Types & classes — github.com/bytedance/GR-MG

CodeHub MCPcopy Create free account

hub / github.com/bytedance/GR-MG / types & classes

Types & classes30 in github.com/bytedance/GR-MG

⨍ Functions 177◇ Types & classes 30 ↳ Endpoints 1

↓ 5 callersClassBlock

policy/model/vision_transformer.py:184

↓ 4 callersClassCalvinDataset_Goalgen

goal_gen/data/calvindataset.py:27

↓ 3 callersClassCalvinDataset_Policy

policy/data/calvin_dataset.py:80

↓ 3 callersClassEgo4DDataset_Policy

policy/data/ego4d_dataset.py:84

↓ 3 callersClassVisionTransformer

Vision Transformer

policy/model/vision_transformer.py:223

↓ 2 callersClassGPT2Attention

policy/model/gpt2.py:123

↓ 2 callersClassGR_MG

policy/model/model.py:33

↓ 2 callersClassIP2P

InstructPix2Pix model.

goal_gen/model/model.py:23

↓ 2 callersClassIP2PEvaluation

goal_gen/evaluate.py:25

↓ 2 callersClassRandomShiftsSingleAug

policy/data/calvin_dataset.py:54

↓ 1 callersClassAttention

policy/model/vision_transformer.py:157

↓ 1 callersClassCalvinEnvWrapperRaw

evaluate/wrapper/calvin_env_wrapper_raw.py:33

↓ 1 callersClassCustomModel

evaluate/wrapper/model_wrapper.py:29

↓ 1 callersClassDropPath

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

policy/model/vision_transformer.py:127

↓ 1 callersClassGPT2Block

policy/model/gpt2.py:361

↓ 1 callersClassGPT2MLP

policy/model/gpt2.py:344

↓ 1 callersClassGPT2Model

policy/model/gpt2.py:669

↓ 1 callersClassGoalgen_Trainer

goal_gen/training/trainer.py:20

↓ 1 callersClassMlp

policy/model/vision_transformer.py:138

↓ 1 callersClassPatchEmbed

Image to Patch Embedding

policy/model/vision_transformer.py:205

↓ 1 callersClassPolicy_Trainer

policy/training/trainer.py:56

↓ 1 callersClassRandomShiftsSingleAug

policy/data/ego4d_dataset.py:59

↓ 1 callersClassSetupCallback

policy/main.py:45

↓ 1 callersClassSetupCallback

goal_gen/utils/utils.py:20

policy/model/vision_transformer.py:346

ClassGPT2DoubleHeadsModelOutput

Base class for outputs of models predicting if two sentences are consecutive or not. Args: loss (`torch.FloatTensor` of shape `(1,)`

policy/model/gpt2.py:489

ClassGPT2PreTrainedModel

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

policy/model/gpt2.py:439

goal_gen/utils/pipeline.py:35

ClassRandomShiftsAug

policy/data/ego4d_dataset.py:36

ClassRandomShiftsAug

policy/data/calvin_dataset.py:30