SYMBOL INDEX (183 symbols across 25 files)

FILE: GOT-OCR-2.0-master/GOT/data/__init__.py
  class DataCollatorForSupervisedDataset (line 10) | class DataCollatorForSupervisedDataset(object):
    method __call__ (line 13) | def __call__(self, instances):
  function make_supervised_data_module (line 46) | def make_supervised_data_module(interleave, with_box, tokenizer, data_ar...

FILE: GOT-OCR-2.0-master/GOT/data/base_dataset.py
  class BaseDataset (line 17) | class BaseDataset(Dataset):
    method __init__ (line 18) | def __init__(
    method image_processor (line 30) | def image_processor(self, image):
    method __len__ (line 66) | def __len__(self):
    method __getitem__ (line 69) | def __getitem__(self, i) -> Dict[str, torch.Tensor]:

FILE: GOT-OCR-2.0-master/GOT/data/conversation_dataset_qwen.py
  class ConversationDataset (line 23) | class ConversationDataset(BaseDataset):
    method __init__ (line 26) | def __init__(self, datasets, tokenizer, multimodal_cfg):
    method multimodal_processor (line 71) | def multimodal_processor(self, sources, flag_num_patches):
    method _tokenize_fn (line 85) | def _tokenize_fn(self, strings):
    method _mask_targets (line 110) | def _mask_targets(self, target, tokenized_lens, speakers):
    method token_processor (line 120) | def token_processor(self, sources, image_name):
    method __getitem__ (line 195) | def __getitem__(self, i) -> Dict[str, torch.Tensor]:

FILE: GOT-OCR-2.0-master/GOT/demo/process_results.py
  function svg_to_html (line 12) | def svg_to_html(svg_content, output_filename):

FILE: GOT-OCR-2.0-master/GOT/demo/run_ocr_2.0.py
  function load_image (line 35) | def load_image(image_file):
  function eval_model (line 44) | def eval_model(args):

FILE: GOT-OCR-2.0-master/GOT/demo/run_ocr_2.0_crop.py
  function load_image (line 32) | def load_image(image_file):
  function find_closest_aspect_ratio (line 40) | def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height...
  function dynamic_preprocess (line 57) | def dynamic_preprocess(image, min_num=1, max_num=6, image_size=1024, use...
  function eval_model (line 99) | def eval_model(args):

FILE: GOT-OCR-2.0-master/GOT/eval/eval_GOT_ocr.py
  function load_image (line 49) | def load_image(image_file):
  function find_closest_aspect_ratio (line 58) | def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height...
  function dynamic_preprocess (line 75) | def dynamic_preprocess(image, min_num=1, max_num=6, image_size=1024, use...
  function split_list (line 119) | def split_list(lst, n):
  function get_chunk (line 125) | def get_chunk(lst, n, k):
  function eval_model (line 133) | def eval_model(args):

FILE: GOT-OCR-2.0-master/GOT/eval/multi_hardware_eval_GOT.py
  function run_eval (line 8) | def run_eval(chunk_id, model_name, gtfile_path, image_path, out_path, nu...

FILE: GOT-OCR-2.0-master/GOT/eval/pyevaltools/eval_ocr.py
  function preprocess (line 27) | def preprocess(text, predict_root_):
  function contain_chinese_string (line 33) | def contain_chinese_string(text):
  function split_text (line 43) | def split_text(pages, a_type):
  function nougat_per_metrics (line 64) | def nougat_per_metrics(predict_root_, pred, gt, minlen=1, heavy_mode: in...
  function doc_formated_text_eval (line 106) | def doc_formated_text_eval(gt_root_, predict_root_, datatype):
  function doc_text_eval (line 182) | def doc_text_eval(gt_root_, predict_root_, datatype):

FILE: GOT-OCR-2.0-master/GOT/eval/pyevaltools/eval_ocr_format.py
  function preprocess (line 27) | def preprocess(text, predict_root_):
  function contain_chinese_string (line 33) | def contain_chinese_string(text):
  function split_text (line 43) | def split_text(pages, a_type):
  function nougat_per_metrics (line 64) | def nougat_per_metrics(predict_root_, pred, gt, minlen=1, heavy_mode: in...
  function doc_formated_text_eval (line 106) | def doc_formated_text_eval(gt_root_, predict_root_, datatype):
  function doc_text_eval (line 182) | def doc_text_eval(gt_root_, predict_root_, datatype):

