Functions — github.com/RoboTwin-Platform/RoboTwin

hub / github.com/RoboTwin-Platform/RoboTwin / functions

Functions4,415 in github.com/RoboTwin-Platform/RoboTwin

⨍ Functions 4,415◇ Types & classes 876↳ Endpoints 1

↓ 2 callersMethodembed_suffix

Embed state, noisy_actions, timestep to prepare for Expert Gemma processing.

policy/pi05/src/openpi/models_pytorch/pi0_pytorch.py:237

↓ 2 callersMethodembed_suffix

( self, obs: _model.Observation, noisy_actions: _model.Actions, timestep: at.Float[at.Array, " b"]

policy/pi05/src/openpi/models/pi0.py:140

↓ 2 callersMethodencode

(self, inputs: jnp.ndarray)

policy/pi05/src/openpi/models/utils/fsq_tokenizer.py:93

↓ 2 callersMethodencode_images

(self, images)

policy/LLaVA-VLA/llava/model/llava_arch.py:142

↓ 2 callersFunctionencode_obs

(observation)

policy/pi0/deploy_policy.py:14

↓ 2 callersFunctionencode_obs

(observation)

policy/LLaVA-VLA/deploy_policy.py:16

↓ 2 callersFunctionencode_obs

(observation)

policy/DP/deploy_policy.py:5

↓ 2 callersFunctionencode_obs

(observation)

policy/DP/deploy_policy_double_env.py:7

↓ 2 callersFunctionencode_obs

(observation)

policy/Your_Policy/deploy_policy.py:4

↓ 2 callersFunctionencode_obs

(observation)

policy/Your_Policy/deploy_policy_double_env.py:9

↓ 2 callersFunctionencode_obs

(observation)

policy/RDT/deploy_policy.py:9

↓ 2 callersFunctionencode_obs

(observation)

policy/DP3/deploy_policy.py:33

↓ 2 callersFunctionencode_obs

(observation)

policy/pi05/deploy_policy.py:14

↓ 2 callersFunctioneuler_to_rmat

(euler)

policy/openvla-oft/prismatic/vla/datasets/rlds/oxe/utils/droid_utils.py:13

↓ 2 callersFunctioneval_function_decorator

(policy_name, model_name, conda_env=None)

script/eval_policy_client.py:106

↓ 2 callersMethodevaluate

(self, input_ids: torch.LongTensor = None, actions=None, st

policy/DexVLA/dex_vla/models/modeling_dex_vla.py:675

↓ 2 callersMethodevaluate_rollout_error

(env, states, actions, robot0_eef_pos, robot0_eef_quat, metric_skip_steps=1)

policy/DP/diffusion_policy/common/robomimic_util.py:134

↓ 2 callersMethodextract_actions

(self, tokens: np.ndarray, action_horizon: int, action_dim: int)

policy/pi0/src/openpi/models/tokenizer.py:103

↓ 2 callersMethodfeature_select

(self, image_forward_outs)

policy/LLaVA-VLA/llava/model/multimodal_encoder/clip_encoder.py:35

↓ 2 callersMethodfeature_select

(self, image_forward_outs)

policy/RDT/models/multimodal_encoder/dinov2_encoder.py:34

↓ 2 callersMethodfeature_select

(self, image_forward_outs)

policy/RDT/models/multimodal_encoder/siglip_encoder.py:34

↓ 2 callersFunctionfilter_instructions

Filter instructions to only include those that have all placeholders matching the available episode parameters. No more, no less. Also ac

description/utils/generate_episode_instructions.py:18

↓ 2 callersFunctionflatten_list

(l)

policy/TinyVLA/data_utils/dataset.py:18

↓ 2 callersMethodflush

(self)

policy/LLaVA-VLA/llava/utils.py:87

↓ 2 callersMethodforward

(self, x: Union[np.ndarray, torch.Tensor])

policy/DP/diffusion_policy/model/common/rotation_transformer.py:72

↓ 2 callersFunctionforward_pass

(data, policy)

policy/ACT/imitate_episodes.py:346

↓ 2 callersFunctionfps

(points, num_points=1024, use_cuda=True)

envs/camera/camera.py:20

↓ 2 callersMethodfrom_dict

This method defines the mapping between unstructured data (i.e., nested dict) to the structured Observation format.

policy/pi05/src/openpi/models/model.py:110

↓ 2 callersMethodfusion_input_reasoning

(self, labels, input_ids, hidden_states, prev_layer_hidden_states=None)

policy/DexVLA/dex_vla/models/modeling_dex_vla.py:507

↓ 2 callersFunctiongather_along_dim_with_dim_single

This function indexes out a target dimension of a tensor in a structured way, by allowing a different value to be selected for each member of

policy/DP/diffusion_policy/model/common/tensor_util.py:676

↓ 2 callersFunctiongather_along_dim_with_dim_single

This function indexes out a target dimension of a tensor in a structured way, by allowing a different value to be selected for each member of

policy/DP3/3D-Diffusion-Policy/diffusion_policy_3d/model/common/tensor_util.py:676

