Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/EmbodiedGPT/EmbodiedGPT_Pytorch
/ functions
Functions
424 in github.com/EmbodiedGPT/EmbodiedGPT_Pytorch
⨍
Functions
424
◇
Types & classes
107
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None
robohusky/model/modeling_husky.py:951
Method
forward
r""" encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, `optional`): Sequence of
robohusky/model/modeling_husky.py:1118
Method
forward
(self, hidden_states: torch.Tensor)
robohusky/model/modeling_husky.py:1252
Method
forward
( self, pixel_values: torch.FloatTensor, input_ids: torch.FloatTensor,
robohusky/model/modeling_husky.py:1412
Method
forward
( self, pixel_values: torch.FloatTensor, input_ids: torch.FloatTensor,
robohusky/model/modeling_husky.py:1614
Method
forward
(self, pixel_values: torch.FloatTensor)
robohusky/model/modeling_husky_embody2.py:119
Method
forward
(self, pixel_values: torch.FloatTensor)
robohusky/model/modeling_husky_embody2.py:155
Method
forward
Input shape: Batch x Time x Channel
robohusky/model/modeling_husky_embody2.py:202
Method
forward
( self, hidden_states: torch.Tensor, head_mask: Optional[torch.Tensor]
robohusky/model/modeling_husky_embody2.py:257
Method
forward
(self, hidden_states: torch.Tensor)
robohusky/model/modeling_husky_embody2.py:312
Method
forward
Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mas
robohusky/model/modeling_husky_embody2.py:332
Method
forward
r""" Args: inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Embedded
robohusky/model/modeling_husky_embody2.py:546
Method
forward
( self, pixel_values: Optional[torch.FloatTensor] = None, output_attent
robohusky/model/modeling_husky_embody2.py:641
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None
robohusky/model/modeling_husky_embody2.py:743
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None
robohusky/model/modeling_husky_embody2.py:829
Method
forward
(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor)
robohusky/model/modeling_husky_embody2.py:901
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Flo
robohusky/model/modeling_husky_embody2.py:936
Method
forward
(self, hidden_states: torch.Tensor)
robohusky/model/modeling_husky_embody2.py:969
Method
forward
(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor)
robohusky/model/modeling_husky_embody2.py:982
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None
robohusky/model/modeling_husky_embody2.py:1006
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None
robohusky/model/modeling_husky_embody2.py:1096
Method
forward
r""" encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, `optional`): Sequence of
robohusky/model/modeling_husky_embody2.py:1263
Method
forward
(self, hidden_states: torch.Tensor)
robohusky/model/modeling_husky_embody2.py:1393
Method
forward
( self, pixel_values: torch.FloatTensor, input_ids: torch.FloatTensor,
robohusky/model/modeling_husky_embody2.py:1554
Method
forward
( self, pixel_values: Optional[torch.FloatTensor] = None, input_ids: Op
robohusky/model/modeling_husky_embody2.py:1757
Method
forward
(self, pixel_values: torch.FloatTensor)
robohusky/model/modeling_husky_embody2_ori.py:109
Method
forward
(self, pixel_values: torch.FloatTensor)
robohusky/model/modeling_husky_embody2_ori.py:145
Method
forward
Input shape: Batch x Time x Channel
robohusky/model/modeling_husky_embody2_ori.py:192
Method
forward
(self, hidden_states: torch.Tensor)
robohusky/model/modeling_husky_embody2_ori.py:249
Method
forward
Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (
robohusky/model/modeling_husky_embody2_ori.py:265
Method
forward
r""" Args: inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Embedded rep
robohusky/model/modeling_husky_embody2_ori.py:474
Method
forward
( self, pixel_values: Optional[torch.FloatTensor] = None, output_attention
robohusky/model/modeling_husky_embody2_ori.py:569
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None,
robohusky/model/modeling_husky_embody2_ori.py:671
Method
forward
(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor)
robohusky/model/modeling_husky_embody2_ori.py:764
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatT
robohusky/model/modeling_husky_embody2_ori.py:795
Method
forward
(self, hidden_states: torch.Tensor)
robohusky/model/modeling_husky_embody2_ori.py:828
Method
forward
(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor)
robohusky/model/modeling_husky_embody2_ori.py:841
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None,
robohusky/model/modeling_husky_embody2_ori.py:865
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None,
robohusky/model/modeling_husky_embody2_ori.py:955
Method
forward
r""" encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, `optional`): Sequence of h
robohusky/model/modeling_husky_embody2_ori.py:1122
Method
forward
(self, hidden_states: torch.Tensor)
robohusky/model/modeling_husky_embody2_ori.py:1252
Method
forward
( self, pixel_values: torch.FloatTensor, input_ids: torch.FloatTensor,
robohusky/model/modeling_husky_embody2_ori.py:1413
Method
forward
( self, pixel_values: Optional[torch.FloatTensor] = None, input_ids: Optio
robohusky/model/modeling_husky_embody2_ori.py:1616
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
robohusky/configuration_husky.py:217
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
robohusky/model/configuration_husky_ori.py:112
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
robohusky/model/configuration_husky_ori.py:218
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
robohusky/model/configuration_husky.py:222
Method
from_vision_qformer_text_configs
r""" Instantiate a [`HuskyConfig`] (or a derived class) from a Husky vision model, Q-Former and language model configurations.
robohusky/configuration_husky.py:289
Method
from_vision_qformer_text_configs
r""" Instantiate a [`HuskyConfig`] (or a derived class) from a Husky vision model, Q-Former and language model configurations.
