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
↓ 2 callersFunctionregister_recr
(net_, count, place_in_transformer)
eval/TextCrafter/TextCrafter_Flux/utils.py:293
↓ 2 callersMethodremove_punctuation
(self, text: str)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/tokenization_siglip.py:258
↓ 2 callersFunctionrotate_half
Rotates half the hidden dims of the input.
RL/flow_grpo/flow_grpo/bagel/modeling/qwen2/modeling_qwen2.py:154
↓ 2 callersFunctionrotate_half
(x)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/siglip_navit.py:130
↓ 2 callersMethodset_attn_processor
r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor`
eval/TextCrafter/TextCrafter_Flux/textcrafter_transformer_flux.py:315
↓ 2 callersMethodset_attn_processor
r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor`
eval/TextCrafter/TextCrafter_SD3/textcrafter_transformer_sd3.py:381
↓ 2 callersMethodset_chunk_feed_forward
(self, chunk_size: Optional[int], dim: int = 0)
eval/TextCrafter/TextCrafter_SD3/textcrafter_transformer_sd3.py:136
↓ 2 callersFunctionsplit_chinese_or_mix
(text_list)
eval/TextPecker_eval/parse_utils_pecker.py:106
↓ 2 callersFunctionupdate_metrics
(data_type)
train/get_metrics_for_tsap_and_ctr.py:251
↓ 2 callersFunctionupdate_recog_metrics
(data_type, correct_text, positive_pred, edit_dist)
train/get_metrics_for_tsap_and_ctr.py:278
↓ 2 callersFunctionvariance_scaling_
(tensor, scale=1.0, mode="fan_in", distribution="normal")
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:108
↓ 2 callersFunctionvisualize_rectangles
Visualize rectangles and points, adjust the coordinate system so that (0,0) is at the top left corner, and save the image to a file. Para
eval/TextCrafter/TextCrafter_Flux/rectangles.py:115
↓ 2 callersFunctionvisualize_rectangles
Visualize rectangles and points, adjust the coordinate system so that (0,0) is at the top left corner, and save the image to a file. Para
eval/TextCrafter/TextCrafter_SD3/rectangles.py:114
↓ 2 callersFunctionwan_pipeline_with_logprob
r""" The call function to the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*): The prompt or pro
RL/flow_grpo/flow_grpo/diffusers_patch/wan_pipeline_with_logprob.py:86
↓ 1 callersFunctionFluxSingleTransformerBlock_init_forward
(self, module)
eval/TextCrafter/TextCrafter_Flux/init.py:19
↓ 1 callersFunctionFluxTransformerBlock_init_forward
(self, module)
eval/TextCrafter/TextCrafter_Flux/init.py:32
↓ 1 callersFunctionSD3TransformerBlock_init_forward
(self, module)
eval/TextCrafter/TextCrafter_SD3/init.py:8
↓ 1 callersMethod__init__
( self, dim: int, num_attention_heads: int, attention_head
eval/TextCrafter/TextCrafter_SD3/textcrafter_transformer_sd3.py:54
↓ 1 callersMethod__init__
(self, name='vit_large',content_proj_head='default', model_path=None)
eval/OneIG-Benchmark/scripts/utils/CSD_config.py:88
↓ 1 callersMethod__init__
(self)
RL/flow_grpo/flow_grpo/aesthetic_scorer.py:14
↓ 1 callersMethod__init__
(self, language_model, vit_model, config: BagelConfig)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/bagel.py:67
↓ 1 callersMethod__init__
( self, max_image_size, min_image_size, image_stride, max_pixels=1
RL/flow_grpo/flow_grpo/bagel/data/transforms.py:91
↓ 1 callersMethod_build_pipe
(self)
eval/TIIF-Bench/eval/inference_t2i_models.py:24
↓ 1 callersMethod_convert_to_str
(self, instruction, text)
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:270
↓ 1 callersMethod_dynamic_frequency_update
dynamic RoPE layers should recompute `inv_freq` in the following situations: 1 - growing beyond the cached sequence length (allow sca
RL/flow_grpo/flow_grpo/bagel/modeling/qwen2/modeling_qwen2.py:111
↓ 1 callersMethod_encode
