Functions — github.com/devinxzhang/MFuser

CodeHub MCPcopy Create free account

hub / github.com/devinxzhang/MFuser / functions

Functions1,143 in github.com/devinxzhang/MFuser

⨍ Functions 1,143◇ Types & classes 269

(self, cont_img, styl_img, cont_seg, styl_seg)

mmseg/models/uda/photo_wct_batch.py:73

mmseg/models/uda/vgg.py:76

(self, x, pool1_idx=None, pool1_size=None, pool2_idx=None, pool2_size=None, pool3_idx=None, po

mmseg/models/uda/vgg.py:251

models/backbones/dino_v2.py:49

(self, *args, **kwargs)

models/backbones/dino_v2.py:330

(self, x: torch.Tensor)

models/backbones/clip/models.py:19

(self, x: torch.Tensor)

models/backbones/clip/models.py:26

(self, x: torch.Tensor, H=None, W=None)

models/backbones/clip/models.py:63

(self, x: torch.Tensor)

models/backbones/clip/models.py:77

(self, q, k, v)

models/backbones/clip/models.py:98

(self, x, visual)

models/backbones/clip/models.py:139

(self, x: torch.Tensor, use_adapter=True)

models/backbones/clip/models.py:304

models/backbones/clip/models.py:424

(self, text, context=None)

models/backbones/clip/models.py:496

(self, text, visual)

models/backbones/clip/models.py:580

(self, pixel_values: torch.FloatTensor, interpolate_pos_encoding=False)

models/backbones/siglip/modeling_siglip.py:401

( self, input_ids: Optional[torch.LongTensor] = None, position_ids: Optional[torch.Lon

models/backbones/siglip/modeling_siglip.py:426

Input shape: Batch x Time x Channel

models/backbones/siglip/modeling_siglip.py:488

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.LongTensor] = None

models/backbones/siglip/modeling_siglip.py:555

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None,

models/backbones/siglip/modeling_siglip.py:621

( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor, output_atte

models/backbones/siglip/modeling_siglip.py:700

( self, inputs_embeds, attention_mask: Optional[torch.Tensor] = None, output_a

models/backbones/siglip/modeling_siglip.py:738

( self, input_ids: Optional[torch.Tensor] = None, attention_mask: Optional[torch.Tenso

models/backbones/siglip/modeling_siglip.py:834

( self, pixel_values, output_attentions: Optional[bool] = None, output_hidden_

models/backbones/siglip/modeling_siglip.py:1001

(self, hidden_state)

models/backbones/siglip/modeling_siglip.py:1078

models/backbones/dino_layers/drop_path.py:33

(self, x_or_x_list)

models/backbones/dino_layers/block.py:252

models/backbones/dino_layers/dino_head.py:36

(self, x: Tensor)

models/backbones/dino_layers/layer_scale.py:26

(self, x: Tensor, attn_bias=None)

models/backbones/dino_layers/attention.py:73

(self, x: Tensor)

models/backbones/dino_layers/mlp.py:34

(self, x: Tensor)

models/backbones/dino_layers/swiglu_ffn.py:30

(self, x: Tensor)

models/backbones/dino_layers/patch_embed.py:68

(self, image_features, text_features, logit_scale=1.)

models/backbones/eva_clip/loss.py:95

(self, t, start_index = 0)

models/backbones/eva_clip/rope.py:70

(self, t, patch_indices_keep=None)

models/backbones/eva_clip/rope.py:124

(ctx, tensor, rank, world_size)

models/backbones/eva_clip/utils.py:311

(self, x: torch.Tensor)

models/backbones/eva_clip/modified_resnet.py:42

models/backbones/eva_clip/modified_resnet.py:68

models/backbones/eva_clip/modified_resnet.py:173

hidden_states: (B, L, D) Returns: same shape as hidden_states

models/backbones/eva_clip/adapter_module.py:147

models/backbones/eva_clip/transform.py:24

models/backbones/eva_clip/timm_model.py:119

(self, x:BaseModelOutput, attention_mask:TensorType)

models/backbones/eva_clip/hf_model.py:46

(self, x:BaseModelOutput, attention_mask:TensorType)

models/backbones/eva_clip/hf_model.py:53

(self, x:BaseModelOutput, attention_mask:TensorType)

models/backbones/eva_clip/hf_model.py:65

(self, x:TensorType)

models/backbones/eva_clip/hf_model.py:213

(self, x: torch.Tensor)

models/backbones/eva_clip/transformer.py:45

(self, x: torch.Tensor)

models/backbones/eva_clip/transformer.py:59

(self, x: torch.Tensor)

models/backbones/eva_clip/transformer.py:66

models/backbones/eva_clip/transformer.py:76

models/backbones/eva_clip/transformer.py:91

(self, x, attn_mask: Optional[torch.Tensor] = None)

models/backbones/eva_clip/transformer.py:199

(self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, attn_mask: Optional[torch.Tensor] = None)

models/backbones/eva_clip/transformer.py:290

(self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, attn_mask: Optional[torch.Tensor] = None)

models/backbones/eva_clip/transformer.py:388

(self, q: torch.Tensor, k: torch.Tensor = None, v: torch.Tensor = None, attn_mask: Optional[torch.Tensor] = No

models/backbones/eva_clip/transformer.py:436

(self, x: torch.Tensor, attn_mask: Optional[torch.Tensor] = None)

