MCPcopy Create free account

hub / github.com/GuyTevet/CLoSD / functions

Functions2,247 in github.com/GuyTevet/CLoSD

↓ 3 callersMethod_get_pos_ohot
(self, pos)
closd/diffusion_planner/data_loaders/humanml/utils/word_vectorizer.py:53
↓ 3 callersMethod_indent
(self, s)
closd/utils/poselib/poselib/skeleton/skeleton3d.py:113
↓ 3 callersMethod_max
(self, x, y)
closd/utils/poselib/poselib/visualization/plt_plotter.py:252
↓ 3 callersMethod_min
(self, x, y)
closd/utils/poselib/poselib/visualization/plt_plotter.py:245
↓ 3 callersMethod_preproc_obs
(self, obs_batch)
closd/learning/amp_players.py:134
↓ 3 callersFunction_recursive_to_list
Takes some iterable that might contain iterables and converts it to a list of lists [of lists... etc] Mainly used for converting the st
closd/utils/poselib/poselib/skeleton/backend/fbx/fbx_py27_backend.py:286
↓ 3 callersFunction_sqrt_positive_part
Returns torch.sqrt(torch.max(0, x)) but with a zero subgradient where x is 0.
closd/utils/pytorch3d_transforms.py:119
↓ 3 callersMethod_transfer_to
(self, new_skeleton_tree: SkeletonTree)
closd/utils/poselib/poselib/skeleton/skeleton3d.py:651
↓ 3 callersMethod_update_lim
(self, xs, ys)
closd/utils/poselib/poselib/visualization/plt_plotter.py:81
↓ 3 callersMethod_update_lim
(self, xs, ys, zs)
closd/utils/poselib/poselib/visualization/plt_plotter.py:267
↓ 3 callersMethod_vb_terms_bpd
Get a term for the variational lower-bound. The resulting units are bits (rather than nats, as one might expect). This allow
closd/diffusion_planner/diffusion/gaussian_diffusion.py:1324
↓ 3 callersMethodalign_to_recon_data
(self, points, recon_data, is_inverse=False)
closd/utils/rep_util.py:141
↓ 3 callersFunctionarcball_constrain_to_axis
Return sphere point perpendicular to axis.
closd/utils/smpllib/utils/transformation.py:1764
↓ 3 callersFunctionarcball_constrain_to_axis
Return sphere point perpendicular to axis.
closd/utils/smpllib/khrylib/utils/transformation.py:1751
↓ 3 callersFunctionbatch_to
(dst, *args)
closd/utils/smpllib/khrylib/utils/torch.py:86
↓ 3 callersMethodbuild_amp_obs_demo_steps
(self, motion_ids, motion_times0, num_steps)
closd/env/tasks/humanoid_amp.py:214
↓ 3 callersFunctionbuild_amp_observations_smpl
(root_pos, root_rot, root_vel, root_ang_vel, dof_pos, dof_vel, key_body_pos, shape_params, limb_weight_params,
closd/env/tasks/humanoid_amp.py:920
↓ 3 callersMethodclose
(self)
closd/diffusion_planner/train/train_platforms.py:18
↓ 3 callersFunctionconstruct_template_variables
(unconstrained)
closd/diffusion_planner/sample/generate.py:327
↓ 3 callersFunctioncont6d_to_matrix
(cont6d)
closd/diffusion_planner/data_loaders/humanml/common/quaternion.py:322
↓ 3 callersMethodcreate_humanoid_force_sensors
(self, humanoid_asset, sensor_joint_names)
closd/env/tasks/humanoid.py:888
↓ 3 callersFunctionde_heading
(q)
closd/utils/smpllib/utils/math_utils.py:218
↓ 3 callersMethoddiscount_values
(self, mb_fdones, mb_values, mb_rewards, mb_next_values)
closd/learning/common_agent.py:488
↓ 3 callersFunctiondof_to_obs
(pose, dof_obs_size, dof_offsets)
closd/env/tasks/humanoid.py:1432
↓ 3 callersMethoddrop_nodes_by_names
(self, node_names: List[str], pairwise_translation=None)
closd/utils/poselib/poselib/skeleton/skeleton3d.py:213
↓ 3 callersMethodforward
(self, *args, **kwargs)
closd/utils/smpllib/smpllib/smpl_parser.py:336
↓ 3 callersMethodforward
This function should return a distribution to sample action from
closd/utils/smpllib/khrylib/rl/core/policy.py:8
↓ 3 callersMethodforward
(self, batch_data, tf_ratio, mov_len, eval_mode=False)
closd/diffusion_planner/data_loaders/humanml/networks/trainers.py:277
