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 callersFunctionset_seed_everywhere

Set random seed for all random number generators for reproducibility. Args: seed: The random seed to use

policy/openvla-oft/experiments/robot/robot_utils.py:38

↓ 2 callersFunctionsetup_master_bot

(bot)

policy/DexVLA/aloha_scripts/robot_utils.py:168

↓ 2 callersFunctionsetup_master_bot

(bot)

policy/openvla-oft/experiments/robot/aloha/robot_utils.py:168

↓ 2 callersFunctionsetup_puppet_bot

(bot)

policy/DexVLA/aloha_scripts/robot_utils.py:162

↓ 2 callersFunctionsetup_puppet_bot

(bot)

policy/openvla-oft/experiments/robot/aloha/robot_utils.py:162

↓ 2 callersMethodto_bfloat16_for_selected_params

(self, precision: Literal["bfloat16", "float32"] = "bfloat16")

policy/pi05/src/openpi/models_pytorch/gemma_pytorch.py:63

↓ 2 callersMethodto_tensor

(x)

policy/DP/diffusion_policy/model/common/normalizer.py:146

↓ 2 callersMethodtogether_open_gripper

(self, save_freq=-1, left_pos=1, right_pos=1)

envs/_base_task.py:718

↓ 2 callersMethodtokenize

(self, prompt: str)

policy/pi0/src/openpi/models/tokenizer.py:19

↓ 2 callersMethodtokenize

(self, prompt: str, state: np.ndarray | None = None)

policy/pi05/src/openpi/models/tokenizer.py:22

↓ 2 callersMethodtokenize

( self, prompt: str, state: np.ndarray, actions: np.ndarray | None )

policy/pi05/src/openpi/models/tokenizer.py:300

↓ 2 callersMethodtraining_step

Perform a training step on a batch of inputs. Subclass and override to inject custom behavior. Args: model (`nn

policy/DexVLA/dex_vla/train/dex_vla_trainer.py:394

↓ 2 callersMethodtrans_base

( now_base_mat: np.ndarray, init_base_mat: np.ndarray, init_pose_mat: np.ndarray,

envs/utils/transforms.py:143

↓ 2 callersFunctiontransform

(img: np.ndarray)

policy/DP/diffusion_policy/common/cv2_util.py:116

↓ 2 callersFunctiontree_map

(fn: Callable, tree: Dict)

policy/openvla-oft/prismatic/vla/datasets/rlds/utils/data_utils.py:24

↓ 2 callersMethodtrim

(self, start_t: float, end_t: float)

policy/DP/diffusion_policy/common/pose_trajectory_interpolator.py:67

↓ 2 callersFunctionunflatten_dict

Unflatten a flattened dictionary. Assumes that '/' was used as a separator.

policy/pi0/src/openpi/transforms.py:326

↓ 2 callersFunctionunflatten_dict

Unflatten a flattened dictionary. Assumes that '/' was used as a separator.

policy/pi05/src/openpi/transforms.py:345

↓ 2 callersMethodupdate

(self, value, n=1)

policy/ACT/detr/util/misc.py:41

↓ 2 callersMethodupdate

(self, value, n=1)

policy/DexVLA/dex_vla/external_vision_encoder/misc.py:40

↓ 2 callersMethodupdate

(self, value, n=1)

policy/DexVLA/policy_heads/util/misc.py:40

↓ 2 callersFunctionupdate_auto_map

Update the AutoMap configuration in the checkpoint config.json file. This loads the config.json file inside the checkpoint directory and ove

policy/openvla-oft/experiments/robot/openvla_utils.py:56

↓ 2 callersMethodupdate_obs

(self, observation)

policy/DP3/3D-Diffusion-Policy/dp3_policy.py:34

↓ 2 callersMethodupdate_observation_window

(self, img_arr, state)

policy/pi0/pi_model.py:59

↓ 2 callersMethodupdate_observation_window

(self, input_rgb_arr, input_state)

policy/GO1/deploy_policy.py:42

↓ 2 callersMethodupdate_observation_window

(self, img_arr, state)

policy/pi05/pi_model.py:59

↓ 2 callersMethodupdate_picture

(self)

envs/camera/camera.py:273

↓ 2 callersFunctionvariance_scaling_

(tensor, scale=1.0, mode="fan_in", distribution="normal")

policy/pi05/src/openpi/models_pytorch/transformers_replace/models/siglip/modeling_siglip.py:103