( self, sentences_batch, device: Optional[str] = None, convert_to_numpy: bool
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:396
↓ 1 callersFunction_encode_prompt_with_clip
( text_encoder, tokenizer, prompt: str, device=None, text_input_ids=None, num_images_p
RL/flow_grpo/flow_grpo/diffusers_patch/train_dreambooth_lora_flux.py:63
↓ 1 callersFunction_encode_prompt_with_clip
( text_encoder, tokenizer, prompt: str, device=None, text_input_ids=None, num_images_p
RL/flow_grpo/flow_grpo/diffusers_patch/train_dreambooth_lora_sd3.py:59
↓ 1 callersFunction_encode_prompt_with_t5
( text_encoder, tokenizer, max_sequence_length=512, prompt=None, num_images_per_prompt=1,
RL/flow_grpo/flow_grpo/diffusers_patch/train_dreambooth_lora_flux.py:19
↓ 1 callersFunction_encode_prompt_with_t5
( text_encoder, tokenizer, max_sequence_length, prompt=None, num_images_per_prompt=1,
RL/flow_grpo/flow_grpo/diffusers_patch/train_dreambooth_lora_sd3.py:19
↓ 1 callersFunction_extract_scores
(text_outputs)
RL/flow_grpo/flow_grpo/rewards.py:1172
↓ 1 callersMethod_get_clip_prompt_embeds
( self, prompt: Union[str, List[str]], num_images_per_prompt: int = 1,
eval/TextCrafter/TextCrafter_Flux/textcrafter_pipeline_flux.py:285
↓ 1 callersMethod_get_model_class
(cls, config_class_name, enable_bidirectional)
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:55
↓ 1 callersFunction_get_t5_prompt_embeds
( text_encoder, tokenizer, prompt: Union[str, List[str]] = None, max_sequence_length: int = 22
RL/flow_grpo/flow_grpo/diffusers_patch/wan_prompt_embedding.py:4
↓ 1 callersMethod_get_t5_prompt_embeds
( self, prompt: Union[str, List[str]] = None, num_images_per_prompt: in
eval/TextCrafter/TextCrafter_Flux/textcrafter_pipeline_flux.py:236
↓ 1 callersMethod_init_weights
(self)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/modeling_utils.py:138
↓ 1 callersMethod_init_weights
(self)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/bagel.py:102
↓ 1 callersMethod_l2_normalize
(self, x)
eval/OneIG-Benchmark/scripts/utils/inference.py:138
↓ 1 callersMethod_load_aesthetic_model
Load aesthetic evaluation model
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:114
↓ 1 callersMethod_load_model
(self, model_path: str)
eval/OneIG-Benchmark/scripts/utils/inference.py:111
↓ 1 callersMethod_load_models
Load all required models
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:36
↓ 1 callersMethod_pack_latents
(latents, batch_size, num_channels_latents, height, width)
eval/TextCrafter/TextCrafter_Flux/textcrafter_pipeline_flux.py:512
↓ 1 callersMethod_skip_instruction
(self, sentence_feature)
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:220
↓ 1 callersMethod_text_length
Help function to get the length for the input text. Text can be either a string (which means a single text) a list of ints (which mea
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:420
↓ 1 callersFunction_trunc_normal_
(tensor, mean, std, a, b)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:46
↓ 1 callersFunctionalignment_score
(img_path, questions, dependencies, img_grid, cache_dir)
eval/OneIG-Benchmark/scripts/alignment/alignment_score.py:20
↓ 1 callersFunctionbad_string_rec
(string)
train/parse_utils.py:286
↓ 1 callersFunctionbatch_to_device
send a pytorch batch to a device (CPU/GPU)
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:25
↓ 1 callersMethodbetween_steps
(self)
eval/TextCrafter/TextCrafter_Flux/utils.py:34
↓ 1 callersMethodbetween_steps
(self)
eval/TextCrafter/TextCrafter_SD3/utils.py:33
↓ 1 callersFunctionbold_max_in_each_column
Bold the max value in each column, including Mean_Accuracy. Auto-adapt for multi-level header and index.
