MCPcopy Create free account

hub / github.com/InternRobotics/NavDP / functions

Functions736 in github.com/InternRobotics/NavDP

⨍ Functions 736◇ Types & classes 227↳ Endpoints 36
↓ 31 callersMethodflatten
(self, z: torch.Tensor)
baselines/gnm/base_model.py:30
↓ 17 callersFunctionnavigator_reset
(intrinsic=None,stop_threshold=-0.5,batch_size=1,port=8888,env_id=None)
utils_tasks/client_utils.py:8
↓ 14 callersFunctiondraw_box_with_text
(image, x, y, width, height, text, box_color=(0, 255, 0), text_color=(255, 255, 255),
utils_tasks/basic_utils.py:46
↓ 10 callersMethodrun
Start client and run until stopped
baselines/logoplanner/lekiwi_logoplanner_host.py:308
↓ 8 callersMethodreset
(self,batch_size)
baselines/gnm/base_agent.py:41
↓ 7 callersMethod__init__
ViNT class: uses a Transformer-based architecture to encode (current and past) visual observations and goals using an EfficientNet CN
baselines/vint/vint_network.py:74
↓ 7 callersMethodact
Infers action to take towards the given (rho, theta) based on depth vision. Args: observations (Union["TensorDict", Dict]): A dic
baselines/ddppo/pointnav_network.py:76
↓ 7 callersFunctionadjust_usd_scale
(prim_path="/World/Scene/terrain", scale=1.0)
utils_tasks/basic_utils.py:74
↓ 7 callersFunctionfind_usd_path
(dir,task='pointgoal')
utils_tasks/basic_utils.py:28
↓ 7 callersMethodflatten
(self, z: torch.Tensor)
baselines/vint/base_model.py:30
↓ 7 callersMethodget_intermediate_layers
( self, x: torch.Tensor, n: Union[int, Sequence] = 1, # Layers or n last layers to ta
baselines/navdp/depth_anything/depth_anything_v2/dinov2.py:297
↓ 7 callersMethodprocess_image
(self,images)
baselines/navdp/policy_agent.py:60
↓ 7 callersMethodvisualize_trajectory
(self, rgb_image, depth_image, intrinsic, trajectory_points, robot_pose, camera_roll=0, all_trajectories_point
utils_tasks/visualization_utils.py:76
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
baselines/logoplanner/depth_anything/depth_anything_v2/util/transform.py:51
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
baselines/logoplanner/depth_anything/metric_depth/dataset/transform.py:96
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/util/transform.py:51
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
baselines/navdp/depth_anything/depth_anything_v2/util/transform.py:51
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
baselines/navdp/depth_anything/metric_depth/dataset/transform.py:96
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/util/transform.py:51
↓ 5 callersMethodpredict_critic
(self,predict_trajectory,rgbd_embed)
baselines/navdp/policy_network.py:83
↓ 5 callersMethodprocess_depth
(self,depths)
baselines/navdp/policy_agent.py:76
↓ 5 callersMethodproject_trajectory
(self,images,n_trajectories,n_values)
baselines/navdp/policy_agent.py:36
↓ 4 callersMethod__init__
(self, vision_encoder, noise_pred_net, dist_pred_net)
baselines/nomad/nomad_model.py:12
↓ 4 callersMethod__init__
GNM main class Args: context_size (int): how many previous observations to used for context len_traj_pred (in
baselines/gnm/gnm_model.py:143
↓ 4 callersMethod__init__
(self, dim)
baselines/navdp/policy_backbone.py:7
↓ 4 callersFunction_make_fusion_block
(features, use_bn, size=None)
baselines/logoplanner/depth_anything/depth_anything_v2/dpt.py:12
↓ 4 callersFunction_make_fusion_block
(features, use_bn, size=None)
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dpt.py:12
↓ 4 callersFunction_make_fusion_block
(features, use_bn, size=None)
baselines/navdp/depth_anything/depth_anything_v2/dpt.py:12
↓ 4 callersFunction_make_fusion_block
(features, use_bn, size=None)
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dpt.py:12
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1, dilate=False)
baselines/viplanner/plannernet.py:121
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1, dilate=False)
baselines/iplanner/percept_net.py:89
↓ 4 callersFunctionadd_point_light
( position: torch.Tensor, intensity: float = 20000.0, color: tuple = (1.0, 1.0, 1.0), radius:
configs/tasks/usd_utils.py:14
↓ 4 callersMethodforward
(self, obs_img: torch.tensor, goal_img: torch.tensor)
baselines/gnm/gnm_model.py:192
↓ 4 callersMethodget_intermediate_layers
( self, x: torch.Tensor, n: Union[int, Sequence] = 1, # Layers or n last layers to ta
baselines/logoplanner/depth_anything/depth_anything_v2/dinov2.py:297
↓ 4 callersFunctionhide_entity
(prim_path: str)
configs/tasks/usd_utils.py:7
↓ 4 callersMethodpredict_noise
(self,last_actions,timestep,goal_embed,rgbd_embed)
baselines/navdp/policy_network.py:63
↓ 4 callersMethodprepare_tokens_with_masks
(self, x, masks=None)
baselines/logoplanner/depth_anything/depth_anything_v2/dinov2.py:212
↓ 4 callersMethodprepare_tokens_with_masks
(self, x, masks=None)
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dinov2.py:212
↓ 4 callersMethodprepare_tokens_with_masks
(self, x, masks=None)
baselines/navdp/depth_anything/depth_anything_v2/dinov2.py:212
↓ 4 callersMethodprepare_tokens_with_masks
(self, x, masks=None)
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dinov2.py:212
↓ 4 callersMethodreset
(self,batch_size,threshold)
baselines/logoplanner/policy_agent.py:32
↓ 4 callersMethodsolve
(self, x00)
utils_tasks/tracking_utils.py:91
↓ 4 callersFunctiontransform_images
Transforms a list of PIL image to a torch tensor.
