MCPcopy Create free account

hub / github.com/CIawevy/TextPecker / functions

Functions1,395 in github.com/CIawevy/TextPecker

⨍ Functions 1,395◇ Types & classes 206↳ Endpoints 2
↓ 1 callersFunctionget_equalizer
(text: str,tokenizer)
eval/TextCrafter/TextCrafter_Flux/utils.py:144
↓ 1 callersFunctionget_equalizer
(text: str,tokenizer)
eval/TextCrafter/TextCrafter_SD3/utils.py:144
↓ 1 callersFunctionget_first_quote_inds
(text: str, tokenizer)
eval/TextCrafter/TextCrafter_Flux/utils.py:340
↓ 1 callersFunctionget_first_quote_inds
(text: str, tokenizer)
eval/TextCrafter/TextCrafter_SD3/utils.py:343
↓ 1 callersFunctionget_gned_score
(rec_text,ref_target,cls=False)
eval/TextPecker_eval/parse_utils_pecker.py:452
↓ 1 callersFunctionget_gned_score
(rec_text,ref_target,cls=False)
RL/flow_grpo/flow_grpo/parse_utils_pecker.py:452
↓ 1 callersFunctionget_image_transform
(processor:AutoImageProcessor)
RL/flow_grpo/flow_grpo/clip_scorer.py:22
↓ 1 callersMethodget_input_embeddings
(self)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:1087
↓ 1 callersMethodget_ld
Calculate normalized version of Levenshtein distance
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:132
↓ 1 callersMethodget_pooling
(self, features, last_hidden_states)
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:236
↓ 1 callersFunctionget_quote_inds
(text: str, tokenizer)
eval/TextCrafter/TextCrafter_Flux/utils.py:312
↓ 1 callersFunctionget_quote_inds
(text: str, tokenizer)
eval/TextCrafter/TextCrafter_SD3/utils.py:313
↓ 1 callersFunctionget_rec_template
Creates the prompt for the Recognition task
eval/TextPecker_eval/textpecker_eval_server.py:255
↓ 1 callersFunctionget_scaled_quality_score
(rec_text, amplify_factor=1.0)
eval/TextPecker_eval/parse_utils_pecker.py:477
↓ 1 callersFunctionget_scaled_quality_score
(rec_text, amplify_factor=1.0)
RL/flow_grpo/flow_grpo/parse_utils_pecker.py:477
↓ 1 callersFunctionget_siglip_config
(model_name)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/convert_siglip_to_hf.py:55
↓ 1 callersFunctionget_sigmas
(noise_scheduler, timesteps, accelerator, n_dim=4, dtype=torch.float32)
RL/flow_grpo/scripts/train_sd3_sft.py:181
↓ 1 callersFunctionget_sigmas
(noise_scheduler, timesteps, accelerator, n_dim=4, dtype=torch.float32)
RL/flow_grpo/scripts/train_sd3_dpo.py:179
↓ 1 callersMethodget_spm_processor
(self)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/tokenization_siglip.py:126
↓ 1 callersMethodget_style_embedding
(self, image_path: str)
eval/OneIG-Benchmark/scripts/utils/inference.py:121
↓ 1 callersMethodget_style_embedding
(self, image_path: str)
eval/OneIG-Benchmark/scripts/utils/inference.py:141
↓ 1 callersFunctionget_word_inds
(text: str, word: str, tokenizer)
eval/TextCrafter/TextCrafter_Flux/utils.py:330
↓ 1 callersFunctionget_word_inds
(text: str, word: str, tokenizer)
eval/TextCrafter/TextCrafter_SD3/utils.py:332
↓ 1 callersFunctionhandle_prompt_based_metric
(key)
eval/OneIG-Benchmark/fine_grained_analysis.py:66
↓ 1 callersFunctionhandle_text
()
eval/OneIG-Benchmark/fine_grained_analysis.py:128
↓ 1 callersMethodimage_similarity
(self, pixels, ref_pixels)
RL/flow_grpo/flow_grpo/clip_scorer.py:56
↓ 1 callersFunctionimg_similar_score
(image_1_path, image_2_path)
eval/OneIG-Benchmark/scripts/diversity/diversity_score.py:23
↓ 1 callersMethodinfer_ocr
(self, images_path: list, max_new_tokens: int = 128)
eval/OneIG-Benchmark/scripts/utils/inference.py:82
↓ 1 callersMethodinfer_semantic
(self, images_path: list, question: str)
eval/OneIG-Benchmark/scripts/utils/inference.py:68
↓ 1 callersFunctioninference
( prompt, carrier_list, sentence_list, min_area=None, pre_generat
eval/TextCrafter/TextCrafter_Flux/eval.py:17
↓ 1 callersFunctioninference
( prompt, sentence_list, insulation_steps=10, num_inference_steps=30, # S
eval/TextCrafter/TextCrafter_Flux/eval_creativebench.py:17
