboOrchard Dataset (Data Packaging)
    • Ecosystem: MCAP and LeRobot Interoperability
  • Trainer Tutorials
    • Configuration & Your First Basic Training Run
    • Leveraging Built-in Hooks for Common Training Tasks
    • (Advanced) Creating Custom Hooks for Tailored Logic
  • Model Zoo Tutorials
    • Creating, Saving, and Loading Models
    • Creating, Saving, and Loading Inference Pipelines
    • Model Zoo: Loading Pre-trained Perception Models
    • Model Zoo: Loading Pre-trained Manipulation Models
    • Model Zoo: Loading Pre-trained Navigation Models
  • API Reference
    • robo_orchard_lab
      • dataset
        • collates
        • datatypes
          • camera
          • geometry
          • hg_features
            • base
            • tensor
          • joint_state
          • tf_graph
        • embodiedscan
          • embodiedscan_det_grounding_dataset
          • metrics
          • transforms
          • utils
        • graspnet1b
          • ecograsp1b_dataset
          • metrics
        • horizon_manipulation
          • packer
            • mcap_arrow_packer
            • mcap_lmdb_packer
            • utils
        • lmdb
          • base_lmdb_dataset
          • lmdb_wrapper
        • robot
          • columns
          • conversion
            • lerobot_dataset
          • dataset
          • db_orm
            • base
            • episode
            • instruction
            • md5
            • robot
            • sql_types
            • task
          • engine
          • merge
          • packaging
          • re_packing
          • row_sampler
        • robotwin
          • close_loop_eval
          • robotwin_lmdb_dataset
          • robotwin_packer
          • transforms
        • sampler
        • transforms
      • distributed
        • utils
      • envs
        • maniskill
        • robotwin
          • env
          • obs
      • inference
        • basic
        • mixin
        • processor
          • compose
          • identity
          • mixin
      • metrics
        • base
      • models
        • aux_think
          • model
          • processor
        • bip3d
          • bert
          • feature_enhancer
          • grounding_decoder
            • bbox3d_decoder
            • deformable_aggregation
            • instance_bank
            • target
            • utils
          • layers
          • spatial_enhancer
          • structure
          • utils
        • checkpoints
        • codec
          • base
          • normalize
        • finegrasp
          • backbone
            • minkunet
            • spunet
          • finegrasp
          • head
            • head
          • losses
          • processor
          • utils
        • layers
          • data_preprocessors
          • transformer_layers
        • mixin
        • modules
          • channel_mapper
          • resnet
          • swin_transformer
        • monodream
          • builder
          • configuration_llava
          • language_model
            • builder
            • llava_llama
          • model
          • multimodal_encoder
            • basic
            • builder
            • image_processor
            • mm_utils
            • siglip
              • modeling_siglip
            • siglip_encoder
            • vision_encoder
          • multimodal_projector
            • base_projector
            • builder
          • navigation_arch
          • processor
          • utils
            • constants
            • tokenizer
        • sem_modules
          • action_decoder
          • layers
          • processor
          • robot_state_encoder
        • tokenizer
          • action_bbpe
          • action_dct
          • huggingface
        • torch_model
      • ops
        • deformable_aggregation
          • deformable_aggregation
      • pipeline
        • batch_processor
          • mixin
          • simple
        • hook_based_trainer
        • hooks
          • checkpoint
          • grad_clip
          • loss_tracker
          • memory
          • metric
          • mixin
          • optimizer
          • stats
          • validation
        • trainer
      • policy
        • base
        • evaluator
        • remote
      • transforms
        • action
          • joint_state
        • base
        • image
          • affine
          • color
          • decode
          • formatter
          • random
          • transform2d
        • noise
        • normalize
        • padding
        • take
      • utils
        • build
        • env
        • geometry
        • huggingface
        • logging
        • misc
        • path
        • protobuf
        • pydantic
        • random
        • state
        • torch
      • version
Back to top
View this page

models¶

Submodules¶

  • aux_think
  • bip3d
  • checkpoints
  • codec
  • finegrasp
  • layers
  • mixin
  • modules
  • monodream
  • sem_modules
  • tokenizer
  • torch_model
Next
aux_think
Previous
base
Copyright © 2024-2025, Horizon Robotics Developers
Made with Sphinx and @pradyunsg's Furo
On this page
  • models
    • Submodules