↓ 2 callersFunctionvis_stats

(vector, vector_mean, tag)

policy/openvla-oft/rlds_dataset_builder/visualize_dataset.py:61

↓ 2 callersMethodvisualize

(self)

script/create_object_data.py:281

↓ 2 callersMethodvisualize

(self)

script/create_object_data.py:666

↓ 2 callersFunctionvisualize_single

(efforts_list, label, plot_path=None, ylim=None, label_overwrite=None)

policy/DexVLA/aloha_scripts/visualize_episodes.py:130

↓ 2 callersFunctionvisualize_single

(efforts_list, label, plot_path=None, ylim=None, label_overwrite=None)

policy/TinyVLA/aloha_scripts/visualize_episodes.py:130

↓ 2 callersMethodvlm_forward

( self, pixel_values: torch.FloatTensor, input_ids: torch.LongTensor = Non

policy/TinyVLA/vla/models/internvl/modeling_tinyvla.py:56

↓ 2 callersMethodwith_pos_embed

(self, tensor, pos: Optional[Tensor])

policy/ACT/detr/models/transformer.py:182

↓ 2 callersFunctionwrap_ddp

Wrap a module with DistributedDataParallel if distributed environment is initialized. Otherwise, return the module itself (e.g., for single-G

policy/openvla-oft/vla-scripts/finetune.py:236

↓ 2 callersMethodwrite_hyperparameters

(self)

policy/openvla-oft/prismatic/training/metrics.py:82

↓ 1 callersMethod__getitem__

(self, index)

policy/ACT/utils.py:27

↓ 1 callersMethod__getitem__

(self, index)

policy/DexVLA/data_utils/dataset.py:136

↓ 1 callersMethod__getitem__

(self, index)

policy/TinyVLA/data_utils/dataset.py:97

↓ 1 callersMethod__init__

Initializes the model. Parameters: backbones: torch module of the backbone to be used. See backbone.py transformer: t

policy/ACT/detr/models/detr_vae.py:151

↓ 1 callersMethod__init__

(self, num_pos_feats=64, temperature=10000, normalize=False, scale=None)

policy/ACT/detr/models/position_encoding.py:22

↓ 1 callersMethod__init__

(self, config)

policy/LLaVA-VLA/llava/model/llava_arch.py:32

↓ 1 callersMethod__init__

(self, config: LlamaConfig)

policy/LLaVA-VLA/llava/model/language_model/asr_llava.py:37

↓ 1 callersMethod__init__

(self, config: LlamaConfig)

policy/LLaVA-VLA/llava/model/language_model/llava_llama.py:37

↓ 1 callersMethod__init__

(self, config: MptConfig)

policy/LLaVA-VLA/llava/model/language_model/llava_mpt.py:32

↓ 1 callersMethod__init__

(self, config: MistralConfig)

policy/LLaVA-VLA/llava/model/language_model/llava_mistral.py:38

↓ 1 callersMethod__init__

( self, data_size: int, batch_size: int, shuffle: bool = False, seed:

policy/DP/diffusion_policy/workspace/robotworkspace.py:279

↓ 1 callersMethod__init__

( self, input_dim, local_cond_dim=None, global_cond_dim=None, diffusio

policy/DP/diffusion_policy/model/diffusion/conditional_unet1d.py:76

↓ 1 callersMethod__init__

(self, policy_config)

policy/DexVLA/deploy_policy.py:139

↓ 1 callersMethod__init__

(self)

policy/DexVLA/dex_vla/external_vision_encoder/modules.py:42

↓ 1 callersMethod__init__

( self, vocab_size=152064, hidden_size=8192, intermediate_size=29568,

policy/DexVLA/dex_vla/models/configuration_dex_vla.py:187

↓ 1 callersMethod__init__

(self, callback: Callable[[], splits_lib.SplitInfo])

policy/openvla-oft/datasets/conversion_utils.py:107

↓ 1 callersMethod__init__

(self, callback: Callable[[], splits_lib.SplitInfo])

policy/openvla-oft/rlds_dataset_builder/aloha1_put_X_into_pot_300_demos/conversion_utils.py:107