↓ 1 callersFunctioninit_forwards
(self, root_module: torch.nn.Module)
eval/TextCrafter/TextCrafter_Flux/init.py:3
↓ 1 callersFunctioninit_forwards
(self, root_module: torch.nn.Module)
eval/TextCrafter/TextCrafter_SD3/init.py:3
↓ 1 callersMethodinit_gen_context
(self)
RL/flow_grpo/flow_grpo/bagel/inferencer.py:31
↓ 1 callersMethodinsulation_encode_prompt
( self, sentence_list: Union[List[str]], device: Optional[torch.device]
eval/TextCrafter/TextCrafter_Flux/textcrafter_pipeline_flux.py:408
↓ 1 callersMethodinsulation_encode_prompt
( self, sentence_list: Union[List[str]], device: Optional[torch.device]
eval/TextCrafter/TextCrafter_SD3/textcrafter_pipeline_sd3.py:571
↓ 1 callersMethodinsulation_replace_latents
( self, latents, insulation_latents_list, insulation_m_off
eval/TextCrafter/TextCrafter_Flux/textcrafter_pipeline_flux.py:695
↓ 1 callersMethodinsulation_replace_latents
( self, latents, insulation_latents_list, insulation_m_off
eval/TextCrafter/TextCrafter_SD3/textcrafter_pipeline_sd3.py:830
↓ 1 callersMethodinterleave_inference
( self, input_lists: List[Union[str, Image.Image]], think=False, understanding
RL/flow_grpo/flow_grpo/bagel/inferencer.py:258
↓ 1 callersMethodinterpolate_pos_encoding
This method allows to interpolate the pre-trained position encodings, to be able to use the model on higher resolution images. This m
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:260
↓ 1 callersFunctionis_chinese
(char)
eval/TextPecker_eval/parse_utils_pecker.py:107
↓ 1 callersFunctionis_chinese
(char)
RL/flow_grpo/flow_grpo/parse_utils_pecker.py:107
↓ 1 callersFunctionis_english_text
判断文本是否为纯英文（全英文返回True，含任何中文字符返回False）
train/get_metrics_for_tsap_and_ctr.py:183
↓ 1 callersFunctionis_transformers_attn_greater_or_equal_4_38
()
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/models/bidirectional_llama.py:28
↓ 1 callersFunctionis_transformers_attn_greater_or_equal_4_40
()
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/models/bidirectional_llama.py:37
↓ 1 callersFunctionjpeg_incompressibility
()
RL/flow_grpo/flow_grpo/rewards.py:10
↓ 1 callersFunctionlecun_normal_
(tensor)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:133
↓ 1 callersFunctionlevenshtein_distance
(s1, s2)
eval/OneIG-Benchmark/scripts/text/text_utils.py:25
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/SD3.5/infer_sd3_LeX.py:30
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/SD3.5/infer_sd3_oneig.py:30
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/SD3.5/infer_sd3_CVTG2K.py:19
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/SD3.5/infer_sd3_TextAtlasEval.py:30
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Qwenimage/infer_qwenimage_TextAtlasEval.py:130
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Qwenimage/infer_qwenimage_CVTG2K.py:143
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Qwenimage/infer_qwenimage_oneig.py:144
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Qwenimage/infer_qwenimage_LeX.py:145
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Flux/infer_flux_dev_LeX.py:20
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Flux/infer_flux_dev_TextAtlasEval.py:20
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Flux/infer_flux_dev_oneig.py:31
↓ 1 callersFunctionload_json
加载指定路径的 JSON 文件并将其内容解析为 Python 对象。 :param file_path: 要加载的 JSON 文件的路径 :return: 解析后的 Python 对象，如果出现错误则返回 None
eval/models/Flux/infer_flux_dev_CVTG2K.py:31
↓ 1 callersFunctionload_jsonl
加载JSON Lines格式的文件 参数: file_path: str - JSON Lines文件的路径 encoding: str - 文件编码，默认为'utf-8' 返回: list - 包含文件中
eval/TextPecker_eval/textpecker_eval_server.py:82
↓ 1 callersFunctionload_jsonl
Load data from a JSONL file
eval/TextPecker_eval/metric_summary.py:24
↓ 1 callersFunctionload_jsonl
加载JSON Lines格式的文件 参数: file_path: str - JSON Lines文件的路径 encoding: str - 文件编码，默认为'utf-8' 返回: list - 包含文件中