FILE: GOT-OCR-2.0-master/GOT/eval/pyevaltools/eval_ocr_scene.py
  function preprocess (line 20) | def preprocess(text, predict_root_):
  function contain_chinese_string (line 26) | def contain_chinese_string(text):
  function nougat_per_metrics (line 30) | def nougat_per_metrics(predict_root_, pred, gt, minlen=1):
  function doc_text_eval (line 54) | def doc_text_eval(gt_root_, predict_root_, datatype):

FILE: GOT-OCR-2.0-master/GOT/eval/pyevaltools/merge_results.py
  function merge_outputs (line 5) | def merge_outputs(out_path):

FILE: GOT-OCR-2.0-master/GOT/model/GOT_ocr_2_0.py
  class GOTConfig (line 15) | class GOTConfig(Qwen2Config):
  class GOTQwenModel (line 19) | class GOTQwenModel(Qwen2Model):
    method __init__ (line 22) | def __init__(self, config: Qwen2Config):
    method initialize_vision_modules (line 30) | def initialize_vision_modules(
    method forward (line 73) | def forward(
  class GOTQwenForCausalLM (line 208) | class GOTQwenForCausalLM(Qwen2ForCausalLM):
    method __init__ (line 212) | def __init__(self, config):
    method get_model (line 222) | def get_model(self):
    method forward (line 230) | def forward(
    method prepare_inputs_for_generation (line 304) | def prepare_inputs_for_generation(
    method initialize_vision_tokenizer (line 362) | def initialize_vision_tokenizer(

FILE: GOT-OCR-2.0-master/GOT/model/plug/blip_process.py
  class BaseProcessor (line 18) | class BaseProcessor:
    method __init__ (line 19) | def __init__(self):
    method __call__ (line 23) | def __call__(self, item):
  class BlipImageBaseProcessor (line 35) | class BlipImageBaseProcessor(BaseProcessor):
    method __init__ (line 36) | def __init__(self, mean=None, std=None):
  function identity_func (line 48) | def identity_func(img):
  function autocontrast_func (line 52) | def autocontrast_func(img, cutoff=0):
  function equalize_func (line 85) | def equalize_func(img):
  function rotate_func (line 109) | def rotate_func(img, degree, fill=(0, 0, 0)):
  function solarize_func (line 120) | def solarize_func(img, thresh=128):
  function color_func (line 130) | def color_func(img, factor):
  function contrast_func (line 148) | def contrast_func(img, factor):
  function brightness_func (line 162) | def brightness_func(img, factor):
  function sharpness_func (line 171) | def sharpness_func(img, factor):
  function shear_x_func (line 192) | def shear_x_func(img, factor, fill=(0, 0, 0)):
  function translate_x_func (line 201) | def translate_x_func(img, offset, fill=(0, 0, 0)):
  function translate_y_func (line 213) | def translate_y_func(img, offset, fill=(0, 0, 0)):
  function posterize_func (line 225) | def posterize_func(img, bits):
  function shear_y_func (line 233) | def shear_y_func(img, factor, fill=(0, 0, 0)):
  function cutout_func (line 242) | def cutout_func(img, pad_size, replace=(0, 0, 0)):
  function enhance_level_to_args (line 256) | def enhance_level_to_args(MAX_LEVEL):
  function shear_level_to_args (line 263) | def shear_level_to_args(MAX_LEVEL, replace_value):
  function translate_level_to_args (line 273) | def translate_level_to_args(translate_const, MAX_LEVEL, replace_value):
  function cutout_level_to_args (line 283) | def cutout_level_to_args(cutout_const, MAX_LEVEL, replace_value):
  function solarize_level_to_args (line 291) | def solarize_level_to_args(MAX_LEVEL):
  function none_level_to_args (line 299) | def none_level_to_args(level):
  function posterize_level_to_args (line 303) | def posterize_level_to_args(MAX_LEVEL):
  function rotate_level_to_args (line 311) | def rotate_level_to_args(MAX_LEVEL, replace_value):
  class RandomAugment (line 359) | class RandomAugment(object):
    method __init__ (line 360) | def __init__(self, N=2, M=10, isPIL=False, augs=[]):
    method get_random_ops (line 369) | def get_random_ops(self):
    method __call__ (line 373) | def __call__(self, img):
  class VideoRandomAugment (line 385) | class VideoRandomAugment(object):
    method __init__ (line 386) | def __init__(self, N=2, M=10, p=0.0, tensor_in_tensor_out=True, augs=[]):
    method get_random_ops (line 396) | def get_random_ops(self):
    method __call__ (line 400) | def __call__(self, frames):
    method _aug (line 419) | def _aug(self, img, ops, apply_or_not):
  class BlipImageTrainProcessor (line 438) | class BlipImageTrainProcessor(BlipImageBaseProcessor):
    method __init__ (line 439) | def __init__(
    method __call__ (line 474) | def __call__(self, item):
  class BlipImageEvalProcessor (line 478) | class BlipImageEvalProcessor(BlipImageBaseProcessor):
    method __init__ (line 479) | def __init__(self, image_size=384, mean=None, std=None):
    method __call__ (line 492) | def __call__(self, item):