↓ 2 callersFunctiongenerate

(messages: List[dict], custom_format: Type[BaseModel])

description/utils/agent.py:23

↓ 2 callersMethodgenerate

( self, pixel_values: Optional[torch.FloatTensor] = None, input_ids: Optio

policy/TinyVLA/vla/models/internvl/modeling_internvl_chat.py:310

↓ 2 callersMethodget

(self, out=None)

policy/DP/diffusion_policy/shared_memory/shared_memory_queue.py:109

↓ 2 callersFunctionget_1d_sincos_pos_embed_from_grid

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

policy/DexVLA/policy_heads/models/transformer_diffusion/modeling_dit_diffusion.py:616

↓ 2 callersFunctionget_action

(master_bot_left, master_bot_right)

policy/DexVLA/aloha_scripts/real_env.py:142

↓ 2 callersMethodget_action

(self,idx)

policy/LLaVA-VLA/llava/train/calvin_train_obs_real_pos_single_val_clean.py:542

↓ 2 callersMethodget_action

(self, img_arr=None, state=None)

policy/RDT/model.py:200

↓ 2 callersMethodget_action_dim

Dimensionality of the policy's action space.

policy/openvla-oft/prismatic/models/vlas/openvla.py:121

↓ 2 callersFunctionget_args_parser

()

policy/ACT/detr/main.py:14

↓ 2 callersFunctionget_args_parser

()

policy/DexVLA/policy_heads/main.py:12

↓ 2 callersFunctionget_body_type

(static=False)

policy/DP/diffusion_policy/common/pymunk_util.py:11

↓ 2 callersFunctionget_cache_dir

()

policy/pi0/src/openpi/shared/download.py:29

↓ 2 callersFunctionget_cache_dir

()

policy/pi05/src/openpi/shared/download.py:24

↓ 2 callersMethodget_checkpoint_path

(self, tag="latest")

policy/DP/diffusion_policy/workspace/base_workspace.py:73

↓ 2 callersMethodget_checkpoint_path

(self, tag="latest")

policy/DP3/3D-Diffusion-Policy/train_dp3.py:391

↓ 2 callersMethodget_depth

(self)

envs/camera/camera.py:412

↓ 2 callersMethodget_dtype

(self)

policy/DexVLA/dex_vla/models/qwen2_vl_modules.py:1033

↓ 2 callersFunctionget_embodiment_config

(robot_file)

script/eval_policy.py:57

↓ 2 callersFunctionget_embodiment_config

(robot_file)

script/eval_policy_client.py:127

↓ 2 callersFunctionget_embodiment_config

(robot_file)

script/collect_data.py:32

↓ 2 callersFunctionget_embodiment_config

Load embodiment configuration from the robot folder. Args: robot_file (str): Path to the robot folder. Returns: dict: R

code_gen/test_gen_code.py:142

↓ 2 callersFunctionget_face_prod

get product of local_axis (under q world) and target_axis

envs/utils/transforms.py:523

↓ 2 callersMethodget_identity_ctx

()

policy/openvla-oft/prismatic/overwatch/overwatch.py:111

↓ 2 callersMethodget_image_features

Obtains image last hidden states from the vision tower and apply multimodal projection. Args: pixel_values (`torch.Float

policy/pi05/src/openpi/models_pytorch/transformers_replace/models/paligemma/modeling_paligemma.py:232

↓ 2 callersMethodget_input_embeddings

(self)

policy/TinyVLA/vla/models/internvl/modeling_intern_vit.py:390

↓ 2 callersMethodget_left_arm_jointState

(self)

envs/robot/robot.py:494

↓ 2 callersMethodget_left_tcp_pose

(self)

envs/robot/robot.py:564

↓ 2 callersFunctionget_libero_dummy_action

Get dummy/no-op action, used to roll out the simulation while the robot does nothing.

policy/openvla-oft/experiments/robot/libero/libero_utils.py:28

↓ 2 callersFunctionget_libero_env

Initializes and returns the LIBERO environment, along with the task description.

policy/openvla-oft/experiments/robot/libero/libero_utils.py:18

↓ 2 callersFunctionget_llm_backbone_and_tokenizer

( llm_backbone_id: str, llm_max_length: int = 2048, hf_token: Optional[str] = None, inference_

policy/openvla-oft/prismatic/models/materialize.py:94

↓ 2 callersFunctionget_model

(usr_args)

policy/DP/deploy_policy.py:18

↓ 2 callersFunctionget_norm_stats

caculate all data action and qpos(robot state ) mean and std

policy/DexVLA/data_utils/lerobot_dataset.py:155

↓ 2 callersFunctionget_norm_stats

caculate all data action and qpos(robot state ) mean and std

policy/TinyVLA/data_utils/lerobot_dataset.py:153

↓ 2 callersFunctionget_norm_stats

(dataset_path_list, rank0_print=print)

policy/TinyVLA/data_utils/dataset.py:162

↓ 2 callersMethodget_normal_real_gripper_val

(self)

envs/robot/robot.py:619

↓ 2 callersMethodget_num_images_in_input

Returns the number of input images for the vision backbone. Returns: Number of images expected in the input

policy/openvla-oft/prismatic/extern/hf/modeling_prismatic.py:168

↓ 2 callersMethodget_num_images_in_input

Returns the number of input images for the vision backbone.