↓ 1 callersMethod__init__

(self, callback: Callable[[], splits_lib.SplitInfo])

policy/openvla-oft/rlds_dataset_builder/LIBERO_Spatial/conversion_utils.py:107

↓ 1 callersMethod__init__

(self, callback: Callable[[], splits_lib.SplitInfo])

policy/openvla-oft/rlds_dataset_builder/LIBERO_Object/conversion_utils.py:107

↓ 1 callersMethod__init__

(self, callback: Callable[[], splits_lib.SplitInfo])

policy/openvla-oft/rlds_dataset_builder/LIBERO_10/conversion_utils.py:107

↓ 1 callersMethod__init__

(self, callback: Callable[[], splits_lib.SplitInfo])

policy/openvla-oft/rlds_dataset_builder/LIBERO_Goal/conversion_utils.py:107

↓ 1 callersMethod__init__

( self, norm_stats: Optional[Dict[str, Dict[str, Dict[str, Dict[str, List[float]]]]]] = None,

policy/openvla-oft/prismatic/extern/hf/configuration_prismatic.py:132

↓ 1 callersMethod__init__

( self, image_processor: Optional[ImageProcessingMixin] = None, tokenizer: Optional[Pr

policy/openvla-oft/prismatic/extern/hf/processing_prismatic.py:180

↓ 1 callersMethod__init__

( self, chat_json: Path, image_dir: Path, image_transform: ImageTransform,

policy/openvla-oft/prismatic/preprocessing/datasets/datasets.py:30

↓ 1 callersMethod__init__

(self, llm_dim: int, proprio_dim: int)

policy/openvla-oft/prismatic/models/projectors.py:10

↓ 1 callersMethod__init__

(self, llm_backbone_id: str)

policy/openvla-oft/prismatic/models/backbones/llm/base_llm.py:38

↓ 1 callersMethod__init__

(self, model_family: str, system_prompt: Optional[str] = None)

policy/openvla-oft/prismatic/models/backbones/llm/prompting/base_prompter.py:12

↓ 1 callersMethod__init__

(self, vision_backbone_id: str, image_resize_strategy: str, default_image_size: int = 224)

policy/openvla-oft/prismatic/models/backbones/vision/base_vision.py:55

↓ 1 callersMethod__init__

(self, vision_tower, args, delay_load=False)

policy/RDT/models/multimodal_encoder/clip_encoder.py:9

↓ 1 callersMethod__init__

( self, input_dim, local_cond_dim=None, global_cond_dim=None, diffusio

policy/DP3/3D-Diffusion-Policy/diffusion_policy_3d/model/diffusion/simple_conditional_unet1d.py:104

↓ 1 callersMethod__init__

(self)

envs/_base_task.py:38

↓ 1 callersMethod__init__

( self, urdf_path, srdf_path, move_group, robot_origion_pose,

envs/robot/planner.py:282

↓ 1 callersMethod_accept_connections

Accept and handle new client connections

script/policy_model_server.py:109

↓ 1 callersMethod_act_tokens_to_paligemma_tokens

(self, tokens: np.ndarray | list[int])

policy/pi05/src/openpi/models/tokenizer.py:240

↓ 1 callersMethod_act_tokens_to_paligemma_tokens

(self, tokens: np.ndarray | list[int])

policy/pi05/src/openpi/models/tokenizer.py:368

↓ 1 callersFunction_add_speaker_and_signal

Add speaker and start/end signal on each round.

policy/LLaVA-VLA/llava/train/train.py:287

↓ 1 callersMethod_adjust_histograms

Adjust histograms when min or max changes.

policy/pi0/src/openpi/shared/normalize.py:92

↓ 1 callersMethod_adjust_histograms

Adjust histograms when min or max changes.

policy/pi05/src/openpi/shared/normalize.py:88

↓ 1 callersFunction_apply_film_to_vla

Apply FiLM (Feature-wise Linear Modulation) to the VLA vision backbone. Args: vla: The VLA model cfg: Configuration object w

policy/openvla-oft/experiments/robot/openvla_utils.py:311

↓ 1 callersFunction_axis_angle_rotation

Return the rotation matrices for one of the rotations about an axis of which Euler angles describe, for each value of the angle given. A

policy/DexVLA/torch_utils.py:613

↓ 1 callersFunction_bool_feature

Returns a bool_list from a boolean.