↓ 3 callersMethodforward_motion_samples
(self)
closd/env/tasks/humanoid_im.py:440
↓ 3 callersMethodforward_v_net
(self, x)
closd/utils/smpllib/khrylib/models/video_forecast_net.py:113
↓ 3 callersMethodfrom_mjcf
Parses a mujoco xml scene description file and returns a Skeleton Tree. We use the model attribute at the root as the name of the tre
closd/utils/poselib/poselib/skeleton/skeleton3d.py:149
↓ 3 callersMethodget_asset_options
(self, task)
closd/env/tasks/closd_multitask.py:158
↓ 3 callersFunctionget_color_gradient
(percent, color='Blues')
closd/utils/draw_utils.py:12
↓ 3 callersFunctionget_heading_q
(q)
closd/utils/smpllib/utils/math_utils.py:150
↓ 3 callersFunctionget_heading_q
(q)
closd/utils/smpllib/khrylib/utils/math.py:129
↓ 3 callersFunctionget_heading_q_new
(q)
closd/utils/smpllib/utils/math_utils.py:185
↓ 3 callersMethodget_ids_by_task
(self, env_ids=None)
closd/env/tasks/closd_multitask.py:231
↓ 3 callersMethodget_joints_verts
Pose should be batch_size x 156
closd/utils/smpllib/smpllib/smpl_parser.py:591
↓ 3 callersMethodget_num_actors_per_env
(self)
closd/env/tasks/humanoid.py:491
↓ 3 callersFunctionget_opt
(opt_path, device, hml_type=None)
closd/diffusion_planner/data_loaders/humanml/utils/get_opt.py:29
↓ 3 callersMethodget_params
(self, get_name=False)
closd/utils/smpllib/smpllib/smpl_local_robot.py:2339
↓ 3 callersMethodget_running_mean_size
(self)
closd/env/tasks/humanoid.py:474
↓ 3 callersMethodget_total_count
(self)
closd/learning/replay_buffer.py:24
↓ 3 callersFunctionlink_checkpoints
(src_dir, dst_dir)
closd/utils/hf_handler.py:20
↓ 3 callersMethodload
(self, params)
closd/learning/network_builder.py:457
↓ 3 callersMethodload_from_skeleton
( self, betas=None, v_template=None, gender=[0], objs_info=None,
closd/utils/smpllib/smpllib/smpl_local_robot.py:1279
↓ 3 callersFunctionload_take
()
closd/utils/smpllib/utils/replay_data.py:79
↓ 3 callersMethodlogkv
(self, key, val)
closd/diffusion_planner/diffusion/logger.py:347
↓ 3 callersMethodmap_params
(self, params)
closd/utils/smpllib/smpllib/smpl_local_robot.py:2362
↓ 3 callersMethodmask_cond
(self, cond, force_mask=False)
closd/diffusion_planner/model/mdm.py:156
↓ 3 callersFunctionmy_quat_rotate
(q, v)
closd/utils/torch_utils.py:46
↓ 3 callersFunctionnormalize_smpl_pose
(pose_aa, trans=None, random_root=False)
closd/utils/smpllib/smpllib/smpl_mujoco.py:607
↓ 3 callersMethodnum_motions
(self)
closd/utils/motion_lib_base.py:322
↓ 3 callersFunctionparse_and_load_from_model
(parser)
closd/diffusion_planner/utils/parser_util.py:8
↓ 3 callersMethodplay_steps_rnn
(self)
closd/learning/amp_agent.py:185
↓ 3 callersMethodpose_to_hml
(self, pose, aux_ponts=None, fix_ik_bug=False)
closd/utils/rep_util.py:106
↓ 3 callersFunctionprint_current_loss_decomp
(start_time, niter_state, total_niters, losses, epoch=None, inner_iter=None)
closd/diffusion_planner/data_loaders/humanml/utils/utils.py:65
↓ 3 callersFunctionqbetween_np
find the quaternion used to rotate v0 to v1
closd/diffusion_planner/data_loaders/humanml/common/quaternion.py:402
↓ 3 callersFunctionquat_conjugate
quaternion with its imaginary part negated
closd/utils/poselib/poselib/core/rotation3d.py:60
↓ 3 callersFunctionquat_from_rotation_matrix
Construct a 3D rotation from a valid 3x3 rotation matrices. Reference can be found here: http://www.cg.info.hiroshima-cu.ac.jp/~miyazaki/
closd/utils/poselib/poselib/core/rotation3d.py:147
↓ 3 callersFunctionquaternion_multiply_batch
Multiply quaternion(s) q0 with quaternion(s) q1. Expects two equally-sized tensors of shape (*, 4), where * denotes any number of dimensions.