baselines/gnm/gnm_agent.py:22
↓ 4 callersFunctiontransform_images
Transforms a list of PIL image to a torch tensor.
baselines/vint/vint_agent.py:21
↓ 4 callersFunctionwrite_metrics
(metrics, path="exploration.csv")
utils_tasks/basic_utils.py:39
↓ 3 callersMethodTrajGeneratorFromPFreeRot
(self, preds, step)
baselines/gnm/traj_opt.py:43
↓ 3 callersMethodTrajGeneratorFromPFreeRot
(self, preds, step)
baselines/vint/traj_opt.py:43
↓ 3 callersMethod__init__
(self, embed_dim, num_heads, target_length)
baselines/logoplanner/policy_backbone.py:34
↓ 3 callersMethod__init__
(self, in_channels, goal_channels, k=5)
baselines/viplanner/autoencoder.py:66
↓ 3 callersMethodcallback_obs
(self, imgs)
baselines/gnm/base_agent.py:87
↓ 3 callersMethodcallback_obs
(self, imgs)
baselines/vint/base_agent.py:87
↓ 3 callersMethodcompute_ref_theta
(self, ref_traj)
baselines/logoplanner/deployment/mpc_controller.py:125
↓ 3 callersMethodforward
convert from desired [signed linear speed, signed angular speed] to [Left Drive, Right Drive] joint targets. Args: command (np.nd
wheeled_robots/controllers/differential_controller.py:57
↓ 3 callersMethodinfer_image
(self, raw_image, input_size=518)
baselines/logoplanner/depth_anything/depth_anything_v2/dpt.py:187
↓ 3 callersMethodinfer_image
(self, raw_image, input_size=518)
baselines/navdp/depth_anything/depth_anything_v2/dpt.py:187
↓ 3 callersMethodinterp
(self, x, y, xs)
baselines/gnm/traj_opt.py:24
↓ 3 callersFunctionpointgoal_step
(point_goals,rgb_images,depth_images,port=8888)
utils_tasks/client_utils.py:47
↓ 3 callersFunctionreplace_bn_with_gn
Relace all BatchNorm layers with GroupNorm.
baselines/nomad/nomad_model.py:244
↓ 3 callersFunctiontransform_images
Transforms a list of PIL image to a torch tensor.