models/backbones/eva_clip/transformer.py:484

(self, x: torch.Tensor, attn_mask: Optional[torch.Tensor] = None)

models/backbones/eva_clip/transformer.py:515

(self, x: torch.Tensor, return_all_features: bool=False)

models/backbones/eva_clip/transformer.py:615

(self, text, context=None, return_all_features: bool=False)

models/backbones/eva_clip/transformer.py:728

models/backbones/eva_clip/eva_vit_model.py:45

models/backbones/eva_clip/eva_vit_model.py:74

models/backbones/eva_clip/eva_vit_model.py:101

(self, x, rel_pos_bias=None, attn_mask=None)

models/backbones/eva_clip/eva_vit_model.py:177

(self, x, rel_pos_bias=None, attn_mask=None)

models/backbones/eva_clip/eva_vit_model.py:290

(self, x, **kwargs)

models/backbones/eva_clip/eva_vit_model.py:322

models/backbones/eva_clip/eva_vit_model.py:362

(self, x, return_all_features=False)

models/backbones/eva_clip/eva_vit_model.py:590

(self, image, text)

models/backbones/eva_clip/model.py:269

(self, image, text)

models/backbones/eva_clip/model.py:314

Methodforward_dummy

Dummy forward function.

mmseg/models/segmentors/encoder_decoder.py:133

Methodforward_feats

Args: feats (list[Tensor]): Feature maps of each level. Each has shape of (batch_size, c, h, w). Returns

mmseg/models/plugins/tqdm_msdeformattn_pixel_decoder.py:284

Methodforward_inference

(self, inputs, img_metas, test_cfg)

mmseg/models/decode_heads/mask2former_head.py:594

Methodforward_inference

(self, inputs, texts, img_metas, test_cfg)

mmseg/models/decode_heads/tqdm_head.py:562

Methodforward_mask_features

(self, inputs, img_metas, test_cfg)

mmseg/models/decode_heads/mask2former_head.py:599

Methodforward_mlm

(self, input_ids, image_embeds, mlm_probability=0.25)

models/backbones/eva_clip/hf_model.py:177

Methodforward_test

Forward function for testing. Args: inputs (list[Tensor]): List of multi-level img features. img_metas (list[dict]):

mmseg/models/decode_heads/decode_head.py:196

Methodforward_test

Test segment without test-time aumengtation. Only the output of last decoder layers was used. Args: inputs (list[Tensor]

mmseg/models/decode_heads/mask2former_head.py:569

Methodforward_test

Test segment without test-time aumengtation. Only the output of last decoder layers was used. Args: inputs (list[Tensor]

mmseg/models/decode_heads/maskformer_head.py:497

Methodforward_test

Test segment without test-time aumengtation. Only the output of last decoder layers was used. Args: inputs (list[Tensor]

mmseg/models/decode_heads/tqdm_head.py:538

Methodforward_train

Forward function for training. Args: inputs (list[Tensor]): List of multi-level img features. img_metas (list[dict]):

mmseg/models/decode_heads/decode_head.py:171

Methodforward_train

(self, inputs, img_metas, gt_semantic_seg, train_cfg)

mmseg/models/decode_heads/maskclip_head.py:163

Methodforward_train

Forward function for training mode. Args: x (list[Tensor]): Multi-level features from the upstream network, each

mmseg/models/decode_heads/mask2former_head.py:539

Methodforward_train

Forward function for training mode. Args: x (list[Tensor]): Multi-level features from the upstream network, each

mmseg/models/decode_heads/maskformer_head.py:463

Methodforward_train

Forward function for training mode. Args: x (list[Tensor]): Multi-level features from the upstream network, each

mmseg/models/decode_heads/tqdm_head.py:508

Methodforward_train

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict where

mmseg/models/uda/baseline.py:205

Methodforward_train

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

mmseg/models/uda/uda_decorator.py:46

Methodforward_train

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

mmseg/models/uda/dacs.py:184

Methodforward_train

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict where

mmseg/models/uda/stylization.py:205

Methodforward_train

(self, img, img_metas, gt_semantic_seg, **kwargs)

models/segmentors/mfuser_eva_clip.py:111

Methodforward_train

(self, img, img_metas, gt_semantic_seg, **kwargs)

models/segmentors/mfuser_clip.py:111

Methodforward_train

(self, img, img_metas, gt_semantic_seg, **kwargs)

models/segmentors/mfuser_siglip.py:111

Methodfrom_pretrained

(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)

models/backbones/siglip/configuration_siglip.py:210

Methodfrom_text_vision_configs

r""" Instantiate a [`SiglipConfig`] (or a derived class) from siglip text model configuration and siglip vision model configuration.

models/backbones/siglip/configuration_siglip.py:289

Functiongen_code_archive

(out_dir, file='code.tar.gz')

mmseg/utils/collect_env.py:30

Methodget_added_vocab

Returns the added tokens in the vocabulary as a dictionary of token to index. Results might be different from the fast call because f

models/backbones/siglip/tokenization_utils.py:488

Methodget_cast_dtype

models/backbones/eva_clip/transformer.py:433

Methodget_cast_dtype

models/backbones/eva_clip/eva_vit_model.py:518

Functionget_classes

Get class names of a dataset.

mmseg/core/evaluation/class_names.py:123

Methodget_classifier

mmseg/models/backbones/mix_transformer.py:387

← previous next →901–1,000 of 1,143, ranked by callers