robohusky/model/configuration_husky_ori.py:290
Method
from_vision_qformer_text_configs
r""" Instantiate a [`HuskyConfig`] (or a derived class) from a Husky vision model, Q-Former and language model configurations.
robohusky/model/configuration_husky.py:294
Method
generate
Overrides `generate` function to be able to use the model as a conditional generator. Args: pixel_values (`torch.Flo
robohusky/model/modeling_husky_embody2.py:1861
Method
generate
Overrides `generate` function to be able to use the model as a conditional generator. Args: pixel_values (`torch.FloatTe
robohusky/model/modeling_husky_embody2_ori.py:1720
Function
generate_stream
( model, tokenizer, image_processor, params, device )
demo/test.py:185
Function
generate_stream
( model, tokenizer, image_processor, params, device )
demo/inference.py:185
Method
get_attention_map
(self)
robohusky/model/modeling_husky.py:659
Method
get_attention_map
(self)
robohusky/model/modeling_husky_embody2.py:735
Method
get_attention_map
(self)
robohusky/model/modeling_husky_embody2_ori.py:663
Method
get_attn_gradients
(self)
robohusky/model/modeling_husky.py:653
Method
get_attn_gradients
(self)
robohusky/model/modeling_husky_embody2.py:729
Method
get_attn_gradients
(self)
robohusky/model/modeling_husky_embody2_ori.py:657
Method
get_decoder
(self)
robohusky/model/modeling_husky.py:1548
Method
get_decoder
(self)
robohusky/model/modeling_husky_embody2.py:1690
Method
get_decoder
(self)
robohusky/model/modeling_husky_embody2_ori.py:1549
Method
get_encoder
(self)
robohusky/model/modeling_husky.py:1545
Method
get_encoder
(self)
robohusky/model/modeling_husky_embody2.py:1687
Method
get_encoder
(self)
robohusky/model/modeling_husky_embody2_ori.py:1546
Function
get_gpu_memory
Get available memory for each GPU.
robohusky/utils.py:118
Method
get_image_features
( self, pixel_values: Optional[torch.FloatTensor] = None, output_attent
robohusky/model/modeling_husky.py:1343
Method
get_image_features
( self, pixel_values: Optional[torch.FloatTensor] = None, output_attent
robohusky/model/modeling_husky_embody2.py:1485
Method
get_image_features
( self, pixel_values: Optional[torch.FloatTensor] = None, output_attention
robohusky/model/modeling_husky_embody2_ori.py:1344
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky.py:615
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky.py:1059
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky.py:1533
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky_embody2.py:691
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky_embody2.py:1204
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky_embody2.py:1675
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky_embody2_ori.py:619
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky_embody2_ori.py:1063
Method
get_input_embeddings
(self)
robohusky/model/modeling_husky_embody2_ori.py:1534
Function
get_media_type
(image_file)
robohusky/base_dataset_uni.py:76
Method
get_output_embeddings
(self)
robohusky/model/modeling_husky.py:1542
Method
get_output_embeddings
(self)
robohusky/model/modeling_husky_embody2.py:1684
Method
get_output_embeddings
(self)
robohusky/model/modeling_husky_embody2_ori.py:1543
Method
get_qformer_features
r""" Returns: vision_outputs (`BaseModelOutputWithPooling` or tuple of `torch.FloatTensor`): The vision model o
robohusky/model/modeling_husky.py:1366
Method
get_qformer_features
r""" Returns: vision_outputs (`BaseModelOutputWithPooling` or tuple of `torch.FloatTensor`): The vision model o
robohusky/model/modeling_husky_embody2.py:1508
Method
get_qformer_features
r""" Returns: vision_outputs (`BaseModelOutputWithPooling` or tuple of `torch.FloatTensor`): The vision model outp
robohusky/model/modeling_husky_embody2_ori.py:1367
Method
get_text_features
r""" Returns: text_outputs (`CausalLMOutputWithPast`, or `tuple(torch.FloatTensor)` if `return_dict=False`): Th
robohusky/model/modeling_husky.py:1311
Method
get_text_features
r""" Returns: text_outputs (`CausalLMOutputWithPast`, or `tuple(torch.FloatTensor)` if `return_dict=False`): Th
robohusky/model/modeling_husky_embody2.py:1453
Method
get_text_features
r""" Returns: text_outputs (`CausalLMOutputWithPast`, or `tuple(torch.FloatTensor)` if `return_dict=False`): The l
robohusky/model/modeling_husky_embody2_ori.py:1312
Method
get_video_embeddings
(self)
robohusky/model/modeling_husky.py:618
Method
get_video_embeddings
(self)
robohusky/model/modeling_husky_embody2.py:694
Method
get_video_embeddings
(self)
robohusky/model/modeling_husky_embody2_ori.py:622
Function
husky_processor
(examples)
robohusky/train/train.py:511
Function
husky_processor
(examples)
robohusky/train/train_uni.py:510
Function
is_image
(image_file)
robohusky/base_dataset.py:29
Function
is_video
(image_file)
robohusky/base_dataset.py:35
Function
iter_over_async
Convert async generator to sync generator :param async_gen: the AsyncGenerator to convert :param event_loop: the event loop to run o
robohusky/utils.py:199
Function
load_compress_model
(model_path, device, torch_dtype, use_fast=False)
robohusky/compression.py:102
Method
merge_box
(self,dict1,dict2,dict3)
demo/script.py:409
Method
model_input_names
(self)
robohusky/model/processing_husky.py:175
← previous
next →
301–400 of 424, ranked by callers