policy/RDT/data/agilex/hdf5totfrecords.py:18

↓ 1 callersMethod_build_multimodal_labels

Build multimodal labels with IGNORE_INDEX for patch embeddings

policy/openvla-oft/prismatic/extern/hf/modeling_prismatic.py:486

↓ 1 callersMethod_calculate_scaled_bounds

Calculate the scaled bounds of the bounding box. Returns: Tuple of (min_bound, max_bound) arrays

description/utils/get_image_from_glb.py:64

↓ 1 callersMethod_compute_quantiles

Compute quantiles based on histograms.

policy/pi0/src/openpi/shared/normalize.py:110

↓ 1 callersMethod_compute_quantiles

Compute quantiles based on histograms.

policy/pi05/src/openpi/shared/normalize.py:106

↓ 1 callersMethod_connect

(self)

script/eval_policy_client.py:141

↓ 1 callersFunction_decode_aloha

(data: dict, *, adapt_to_pi: bool = False)

policy/pi0/src/openpi/policies/aloha_policy.py:168

↓ 1 callersFunction_decode_aloha

(data: dict, *, adapt_to_pi: bool = False)

policy/pi05/src/openpi/policies/aloha_policy.py:159

↓ 1 callersFunction_decode_state

(state: np.ndarray, *, adapt_to_pi: bool = False)

policy/pi0/src/openpi/policies/aloha_policy.py:190

↓ 1 callersFunction_decode_state

(state: np.ndarray, *, adapt_to_pi: bool = False)

policy/pi05/src/openpi/policies/aloha_policy.py:181

↓ 1 callersFunction_download_fsspec

Download a file from a remote filesystem to the local cache, and return the local path.

policy/pi0/src/openpi/shared/download.py:121

↓ 1 callersFunction_download_fsspec

Download a file from a remote filesystem to the local cache, and return the local path.

policy/pi05/src/openpi/shared/download.py:103

↓ 1 callersMethod_dynamic_frequency_update

dynamic RoPE layers should recompute `inv_freq` in the following situations: 1 - growing beyond the cached sequence length (allow sca

policy/DexVLA/dex_vla/models/qwen2_vl_modules.py:156

↓ 1 callersFunction_encode_actions

(actions: np.ndarray, *, adapt_to_pi: bool = False)

policy/pi0/src/openpi/policies/aloha_policy.py:199

↓ 1 callersFunction_encode_actions

(actions: np.ndarray, *, adapt_to_pi: bool = False)

policy/pi05/src/openpi/policies/aloha_policy.py:190

↓ 1 callersFunction_encode_actions_inv

(actions: np.ndarray, *, adapt_to_pi: bool = False)

policy/pi0/src/openpi/policies/aloha_policy.py:207

↓ 1 callersFunction_encode_actions_inv

(actions: np.ndarray, *, adapt_to_pi: bool = False)

policy/pi05/src/openpi/policies/aloha_policy.py:198

↓ 1 callersFunction_extract_observation

(args: Args, obs_dict, *, save_to_disk=False)

policy/pi0/examples/droid/main.py:195

↓ 1 callersFunction_extract_observation

(args: Args, obs_dict, *, save_to_disk=False)

policy/pi05/examples/droid/main.py:195

↓ 1 callersMethod_flash_attn

(self, x, key_padding_mask=None, need_weights=False)

policy/TinyVLA/vla/models/internvl/modeling_intern_vit.py:229

↓ 1 callersMethod_format_joint_to_state

Format the joint proprioception into the unified action vector. Args: joints (torch.Tensor): The joint proprioception to

policy/RDT/scripts/agilex_model.py:184

↓ 1 callersMethod_format_joint_to_state

Format the robot joint state into the unified state vector. Args: joints (torch.Tensor): The joint state to be formatted

policy/RDT/scripts/maniskill_model.py:197

↓ 1 callersMethod_forward_impl

(self, x: Tensor, film_features: List[Optional[Tensor]],

policy/DexVLA/dex_vla/external_vision_encoder/resnet_film.py:296

← previous next →801–900 of 4,415, ranked by callers