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 callersFunctionconvert_numpy_types
Recursively convert numpy types to Python native types for JSON serialization
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:15
↓ 1 callersFunctionconvert_siglip_checkpoint
Copy/paste/tweak model's weights to our SigLIP structure.
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/convert_siglip_to_hf.py:245
↓ 1 callersFunctionconvert_state_dict
(state_dict)
eval/OneIG-Benchmark/scripts/utils/CSD_config.py:9
↓ 1 callersFunctionconvert_weights_float
Convert applicable model parameters to fp32
eval/OneIG-Benchmark/scripts/utils/CSD_config.py:17
↓ 1 callersFunctioncopy_learner_to_ref
(transformer)
RL/flow_grpo/scripts/train_sd3_sft.py:136
↓ 1 callersFunctioncopy_learner_to_ref
(transformer)
RL/flow_grpo/scripts/train_sd3_dpo.py:134
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_sd3_fast_guard.py:188
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_qwenimage_fast_guard.py:214
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_qwenimage_fast.py:214
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_flux_kontext.py:168
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_sd3_GRPO_Guard.py:188
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_sd3_fast.py:187
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_flux_fast.py:192
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_qwenimage_edit.py:186
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_sd3.py:169
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_qwenimage.py:192
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_flux.py:174
↓ 1 callersFunctioncreate_generator
(prompts, base_seed)
RL/flow_grpo/scripts/train_flux_fast_guard.py:192
↓ 1 callersFunctioncreate_generators
(prompts, base_seed)
RL/flow_grpo/scripts/train_bagel.py:173
↓ 1 callersFunctioncreate_image_gallery
(images, rows=2, cols=2)
eval/models/SD3.5/infer_sd3_oneig.py:17
↓ 1 callersFunctioncreate_image_gallery
(images, rows=2, cols=2, target_size=(1024, 1024))
eval/models/Qwenimage/infer_qwenimage_oneig.py:31
↓ 1 callersFunctioncreate_image_gallery
(images, rows=2, cols=2)
eval/models/Flux/infer_flux_dev_oneig.py:18
↓ 1 callersFunctioncreate_image_gallery
(images, rows=2, cols=2)
eval/OneIG-Benchmark/text2image.py:5
↓ 1 callersFunctioncreate_rename_keys
(config)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/convert_siglip_to_hf.py:93
↓ 1 callersFunctioncreate_sparse_mask
(document_lens, split_lens, attn_modes, device)
RL/flow_grpo/flow_grpo/bagel/data/data_utils.py:13
↓ 1 callersMethoddecode_image
(self, latent, image_shape)
RL/flow_grpo/flow_grpo/bagel/inferencer.py:228
↓ 1 callersFunctiondefault_flax_embed_init
(tensor)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:137
↓ 1 callersFunctiondistribute_samples
(tasks, weights, total_samples)
RL/flow_grpo/dataset/merge_genevaltask.py:5
↓ 1 callersFunctionensure_dir
(path)
eval/TIIF-Bench/eval/eval_with_vlm.py:110
↓ 1 callersFunctioneval
(inferencer, inference_hyper, test_dataloader, tokenizer, config, accelerator, global_step, eval_reward_fn, ex
RL/flow_grpo/scripts/train_bagel.py:185
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_sd3_fast_guard.py:241
↓ 1 callersFunctioneval
(pipeline, test_dataloader, config, rank, local_rank, world_size, device, global_step, reward_fn, executor, au
RL/flow_grpo/scripts/train_qwenimage_fast_guard.py:273
↓ 1 callersFunctioneval
(pipeline, test_dataloader, config, rank, local_rank, world_size, device, global_step, reward_fn, executor, au
RL/flow_grpo/scripts/train_qwenimage_fast.py:273
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_flux_kontext.py:216
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_sd3_GRPO_Guard.py:239
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_sd3_fast.py:236
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_flux_fast.py:241
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_sd3_sft.py:193
↓ 1 callersFunctioneval
(pipeline, test_dataloader, config, rank, local_rank, world_size, device, global_step, reward_fn, executor, au
RL/flow_grpo/scripts/train_qwenimage_edit.py:249
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_sd3.py:217
↓ 1 callersFunctioneval
(pipeline, test_dataloader, config, rank, local_rank, world_size, device, global_step, reward_fn, executor, au
RL/flow_grpo/scripts/train_qwenimage.py:244
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_sd3_dpo.py:191
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_wan2_1.py:232
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_flux.py:219
↓ 1 callersFunctioneval
(pipeline, test_dataloader, text_encoders, tokenizers, config, accelerator, global_step, reward_fn, executor,
RL/flow_grpo/scripts/train_flux_fast_guard.py:241
↓ 1 callersFunctioneval_datasets
(args: argparse.Namespace, lang_mode: str)
eval/TextPecker_eval/textpecker_eval_server.py:1040
↓ 1 callersMethodevaluate
(self, data_chunk)
eval/X-Omni/textbench/evaluate_text_reward.py:66
↓ 1 callersFunctionevaluate_batch_image
Creates and runs a batch of asynchronous evaluation tasks with proper error handling.