FILE: GOT-OCR-2.0-master/GOT/model/vision_encoder/vary_b.py
  class Projector (line 24) | class Projector(nn.Module):
    method __init__ (line 25) | def __init__(
    method forward (line 45) | def forward(self, x: torch.Tensor):
  class MLPBlock (line 53) | class MLPBlock(nn.Module):
    method __init__ (line 54) | def __init__(
    method forward (line 65) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class LayerNorm2d (line 71) | class LayerNorm2d(nn.Module):
    method __init__ (line 72) | def __init__(self, num_channels: int, eps: float = 1e-6) -> None:
    method forward (line 78) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class ImageEncoderViT (line 87) | class ImageEncoderViT(nn.Module):
    method __init__ (line 88) | def __init__(
    method forward (line 180) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class Block (line 196) | class Block(nn.Module):
    method __init__ (line 199) | def __init__(
    method forward (line 243) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class Attention (line 262) | class Attention(nn.Module):
    method __init__ (line 265) | def __init__(
    method forward (line 301) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  function window_partition (line 320) | def window_partition(x: torch.Tensor, window_size: int) -> Tuple[torch.T...
  function window_unpartition (line 344) | def window_unpartition(
  function get_rel_pos (line 369) | def get_rel_pos(q_size: int, k_size: int, rel_pos: torch.Tensor) -> torc...
  function add_decomposed_rel_pos (line 402) | def add_decomposed_rel_pos(
  class PatchEmbed (line 441) | class PatchEmbed(nn.Module):
    method __init__ (line 446) | def __init__(
    method forward (line 468) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  function build_vary_vit_b (line 476) | def build_vary_vit_b(checkpoint=None):
  function _build_vary (line 486) | def _build_vary(

FILE: GOT-OCR-2.0-master/GOT/train/train.py
  function train (line 33) | def train():

FILE: GOT-OCR-2.0-master/GOT/train/train_GOT.py
  function train (line 38) | def train():

FILE: GOT-OCR-2.0-master/GOT/train/train_lora.py
  function train (line 45) | def train():

FILE: GOT-OCR-2.0-master/GOT/train/trainer.py
  function unwrap_model (line 9) | def unwrap_model(model: nn.Module) -> nn.Module:
  class GOTTrainer (line 23) | class GOTTrainer(Trainer):
    method _safe_save (line 25) | def _safe_save(self, output_dir: str):
    method _save (line 42) | def _save(self, output_dir: Optional[str] = None, state_dict=None):

