Functions — github.com/csuhan/OneLLM

CodeHub MCPcopy Create free account

hub / github.com/csuhan/OneLLM / functions

Functions248 in github.com/csuhan/OneLLM

⨍ Functions 248◇ Types & classes 55 ↳ Endpoints 1

:param xyz: (B, N, 3) tensor of the xyz coordinates of the features :param features: (B, N, C) tensor of the descriptors of the the f

model/lib/pointnet2/pointnet2_modules.py:19

:param unknown: (B, n, 3) tensor of the xyz positions of the unknown features :param known: (B, m, 3) tensor of the xyz positions of

model/lib/pointnet2/pointnet2_modules.py:127

(self, x: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor], prompt=None)

model/LLM/onellm.py:112

model/LLM/onellm.py:176

(self, x: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor], prompt=None)

model/LLM/onellm.py:200

(self, examples, image=None, modal='image')

model/LLM/onellm.py:421

data/data_utils.py:30

(self, tensors)

data/data_utils.py:41

Args: videos: A list of C, T, H, W videos. Returns: videos: A list with 3x the number of elements. Each video

data/video_utils.py:123

Functionfurthest_point_sampling_wrapper

model/lib/pointnet2/src/sampling.cpp:35

Functiongather_points_grad_wrapper_fast

model/lib/pointnet2/src/sampling.cpp:22

Functiongather_points_wrapper_fast

model/lib/pointnet2/src/sampling.cpp:10

Functionget_2d_sincos_pos_embed

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/

util/pos_embed.py:19

Methodget_image_words

model/meta.py:174

Functionget_signal_frames

Given a signal track return the frames between video_start_sec and video_end_sec

data/imu_utils.py:83

Methodglobal_avg

util/misc.py:81

Functiongroup_points_grad_wrapper_fast

model/lib/pointnet2/src/group_points.cpp:11

Functiongroup_points_wrapper_fast

model/lib/pointnet2/src/group_points.cpp:24

Functionindex_narrations

data/imu_utils.py:33

Functioninit_distributed_mode

util/misc.py:230

Functioninit_distributed_mode1

util/misc.py:275

Functioninterpolate_pos_embed

(model, checkpoint_model)

util/pos_embed.py:74

Functioninterpolate_pos_embed_online

( pos_embed, orig_size, new_size, num_extra_tokens: int )

util/pos_embed.py:98

Methodload_audio

data/finetune_dataset.py:209

Methodload_fmri

data/finetune_dataset.py:239

Methodload_image

data/finetune_dataset.py:203

(self, data_dict)

data/finetune_dataset.py:246

Functionload_model

(args, model, optimizer, loss_scaler)

util/misc.py:408

Methodload_point

data/finetune_dataset.py:221

Methodload_rgbx

data/finetune_dataset.py:227

Methodload_rgbx_from_ceph

(self, image_path)

data/pretrain_dataset.py:182

Methodload_trans_image

(self, image_path)

data/pretrain_dataset.py:128

Methodload_video

(self, video_path)

data/pretrain_dataset.py:148

Methodload_video

data/finetune_dataset.py:215

util/misc.py:71

Functionmodel_worker

The worker function that manipulates the GPU to run the inference. Exact n_gpu workers are started, with each one operating on a separate GPU

demos/multi_turn_mm.py:43

Functionopt_n_threads

model/lib/pointnet2/src/cuda_utils.h:10

Functionsave_model

(output_dir, args, epoch, iteration, model, optimizer, loss_scaler, dataset_state)

util/misc.py:358

Functionsave_on_master

(*args, **kwargs)

util/misc.py:226

Functionshow_user_input

demos/multi_turn_mm.py:162

Functionstream_model_output

(img_path, audio_path, video_path, chatbot, max_gen_len, gen_t, top_p, modality)

demos/multi_turn_mm.py:165

Methodsynchronize_between_processes

Warning: does not synchronize the deque!

util/misc.py:57

Functionthree_interpolate_grad_wrapper_fast

model/lib/pointnet2/src/interpolate.cpp:40

Functionthree_interpolate_wrapper_fast

model/lib/pointnet2/src/interpolate.cpp:25

Functionthree_nn_wrapper_fast

model/lib/pointnet2/src/interpolate.cpp:13

Methodto_gradio_chatbot

data/conversation_lib.py:115

demos/multi_turn_mm.py:175

util/misc.py:89

← previous201–248 of 248, ranked by callers