eval/TextPecker_eval/textpecker_eval_server.py:359
↓ 1 callersMethodevaluate_full_dataset
Evaluate complete dataset
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:449
↓ 1 callersFunctionevaluate_image
带重试机制的异步图像评估函数
eval/TextPecker_eval/textpecker_eval_server.py:317
↓ 1 callersFunctionevaluate_image
Sends a single asynchronous request to the vLLM server.
eval/TextPecker_eval/demo.py:101
↓ 1 callersMethodevaluate_single_area
Evaluate data for a single area
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:345
↓ 1 callersFunctionextract_gt_from_infer
从推理结果项中提取GT文本
train/convert_api_infer_results_swift.py:36
↓ 1 callersFunctionextract_pred_text
从response中提取预测的文本
train/convert_api_infer_results_swift.py:26
↓ 1 callersFunctionextract_rec_texts
(s)
eval/TextPecker_eval/parse_utils_pecker.py:243
↓ 1 callersFunctionextract_rec_texts
(s)
RL/flow_grpo/flow_grpo/parse_utils_pecker.py:243
↓ 1 callersFunctionextract_scores
(output_text)
RL/flow_grpo/flow_grpo/qwenvl.py:16
↓ 1 callersFunctionextract_texts
(s)
train/parse_utils.py:197
↓ 1 callersMethodextract_words_from_prompt
Extract words within single quotes from prompt
eval/TextCrafter/TextCrafter_Eval/unified_metrics_eval.py:140
↓ 1 callersFunctionextract_yes_no
(model_output, questions)
eval/TIIF-Bench/eval/eval_with_vlm.py:164
↓ 1 callersFunctionfilter_train_metadata
(test_path, train_path, output_path)
RL/flow_grpo/dataset/geneval_filter_test.py:3
↓ 1 callersFunctionfind_image_by_idx
(img_dir, idx)
eval/TIIF-Bench/eval/eval_with_vlm.py:114
↓ 1 callersFunctionflatten_nested_dict
(params, parent_key="", sep="/")
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/convert_siglip_to_hf.py:231
↓ 1 callersMethodflush
(self)
eval/TIIF-Bench/eval/summary_dimension_results.py:19
↓ 1 callersFunctionformat_questions_prompt
(raw_prompt, questions)
eval/TIIF-Bench/eval/eval_with_vlm.py:103
↓ 1 callersMethodforward
(self, attn, place_in_transformer: str)
eval/TextCrafter/TextCrafter_Flux/utils.py:38
↓ 1 callersMethodforward
(self, attn, place_in_transformer: str)
eval/TextCrafter/TextCrafter_Flux/utils.py:62
↓ 1 callersMethodforward
(self, attn, place_in_transformer: str)
eval/TextCrafter/TextCrafter_SD3/utils.py:37
↓ 1 callersMethodforward
(self, attn, place_in_transformer: str)
eval/TextCrafter/TextCrafter_SD3/utils.py:62
↓ 1 callersMethodforward
(self, sentence_feature: Dict[str, Tensor])
eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:227
↓ 1 callersMethodforward
(self, hidden_states: torch.Tensor)
RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:596
↓ 1 callersMethodforward_cache_update_vae
( self, vae_model, past_key_values: NaiveCache, padded_images: torch.Tensor,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/bagel.py:497
↓ 1 callersMethodforward_hidden_states_list
The [`FluxTransformer2DModel`] forward method. Args: hidden_states (`torch.FloatTensor` of shape `(batch size, chann
eval/TextCrafter/TextCrafter_Flux/textcrafter_transformer_flux.py:725
↓ 1 callersMethodforward_hidden_states_list
The [`SD3Transformer2DModel`] forward method with additional return of hidden states list. Args: hidden_states (`tor
eval/TextCrafter/TextCrafter_SD3/textcrafter_transformer_sd3.py:672
↓ 1 callersMethodforward_inference
( self, packed_query_sequence: torch.Tensor, query_lens: torch.Tensor, packed_
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:310
↓ 1 callersMethodforward_inference
( self, packed_query_sequence: torch.Tensor, query_lens: torch.Tensor, packed_
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:496
↓ 1 callersMethodforward_inference