baselines/nomad/nomad_agent.py:22
↓ 2 callersMethodTrajGeneratorFromPFreeRot
(self, preds, step)
baselines/nomad/traj_opt.py:43
↓ 2 callersMethod__init__
( self, in_channels, features=256, use_bn=False, out_channels=[256
baselines/logoplanner/depth_anything/depth_anything_v2/dpt.py:39
↓ 2 callersMethod__init__
( self, in_channels, features=256, use_bn=False, out_channels=[256
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dpt.py:39
↓ 2 callersMethod__init__
( self, in_channels, features=256, use_bn=False, out_channels=[256
baselines/navdp/depth_anything/depth_anything_v2/dpt.py:39
↓ 2 callersMethod__init__
( self, in_channels, features=256, use_bn=False, out_channels=[256
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dpt.py:39
↓ 2 callersMethodcallback_obs
(self, imgs)
baselines/nomad/base_agent.py:87
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
baselines/viplanner/plannernet.py:10
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
baselines/iplanner/percept_net.py:10
↓ 2 callersFunctiondrop_add_residual_stochastic_depth
( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, )
baselines/logoplanner/depth_anything/depth_anything_v2/dinov2_layers/block.py:110
↓ 2 callersFunctiondrop_add_residual_stochastic_depth
( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, )
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/block.py:110
↓ 2 callersFunctiondrop_add_residual_stochastic_depth
( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, )
baselines/navdp/depth_anything/depth_anything_v2/dinov2_layers/block.py:110
↓ 2 callersFunctiondrop_add_residual_stochastic_depth
( x: Tensor, residual_func: Callable[[Tensor], Tensor], sample_drop_ratio: float = 0.0, )
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/block.py:110
↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list
( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =
baselines/logoplanner/depth_anything/depth_anything_v2/dinov2_layers/block.py:181
↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list
( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/block.py:181
↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list
( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =
baselines/navdp/depth_anything/depth_anything_v2/dinov2_layers/block.py:181
↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list
( x_list: List[Tensor], residual_func: Callable[[Tensor, Any], Tensor], sample_drop_ratio: float =
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/block.py:181
↓ 2 callersMethodget_action
(self,diffusion_output, action_stats)
baselines/nomad/nomad_agent.py:70
↓ 2 callersFunctionget_attn_bias_and_cat
this will perform the index select, cat the tensors, and provide the attn_bias from cache
baselines/logoplanner/depth_anything/depth_anything_v2/dinov2_layers/block.py:157
↓ 2 callersFunctionget_attn_bias_and_cat
this will perform the index select, cat the tensors, and provide the attn_bias from cache
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/block.py:157
↓ 2 callersFunctionget_attn_bias_and_cat
this will perform the index select, cat the tensors, and provide the attn_bias from cache
baselines/navdp/depth_anything/depth_anything_v2/dinov2_layers/block.py:157
↓ 2 callersFunctionget_attn_bias_and_cat
this will perform the index select, cat the tensors, and provide the attn_bias from cache
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/block.py:157
↓ 2 callersFunctionimagegoal_step
(image_goals,rgb_images,depth_images,port=8888)
utils_tasks/client_utils.py:82
↓ 2 callersMethodinfer_image
(self, raw_image, input_size=518)
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dpt.py:188
↓ 2 callersMethodinfer_image
(self, raw_image, input_size=518)
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dpt.py:188
↓ 2 callersFunctionload_pointnav_policy
Loads a PointNavResNetPolicy policy from a .pth file. Args: file_path (str): The path to the trained weights of the pointnav policy.
baselines/ddppo/pointnav_network.py:119
↓ 2 callersFunctionmake_2tuple
(x)
baselines/logoplanner/depth_anything/depth_anything_v2/dinov2_layers/patch_embed.py:17
↓ 2 callersFunctionmake_2tuple
(x)
baselines/logoplanner/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/patch_embed.py:17
↓ 2 callersFunctionmake_2tuple
(x)
baselines/navdp/depth_anything/depth_anything_v2/dinov2_layers/patch_embed.py:17
↓ 2 callersFunctionmake_2tuple
(x)
baselines/navdp/depth_anything/metric_depth/depth_anything_v2/dinov2_layers/patch_embed.py:17
↓ 2 callersMethodmake_ref_denser
(self, ref_traj, ratio=50)
baselines/logoplanner/deployment/mpc_controller.py:72
↓ 2 callersFunctionnogoal_step
(rgb_images,depth_images,port=8888)
utils_tasks/client_utils.py:20
↓ 2 callersMethodpredict
(self, image: np.ndarray)
baselines/viplanner/m2f_inference.py:30
↓ 2 callersMethodpredict_imagegoal_distance_and_action
(self, image, goal_image)
baselines/gnm/gnm_model.py:275
↓ 2 callersMethodpredict_imagegoal_distance_and_action
(self, image, goal_image)
baselines/vint/vint_network.py:413
↓ 2 callersMethodpredict_nogoal_action
(self, obs_images, goal_img, no_goal_mask, sample_num=8)
baselines/nomad/nomad_model.py:333
↓ 2 callersMethodpredict_pointgoal_action
(self,start_goal,memory_rgbd,context_rgbd,sample_num=16)
baselines/logoplanner/policy_network.py:103
↓ 2 callersMethodprocess_depth
(self,depths)
baselines/logoplanner/policy_agent.py:80
↓ 2 callersMethodprocess_image
Process for image.
baselines/nomad/base_agent.py:37
↓ 2 callersMethodprocess_image
Process for image.
baselines/gnm/base_agent.py:37
↓ 2 callersMethodprocess_image
Process for image.
baselines/vint/base_agent.py:37
↓ 2 callersMethodprocess_image
(self,images)
baselines/logoplanner/policy_agent.py:69
next →1–100 of 736, ranked by callers