policy/openvla-oft/prismatic/models/film_vit_wrapper.py:223

↓ 2 callersMethodget_num_patches

Returns the number of vision patches output by the vision backbone. Returns: Number of patches per image

policy/openvla-oft/prismatic/extern/hf/modeling_prismatic.py:159

↓ 2 callersMethodget_observation

(self, t=0)

policy/openvla-oft/experiments/robot/aloha/real_env.py:111

↓ 2 callersMethodget_place_pose

( self, actor: Actor, arm_tag: ArmTag, target_pose: list | np.ndarray,

envs/_base_task.py:1220

↓ 2 callersMethodget_points

(self, type: str)

script/create_object_data.py:348

↓ 2 callersMethodget_pose

Get the sapien.Pose of the actor.

envs/utils/actor_utils.py:54

↓ 2 callersMethodget_prompt

Get the prompt for generation.

policy/TinyVLA/vla/models/internvl/conversation.py:63

↓ 2 callersMethodget_qpos

(physics)

policy/ACT/sim_env.py:100

↓ 2 callersMethodget_qpos

(self)

policy/openvla-oft/experiments/robot/aloha/real_env.py:57

↓ 2 callersMethodget_reward

(self)

policy/pi0/examples/aloha_real/real_env.py:138

↓ 2 callersMethodget_reward

(self)

policy/DexVLA/aloha_scripts/real_env.py:111

↓ 2 callersMethodget_reward

(self)

policy/pi05/examples/aloha_real/real_env.py:138

↓ 2 callersMethodget_rgb

(self)

envs/camera/camera.py:323

↓ 2 callersMethodget_rgba

(self)

envs/camera/camera.py:332

↓ 2 callersMethodget_right_arm_jointState

(self)

envs/robot/robot.py:501

↓ 2 callersMethodget_right_tcp_pose

(self)

envs/robot/robot.py:567

↓ 2 callersMethodget_rope_index

Calculate the 3D rope index based on image and video's temporal, height and width in LLM. Explanation: Each embedding se

policy/DexVLA/dex_vla/models/modeling_dex_vla.py:83

↓ 2 callersFunctionget_scheduler

Added kwargs vs diffuser's original implementation Unified API to get any scheduler from its name. Args: name (`str` or `Schedu

policy/DP/diffusion_policy/model/common/lr_scheduler.py:10

↓ 2 callersMethodget_segmentation

(self, level="mesh")

envs/camera/camera.py:377

↓ 2 callersMethodget_tokenizer

(self)

policy/openvla-oft/prismatic/models/backbones/llm/base_llm.py:46

↓ 2 callersFunctionget_vision_backbone_and_transform

Instantiate a Vision Backbone, returning both the nn.Module wrapper class and default Image Transform.

policy/openvla-oft/prismatic/models/materialize.py:78

↓ 2 callersFunctionget_world_size

()

policy/ACT/detr/util/misc.py:398

↓ 2 callersFunctionget_world_size

()

policy/DexVLA/dex_vla/external_vision_encoder/misc.py:386

↓ 2 callersFunctionget_world_size

()

policy/DexVLA/policy_heads/util/misc.py:386

↓ 2 callersMethodinit_joints

(self)

envs/robot/robot.py:166

↓ 2 callersMethodinitialize_episode

Sets the state of the environment at the start of each episode.

policy/ACT/sim_env.py:204

↓ 2 callersMethodinitialize_episode

Sets the state of the environment at the start of each episode.

policy/ACT/ee_sim_env.py:232

↓ 2 callersMethodinitialize_robots

(self, physics)

policy/ACT/ee_sim_env.py:94

↓ 2 callersMethodinputs_spec

Returns the input specification for the model. Values are jax.ShapeDtypeStruct.

policy/pi0/src/openpi/models/model.py:236

↓ 2 callersMethodinputs_spec

Returns the input specification for the model. Values are jax.ShapeDtypeStruct.

policy/pi05/src/openpi/models/model.py:250

↓ 2 callersFunctioninsert_separator

(X, sep)

policy/LLaVA-VLA/llava/mm_utils.py:190

↓ 2 callersMethodinverse

(self, x: Union[np.ndarray, torch.Tensor])

policy/DP/diffusion_policy/model/common/rotation_transformer.py:75

↓ 2 callersMethodis_left_gripper_close

(self)

envs/robot/robot.py:550

← previous next →601–700 of 4,415, ranked by callers