eval/models/SD3.5/infer_sd3_TIIF.py:30
↓ 1 callersFunctionload_jsonl
加载JSON Lines格式的文件 参数: file_path: str - JSON Lines文件的路径 encoding: str - 文件编码，默认为'utf-8' 返回: list - 包含文件中
eval/models/Qwenimage/infer_qwenimage_TIIF.py:37
↓ 1 callersFunctionload_jsonl
加载JSON Lines格式的文件 参数: file_path: str - JSON Lines文件的路径 encoding: str - 文件编码，默认为'utf-8' 返回: list - 包含文件中
eval/models/Flux/infer_flux_dev_TIIF.py:40
↓ 1 callersFunctionload_jsonl_lines
读取 jsonl 文件，每行 parse 成 json 对象，返回列表
eval/TIIF-Bench/eval/eval_with_vlm.py:58
↓ 1 callersFunctionload_model
(local_rank, model_path, lora_path=None)
eval/models/SD3.5/infer_sd3_LeX.py:104
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/SD3.5/infer_sd3_gentexteval.py:120
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/SD3.5/infer_sd3_oneig.py:115
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/SD3.5/infer_sd3_CVTG2K.py:102
↓ 1 callersFunctionload_model
(local_rank, model_path, lora_path=None)
eval/models/SD3.5/infer_sd3_TextAtlasEval.py:104
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/SD3.5/infer_sd3_longtext.py:120
↓ 1 callersFunctionload_model
(local_rank, model_path, lora_path=None)
eval/models/SD3.5/infer_sd3_TIIF.py:124
↓ 1 callersFunctionload_model
(local_rank, model_path, ckpt_path=None,use_lora=True)
eval/models/Qwenimage/infer_qwenimage_TextAtlasEval.py:38
↓ 1 callersFunctionload_model
(local_rank, model_path, ckpt_path=None,use_lora=True)
eval/models/Qwenimage/infer_qwenimage_CVTG2K.py:52
↓ 1 callersFunctionload_model
(local_rank, model_path, ckpt_path=None,use_lora=True)
eval/models/Qwenimage/infer_qwenimage_TIIF.py:77
↓ 1 callersFunctionload_model
(local_rank, model_path, ckpt_path=None,use_lora=True)
eval/models/Qwenimage/infer_qwenimage_oneig.py:52
↓ 1 callersFunctionload_model
(local_rank, model_path, ckpt_path=None,use_lora=True)
eval/models/Qwenimage/infer_qwenimage_gentexteval.py:52
↓ 1 callersFunctionload_model
(local_rank, model_path, ckpt_path=None,use_lora=True)
eval/models/Qwenimage/infer_qwenimage_longtext.py:51
↓ 1 callersFunctionload_model
(local_rank, model_path, ckpt_path=None,use_lora=True)
eval/models/Qwenimage/infer_qwenimage_LeX.py:53
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/Flux/infer_flux_dev_TIIF.py:134
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/Flux/infer_flux_dev_longtext.py:108
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/Flux/infer_flux_dev_LeX.py:92
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/Flux/infer_flux_dev_TextAtlasEval.py:93
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/Flux/infer_flux_dev_gentexteval.py:96
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/Flux/infer_flux_dev_oneig.py:104
↓ 1 callersFunctionload_model
(local_rank, model_path,lora_path=None)
eval/models/Flux/infer_flux_dev_CVTG2K.py:100
↓ 1 callersFunctionmain
(args)
eval/TIIF-Bench/eval/eval_with_vlm.py:177
↓ 1 callersFunctionmain
()
eval/TIIF-Bench/eval/summary_dimension_results.py:5
↓ 1 callersFunctionmain
()
eval/TIIF-Bench/eval/summary_results.py:44
↓ 1 callersFunctionmain
()
eval/TIIF-Bench/eval/inference_t2i_models.py:237
↓ 1 callersFunctionmain
()
eval/TextPecker_eval/textpecker_eval_server.py:1251
↓ 1 callersFunctionmain
()
eval/TextPecker_eval/metric_summary.py:73
↓ 1 callersFunctionmain
Main function to run the test. This simulates the call from the reward function.
eval/TextPecker_eval/demo.py:141
↓ 1 callersFunctionmain
()
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:517
↓ 1 callersFunctionmain
(args)
eval/X-Omni/chat.py:7
↓ 1 callersFunctionmain
(args)
eval/X-Omni/generate.py:8
↓ 1 callersFunctionmain
(args)
eval/X-Omni/textbench/evaluate_text_reward.py:86
↓ 1 callersFunctionmain
()
eval/models/SD3.5/infer_sd3_LeX.py:142
↓ 1 callersFunctionmain
()
eval/models/SD3.5/infer_sd3_gentexteval.py:158
← previousnext →401–500 of 1,395, ranked by callers