closd/utils/smpllib/utils/torch_utils.py:408
↓ 3 callersFunctionquaternion_raw_multiply
Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part
closd/utils/pytorch3d_transforms.py:473
↓ 3 callersFunctionquaternion_raw_multiply
Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part
closd/utils/smpllib/utils/rotation_conversions.py:350
↓ 3 callersFunctionquaternion_raw_multiply
Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part
closd/diffusion_planner/utils/rotation_conversions.py:341
↓ 3 callersFunctionquaternion_to_cont6d_np
(quaternions)
closd/diffusion_planner/data_loaders/humanml/common/quaternion.py:310
↓ 3 callersMethodreport_media
(self, title, series, iteration, local_path)
closd/diffusion_planner/train/train_platforms.py:12
↓ 3 callersMethodresample_motions
(self)
closd/env/tasks/humanoid_im.py:339
↓ 3 callersMethodreset_max_len
(self, length)
closd/diffusion_planner/data_loaders/humanml/data/dataset.py:313
↓ 3 callersMethodretarget_to
Retarget the skeleton state to a target skeleton tree. This is a naive retarget implementation with rough approximations. The functi
closd/utils/poselib/poselib/skeleton/skeleton3d.py:717
↓ 3 callersFunctionrotation_from_quaternion
(quaternion, separate=False)
closd/utils/smpllib/khrylib/utils/transformation.py:362
↓ 3 callersMethodsample
(self, n)
closd/learning/replay_buffer.py:51
↓ 3 callersFunctionsample_goal
(batch_size, device, force_joints=None)
closd/diffusion_planner/data_loaders/humanml/scripts/motion_process.py:642
↓ 3 callersMethodsample_time
(self, motion_ids, truncate_time=None)
closd/utils/motion_lib_base.py:397
↓ 3 callersMethodsave
(self, file_name, ep, total_it)
closd/diffusion_planner/data_loaders/humanml/networks/trainers.py:94
↓ 3 callersFunctionsave_multiple_samples
(out_path, file_templates, animations, fps, max_frames, no_dir=False)
closd/diffusion_planner/sample/generate.py:299
↓ 3 callersMethodset_random_target_loc
(self, env_ids, task)
closd/env/tasks/closd_multitask.py:350
↓ 3 callersMethodset_state
(self, qpos, qvel)
closd/utils/smpllib/khrylib/rl/envs/common/mujoco_env.py:106
↓ 3 callersFunctionsmplh_to_smpl
(pose)
closd/utils/smpllib/smpllib/smpl_mujoco.py:321
↓ 3 callersMethodstore
(self, data_dict)
closd/learning/replay_buffer.py:27
↓ 3 callersMethodto_dict
(self)
closd/utils/poselib/poselib/skeleton/skeleton3d.py:141
↓ 3 callersFunctionto_torch
(tensor)
closd/utils/smpllib/utils/torch_ext.py:185
↓ 3 callersMethodtrans_value
transform states before going into value net
closd/utils/smpllib/khrylib/rl/agents/agent.py:137
↓ 3 callersFunctiontransform_mul
Combine two transformation together
closd/utils/poselib/poselib/core/rotation3d.py:318
↓ 3 callersMethodupdate_value
update critic
closd/utils/smpllib/khrylib/rl/agents/agent_pg.py:18
↓ 3 callersMethodupdate_values_dict
(self, values_dict, rnn_format = False, horizon_length = 1, num_envs = 1)
closd/learning/amp_datasets.py:36
↓ 2 callersMethod__getattr__
(self, name, default=None)
closd/diffusion_planner/utils/sampler_util.py:33
↓ 2 callersMethod__init__
SMPL model constructor Parameters ---------- model_path: str The path to the folder or to the file where the model
closd/utils/smpllib/smpllib/smpl_parser.py:260
↓ 2 callersMethod__init__
(self, chomp_size)
closd/utils/smpllib/khrylib/models/tcn.py:7
↓ 2 callersMethod__init__
(self, task, rl_device, sync_frame_time=False, clip_observations=5.0)
closd/env/tasks/vec_task_wrappers.py:35
↓ 2 callersMethod__init__
(self, task, rl_device, clip_observations=5.0)
closd/env/tasks/vec_task.py:40
↓ 2 callersMethod_actor_loss
(self, old_action_log_probs_batch, action_log_probs, advantage, curr_e_clip)
closd/learning/common_agent.py:559
↓ 2 callersMethod_amp_debug
(self, info)
closd/learning/amp_agent.py:996
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
closd/utils/pytorch3d_transforms.py:327
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
closd/utils/smpllib/utils/rotation_conversions.py:204
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
closd/diffusion_planner/utils/rotation_conversions.py:176
↓ 2 callersMethod_build_cnn2d
(self, input_shape, convs, activation, conv_func=torch.nn.Conv2d, norm_func_name=None)
closd/learning/network_builder.py:145
↓ 2 callersMethod_build_conv
(self, ctype, **kwargs)
closd/learning/network_builder.py:135
↓ 2 callersMethod_build_critic
(self, output_dim, **mlp_args)
closd/learning/network_builder.py:861
↓ 2 callersMethod_calc_frame_blend
(self, time, len, num_frames, dt)
closd/utils/motion_lib_base.py:543
↓ 2 callersMethod_calc_input_size
(self, input_shape, cnn_layers=None)
closd/learning/network_builder.py:80
← previousnext →201–300 of 2,247, ranked by callers