Types & classes — github.com/CIawevy/TextPecker

CodeHub MCPcopy Create free account

hub / github.com/CIawevy/TextPecker / types & classes

Types & classes206 in github.com/CIawevy/TextPecker

⨍ Functions 1,395◇ Types & classes 206↳ Endpoints 2

↓ 19 callersClassQwen2RMSNorm

RL/flow_grpo/flow_grpo/bagel/modeling/qwen2/modeling_qwen2.py:45

↓ 17 callersClassPerPromptStatTracker

RL/flow_grpo/flow_grpo/stat_tracking.py:5

↓ 11 callersClassEMAModuleWrapper

RL/flow_grpo/flow_grpo/ema.py:8

↓ 6 callersClassQwen2MLP

RL/flow_grpo/flow_grpo/bagel/modeling/qwen2/modeling_qwen2.py:190

↓ 6 callersClassResnetBlock

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:68

↓ 4 callersClassFSDPConfig

RL/flow_grpo/flow_grpo/fsdp_utils.py:18

↓ 4 callersClassImageTransform

RL/flow_grpo/flow_grpo/bagel/data/transforms.py:90

↓ 4 callersClassOcrScorerCN

RL/flow_grpo/flow_grpo/ocr.py:340

↓ 4 callersClassOcrScorerEN

RL/flow_grpo/flow_grpo/ocr.py:207

↓ 3 callersClassClipScorer

RL/flow_grpo/flow_grpo/clip_scorer.py:30

↓ 3 callersClassQwen2ForCausalLM

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:1069

↓ 2 callersClassAttnBlock

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:38

↓ 2 callersClassBagel

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/bagel.py:63

↓ 2 callersClassBagelConfig

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/bagel.py:33

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_bagel.py:93

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_sd3_fast_guard.py:98

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_qwenimage_fast_guard.py:123

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_qwenimage_fast.py:123

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_sd3_GRPO_Guard.py:98

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_sd3_fast.py:97

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_flux_fast.py:101

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_sd3_sft.py:81

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_sd3.py:79

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_qwenimage.py:101

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_sd3_dpo.py:79

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_wan2_1.py:81

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_flux.py:83

↓ 2 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_flux_fast_guard.py:101

↓ 2 callersClassFLUX

eval/TIIF-Bench/eval/inference_t2i_models.py:100

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_bagel.py:74

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_sd3_fast_guard.py:79

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_qwenimage_fast_guard.py:104

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_qwenimage_fast.py:104

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_sd3_GRPO_Guard.py:79

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_sd3_fast.py:78

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_flux_fast.py:82

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_sd3_sft.py:62

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_sd3.py:60

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_qwenimage.py:82

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_sd3_dpo.py:60

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_wan2_1.py:62

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_flux.py:64

↓ 2 callersClassGenevalPromptDataset

RL/flow_grpo/scripts/train_flux_fast_guard.py:82

↓ 2 callersClassGenevalPromptImageDataset

RL/flow_grpo/scripts/train_flux_kontext.py:46

↓ 2 callersClassGenevalPromptImageDataset

RL/flow_grpo/scripts/train_qwenimage_edit.py:63

↓ 2 callersClassImageRewardScorer

RL/flow_grpo/flow_grpo/imagereward_scorer.py:6

↓ 2 callersClassInterleaveInferencer

RL/flow_grpo/flow_grpo/bagel/inferencer.py:22

↓ 2 callersClassNaiveCache

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:204

↓ 2 callersClassOcrScorer

RL/flow_grpo/flow_grpo/ocr.py:122

↓ 2 callersClassPackedAttention

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:233

↓ 2 callersClassPickScoreScorer

RL/flow_grpo/flow_grpo/pickscore_scorer.py:5

↓ 2 callersClassPositionEmbedding

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/modeling_utils.py:127

↓ 2 callersClassQwen2RotaryEmbedding

RL/flow_grpo/flow_grpo/bagel/modeling/qwen2/modeling_qwen2.py:66

↓ 2 callersClassQwen2_5VLBatchInferencer

eval/OneIG-Benchmark/scripts/utils/inference.py:17

↓ 2 callersClassQwenVLScorer

RL/flow_grpo/flow_grpo/qwenvl.py:26

↓ 2 callersClassSANA15

eval/TIIF-Bench/eval/inference_t2i_models.py:47

↓ 2 callersClassSD3

eval/TIIF-Bench/eval/inference_t2i_models.py:70

↓ 2 callersClassSiglipEncoder

Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a [`SiglipEncoderLayer`]. Args:

RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:824

↓ 2 callersClassSiglipMLP

RL/flow_grpo/flow_grpo/bagel/modeling/siglip/modeling_siglip.py:588

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_bagel.py:53

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_sd3_fast_guard.py:42

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_qwenimage_fast_guard.py:60

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_qwenimage_fast.py:60

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_sd3_GRPO_Guard.py:42

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_sd3_fast.py:41

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_flux_fast.py:45

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_sd3_sft.py:44

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_sd3.py:42

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_qwenimage.py:61

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_sd3_dpo.py:42

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_wan2_1.py:44

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_flux.py:46

↓ 2 callersClassTextPromptDataset

RL/flow_grpo/scripts/train_flux_fast_guard.py:45

↓ 1 callersClassAestheticScorer

RL/flow_grpo/flow_grpo/aesthetic_scorer.py:32

↓ 1 callersClassAttentionLastStore

eval/TextCrafter/TextCrafter_Flux/pre_generation.py:30

↓ 1 callersClassAttentionLastStore

eval/TextCrafter/TextCrafter_SD3/pre_generation.py:27

↓ 1 callersClassAutoEncoder

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:290

↓ 1 callersClassAutoEncoderParams

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:21

↓ 1 callersClassBaseNavitOutputWithPast

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/qwen2_navit.py:222

↓ 1 callersClassCSDStyleEmbedding

eval/OneIG-Benchmark/scripts/utils/inference.py:97

↓ 1 callersClassCSD_CLIP

backbone + projection head

eval/OneIG-Benchmark/scripts/utils/CSD_config.py:86

↓ 1 callersClassDecoder

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:196

↓ 1 callersClassDiagonalGaussian

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:275

↓ 1 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_flux_kontext.py:77

↓ 1 callersClassDistributedKRepeatSampler

RL/flow_grpo/scripts/train_qwenimage_edit.py:95

↓ 1 callersClassDownsample

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:98

↓ 1 callersClassDummyController

eval/TextCrafter/TextCrafter_Flux/utils.py:282

↓ 1 callersClassDummyController

eval/TextCrafter/TextCrafter_SD3/utils.py:285

↓ 1 callersClassEncoder

RL/flow_grpo/flow_grpo/bagel/modeling/autoencoder.py:122

↓ 1 callersClassFluxSingleTransformerBlock

r""" A Transformer block following the MMDiT architecture, introduced in Stable Diffusion 3. Reference: https://arxiv.org/abs/2403.03206

eval/TextCrafter/TextCrafter_Flux/textcrafter_transformer_flux.py:45

↓ 1 callersClassFluxTransformerBlock

r""" A Transformer block following the MMDiT architecture, introduced in Stable Diffusion 3. Reference: https://arxiv.org/abs/2403.03206

eval/TextCrafter/TextCrafter_Flux/textcrafter_transformer_flux.py:110

↓ 1 callersClassImageEvaluator

eval/X-Omni/textbench/evaluate_text_reward.py:27

↓ 1 callersClassJointTransformerBlock

r""" A Transformer block following the MMDiT architecture, introduced in Stable Diffusion 3. Reference: https://arxiv.org/abs/2403.03206

eval/TextCrafter/TextCrafter_SD3/textcrafter_transformer_sd3.py:40

↓ 1 callersClassLLM2CLIP

eval/OneIG-Benchmark/scripts/utils/inference.py:152

↓ 1 callersClassLLM2Vec

eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/llm2vec.py:35

↓ 1 callersClassLlamaBiModel

eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/models/bidirectional_llama.py:87

↓ 1 callersClassMLP

RL/flow_grpo/flow_grpo/aesthetic_scorer.py:13

↓ 1 callersClassMLPconnector

RL/flow_grpo/flow_grpo/bagel/modeling/bagel/modeling_utils.py:113

↓ 1 callersClassMaxLongEdgeMinShortEdgeResize

Resize the input image so that its longest side and shortest side are within a specified range, ensuring that both sides are divisible by a specif

RL/flow_grpo/flow_grpo/bagel/data/transforms.py:15

↓ 1 callersClassModifiedLlamaDecoderLayer

eval/OneIG-Benchmark/scripts/utils/llm2clip/llm2vec/models/bidirectional_llama.py:71

next →1–100 of 206, ranked by callers