eval/TIIF-Bench/eval/summary_results.py:23
↓ 1 callersMethodbpe
(self, token)
RL/flow_grpo/flow_grpo/bagel/modeling/qwen2/tokenization_qwen2.py:208
↓ 1 callersFunctionbuild_t2i_model
(model_name)
eval/TIIF-Bench/eval/inference_t2i_models.py:107
↓ 1 callersFunctionbytes_to_unicode
Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control characters the bpe code bar
RL/flow_grpo/flow_grpo/bagel/modeling/qwen2/tokenization_qwen2.py:33
↓ 1 callersFunctionca_forward
(self, place_in_transformer)
eval/TextCrafter/TextCrafter_Flux/utils.py:210
↓ 1 callersFunctionca_forward
(self, place_in_transformer)
eval/TextCrafter/TextCrafter_SD3/utils.py:210
↓ 1 callersFunctioncalculate_char_match_ratio
(text_gt, ocr_str, mode='en')
eval/X-Omni/textbench/summary_scores.py:25
↓ 1 callersFunctioncalculate_char_match_ratio
(text_gt, ocr_str)
eval/OneIG-Benchmark/scripts/text/text_utils.py:50
↓ 1 callersFunctioncalculate_metrics
Calculate average metrics from the data
eval/TextPecker_eval/metric_summary.py:37
↓ 1 callersFunctioncalculate_shift
( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_sh
eval/TextCrafter/TextCrafter_Flux/textcrafter_pipeline_flux.py:83
↓ 1 callersFunctioncalculate_shift
( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_shift: float = 0.5
eval/TextCrafter/TextCrafter_SD3/textcrafter_pipeline_sd3.py:92
↓ 1 callersFunctioncalculate_shift
( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_shift: float = 0.5,
RL/flow_grpo/flow_grpo/diffusers_patch/flux_pipeline_with_logprob_fast_guard.py:10
↓ 1 callersFunctioncalculate_shift
( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_shift: float = 0.5,
RL/flow_grpo/flow_grpo/diffusers_patch/flux_pipeline_with_logprob_guard.py:10
↓ 1 callersFunctioncalculate_shift
( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_shift: float = 0.5,
RL/flow_grpo/flow_grpo/diffusers_patch/flux_kontext_pipeline_with_logprob.py:46
↓ 1 callersFunctioncalculate_shift
( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_shift: float = 0.5,
RL/flow_grpo/flow_grpo/diffusers_patch/flux_pipeline_with_logprob_fast.py:10
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_bagel.py:137
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_sd3_fast_guard.py:152
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_qwenimage_fast_guard.py:178
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_qwenimage_fast.py:178
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_flux_kontext.py:132
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_sd3_GRPO_Guard.py:152
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_sd3_fast.py:151
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_flux_fast.py:156
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_sd3_sft.py:144
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_qwenimage_edit.py:150
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_sd3.py:133
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_qwenimage.py:156
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_sd3_dpo.py:142
↓ 1 callersFunctioncalculate_zero_std_ratio
计算每个唯一提示词对应奖励值的标准差为零的比例 参数: prompts: 提示词列表 gathered_rewards: 包含奖励值的字典，须包含'ori_avg'键 返回: zero_std_ra
RL/flow_grpo/scripts/train_wan2_1.py:142
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_flux.py:138
↓ 1 callersFunctioncalculate_zero_std_ratio
Calculate the proportion of unique prompts whose reward standard deviation is zero. Args: prompts: List of prompts. gath
RL/flow_grpo/scripts/train_flux_fast_guard.py:156
↓ 1 callersMethodcanonicalize_text
Returns canonicalized `text` (puncuation removed). Args: text (`str`): String to be canonicalized. ke
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/tokenization_siglip.py:262
↓ 1 callersMethodcheck_inputs
( self, prompt, prompt_2, height, width,
eval/TextCrafter/TextCrafter_Flux/textcrafter_pipeline_flux.py:449
↓ 1 callersFunctionclassify_results
主函数：分离中英文，分别处理后合并结果
eval/TextPecker_eval/parse_utils_pecker.py:427
↓ 1 callersFunctionclassify_results
主函数：分离中英文，分别处理后合并结果
RL/flow_grpo/flow_grpo/parse_utils_pecker.py:427
↓ 1 callersFunctionclean_and_remove_hallucinations
(text)
eval/X-Omni/textbench/evaluate_text_reward.py:18
↓ 1 callersFunctionclean_and_remove_hallucinations
(texts)
eval/OneIG-Benchmark/scripts/text/text_utils.py:17
↓ 1 callersFunctionclean_text
(text)
eval/TextPecker_eval/parse_utils_pecker.py:277
↓ 1 callersFunctionclean_text
(text)
RL/flow_grpo/flow_grpo/parse_utils_pecker.py:277
↓ 1 callersFunctioncollect_data
(path)
eval/TIIF-Bench/eval/cal_gned_and_recall_models.py:90
↓ 1 callersFunctioncollect_tasks
(jsonl_dir, image_dir, eval_model, output_dir, sample_idx_file=None, postfix="")
eval/TIIF-Bench/eval/eval_with_vlm.py:122
↓ 1 callersFunctioncompressibility
()
RL/flow_grpo/config/FLUX.py:8
↓ 1 callersFunctioncompressibility
()
RL/flow_grpo/config/QWEN.py:8
↓ 1 callersFunctioncompressibility
()
RL/flow_grpo/config/SD.py:7
↓ 1 callersMethodcompute_aesthetic_score
Calculate aesthetic score
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:325
↓ 1 callersMethodcompute_clip_score_batch
Batch compute CLIPScore - matching the batch processing logic of original clipscore.py
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:190
↓ 1 callersMethodcompute_ocr_metrics
Calculate OCR-related metrics: total words, correct words, edit distance list for each word
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:148
↓ 1 callersMethodcompute_vqa_score
Calculate VQAScore
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:313
↓ 1 callersFunctioncontain_chinese
(prompts)
train/parse_utils.py:315
↓ 1 callersMethodconvert_conv2d_to_linear
(self, config, meta=False)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/siglip_navit.py:167
← previousnext →201–300 of 1,395, ranked by callers