FILE: GOT-OCR-2.0-master/GOT/train/trainer_llm_llrd.py
  function lr_scale_func (line 28) | def lr_scale_func(key):
  function get_param_groups (line 45) | def get_param_groups(model, no_weight_decay_cond, scale_lr_cond):
  function unwrap_model (line 104) | def unwrap_model(model: nn.Module) -> nn.Module:
  class GOTTrainer (line 118) | class GOTTrainer(Trainer):
    method _safe_save (line 120) | def _safe_save(self, output_dir: str):
    method _save (line 132) | def _save(self, output_dir: Optional[str] = None, state_dict=None):
    method create_optimizer (line 158) | def create_optimizer(self):
    method _wrap_model (line 193) | def _wrap_model(self, model, training=True, dataloader=None):

FILE: GOT-OCR-2.0-master/GOT/train/trainer_vit_fixlr.py
  function unwrap_model (line 11) | def unwrap_model(model: nn.Module) -> nn.Module:
  class GOTTrainer (line 25) | class GOTTrainer(Trainer):
    method _safe_save (line 27) | def _safe_save(self, output_dir: str):
    method _save (line 39) | def _save(self, output_dir: Optional[str] = None, state_dict=None):
    method create_optimizer (line 65) | def create_optimizer(self):

FILE: GOT-OCR-2.0-master/GOT/train/trainer_vit_llrd.py
  function lr_scale_func (line 28) | def lr_scale_func(key):
  function get_param_groups (line 42) | def get_param_groups(model, no_weight_decay_cond, scale_lr_cond, lr, wd):
  function unwrap_model (line 101) | def unwrap_model(model: nn.Module) -> nn.Module:
  class GOTTrainer (line 115) | class GOTTrainer(Trainer):
    method _safe_save (line 117) | def _safe_save(self, output_dir: str):
    method _save (line 129) | def _save(self, output_dir: Optional[str] = None, state_dict=None):
    method create_optimizer (line 155) | def create_optimizer(self):
    method _wrap_model (line 190) | def _wrap_model(self, model, training=True, dataloader=None):

FILE: GOT-OCR-2.0-master/GOT/utils/arguments.py
  class ModelArguments (line 7) | class ModelArguments:
  class DataArguments (line 19) | class DataArguments:
  class TrainingArguments (line 34) | class TrainingArguments(transformers.TrainingArguments):

FILE: GOT-OCR-2.0-master/GOT/utils/conversation.py
  class SeparatorStyle (line 6) | class SeparatorStyle(Enum):
  class Conversation (line 43) | class Conversation:
    method get_prompt (line 56) | def get_prompt(self):
    method append_message (line 113) | def append_message(self, role, message):
    method get_images (line 116) | def get_images(self, return_pil=False):
    method to_gradio_chatbot (line 167) | def to_gradio_chatbot(self):
    method copy (line 197) | def copy(self):
    method dict (line 207) | def dict(self):

FILE: GOT-OCR-2.0-master/GOT/utils/utils.py
  function build_logger (line 18) | def build_logger(logger_name, logger_filename):
  class StreamToLogger (line 61) | class StreamToLogger(object):
    method __init__ (line 65) | def __init__(self, logger, log_level=logging.INFO):
    method __getattr__ (line 71) | def __getattr__(self, attr):
    method write (line 74) | def write(self, buf):
    method flush (line 88) | def flush(self):
  function disable_torch_init (line 94) | def disable_torch_init():
  function violates_moderation (line 103) | def violates_moderation(text):
  function pretty_print_semaphore (line 124) | def pretty_print_semaphore(semaphore):
  class KeywordsStoppingCriteria (line 130) | class KeywordsStoppingCriteria(StoppingCriteria):
    method __init__ (line 131) | def __init__(self, keywords, tokenizer, input_ids):
    method __call__ (line 139) | def __call__(self, output_ids: torch.LongTensor, scores: torch.FloatTe...
  function smart_tokenizer_and_embedding_resize (line 153) | def smart_tokenizer_and_embedding_resize(special_tokens_dict, tokenizer,...
  function maybe_zero_3 (line 179) | def maybe_zero_3(param, ignore_status=False, name=None):
  function get_peft_state_maybe_zero_3 (line 194) | def get_peft_state_maybe_zero_3(named_params, bias):
  function get_peft_state_non_lora_maybe_zero_3 (line 219) | def get_peft_state_non_lora_maybe_zero_3(named_params, require_grad_only...
  function find_all_linear_names (line 227) | def find_all_linear_names(model):