( self, packed_query_sequence: torch.Tensor, query_lens: torch.Tensor, packed_
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:650
↓ 1 callersMethodforward_inference
( self, packed_query_sequence: torch.Tensor, query_lens: torch.Tensor, packed_
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:759
↓ 1 callersMethodforward_inference
( self, packed_query_sequence: torch.Tensor, query_lens: torch.Tensor, packed_
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:875
↓ 1 callersMethodforward_inference
( self, packed_query_sequence: torch.Tensor, query_lens: torch.Tensor, packed_
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:1005
↓ 1 callersMethodforward_inference
( self, packed_query_sequence: torch.Tensor, query_lens: torch.Tensor, packed_
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:1133
↓ 1 callersMethodforward_train
( self, packed_sequence: torch.Tensor, sample_lens: List[int], attention_mask:
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:249
↓ 1 callersMethodforward_train
( self, packed_sequence: torch.Tensor, sample_lens: List[int], attention_mask,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:403
↓ 1 callersMethodforward_train
( self, packed_sequence: torch.Tensor, sample_lens: List[int], attention_mask,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:622
↓ 1 callersMethodforward_train
( self, packed_sequence: torch.Tensor, sample_lens: List[int], attention_mask,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:715
↓ 1 callersMethodforward_train
( self, packed_sequence: torch.Tensor, sample_lens: List[int], attention_mask,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:839
↓ 1 callersMethodforward_train
( self, packed_sequence: torch.Tensor, sample_lens: List[int], attention_mask,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:957
↓ 1 callersMethodforward_train
( self, packed_sequence: torch.Tensor, sample_lens: List[int], attention_mask,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:1113
↓ 1 callersMethodgen_image
( self, image_shape, gen_context, cfg_text_scale=4.0, cfg_img_scale
RL/flow_grpo/flow_grpo/bagel/inferencer.py:98
↓ 1 callersMethodgenerate_image
( self, packed_text_ids: torch.LongTensor, packed_text_indexes: torch.LongTensor,
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/bagel.py:657
↓ 1 callersMethodgenerate_image_learn
( self, sample, grpo_config, accelerator, optimizer, transform
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/bagel.py:775
↓ 1 callersFunctiongenerate_rectangles_fixed
(area)
eval/TextCrafter/TextCrafter_Flux/rectangles.py:201
↓ 1 callersFunctiongenerate_summary_table
为所有模型结果生成漂亮的表格并写入文件 Args: model_results: 模型结果字典 output_file: 输出文件路径 show_dataset_details: 是否显示数据集详情 language_
train/get_metrics_for_tsap_and_ctr.py:336
↓ 1 callersFunctiongenerate_with_prompt
(prompt, image_path, client, model='gpt-4o')
eval/TIIF-Bench/eval/eval_with_vlm.py:74
↓ 1 callersFunctiongentext_eval
(data, batch_size=8)
eval/TextPecker_eval/textpecker_eval_server.py:1123
↓ 1 callersFunctionget_2d_sincos_pos_embed
(embed_dim, grid_size, cls_token=False, extra_tokens=0)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/modeling_utils.py:24
↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
RL/flow_grpo/flow_grpo/bagel/modeling/bagel/modeling_utils.py:37
↓ 1 callersMethodget_average_attention
(self)
eval/TextCrafter/TextCrafter_Flux/utils.py:78
↓ 1 callersMethodget_average_attention
(self)
eval/TextCrafter/TextCrafter_SD3/utils.py:78
↓ 1 callersMethodget_current_decay
(self, optimization_step)
RL/flow_grpo/flow_grpo/ema.py:33
← previousnext →301–400 of 1,395, ranked by callers