init

GroundingDINO/groundingdino/models/__init__.py

+# ------------------------------------------------------------------------
+# Grounding DINO
+# url: https://github.com/IDEA-Research/GroundingDINO
+# Copyright (c) 2023 IDEA. All Rights Reserved.
+# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
+# ------------------------------------------------------------------------
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+from .GroundingDINO import build_groundingdino
+
+
+def build_model(args):
+    # we use register to maintain models from catdet6 on.
+    from .registry import MODULE_BUILD_FUNCS
+
+    assert args.modelname in MODULE_BUILD_FUNCS._module_dict
+    build_func = MODULE_BUILD_FUNCS.get(args.modelname)
+    model = build_func(args)
+    return model

GroundingDINO/groundingdino/models/registry.py

+# ------------------------------------------------------------------------
+# Grounding DINO
+# url: https://github.com/IDEA-Research/GroundingDINO
+# Copyright (c) 2023 IDEA. All Rights Reserved.
+# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
+# ------------------------------------------------------------------------
+# -*- coding: utf-8 -*-
+# @Author: Yihao Chen
+# @Date:   2021-08-16 16:03:17
+# @Last Modified by:   Shilong Liu
+# @Last Modified time: 2022-01-23 15:26
+# modified from mmcv
+
+import inspect
+from functools import partial
+
+
+class Registry(object):
+    def __init__(self, name):
+        self._name = name
+        self._module_dict = dict()
+
+    def __repr__(self):
+        format_str = self.__class__.__name__ + "(name={}, items={})".format(
+            self._name, list(self._module_dict.keys())
+        )
+        return format_str
+
+    def __len__(self):
+        return len(self._module_dict)
+
+    @property
+    def name(self):
+        return self._name
+
+    @property
+    def module_dict(self):
+        return self._module_dict
+
+    def get(self, key):
+        return self._module_dict.get(key, None)
+
+    def registe_with_name(self, module_name=None, force=False):
+        return partial(self.register, module_name=module_name, force=force)
+
+    def register(self, module_build_function, module_name=None, force=False):
+        """Register a module build function.
+        Args:
+            module (:obj:`nn.Module`): Module to be registered.
+        """
+        if not inspect.isfunction(module_build_function):
+            raise TypeError(
+                "module_build_function must be a function, but got {}".format(
+                    type(module_build_function)
+                )
+            )
+        if module_name is None:
+            module_name = module_build_function.__name__
+        if not force and module_name in self._module_dict:
+            raise KeyError("{} is already registered in {}".format(module_name, self.name))
+        self._module_dict[module_name] = module_build_function
+
+        return module_build_function
+
+
+MODULE_BUILD_FUNCS = Registry("model build functions")

GroundingDINO/groundingdino/util/__init__.py

+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved

GroundingDINO/groundingdino/util/get_tokenlizer.py

+from transformers import AutoTokenizer, BertModel, BertTokenizer, RobertaModel, RobertaTokenizerFast
+
+
+def get_tokenlizer(text_encoder_type):
+    if not isinstance(text_encoder_type, str):
+        # print("text_encoder_type is not a str")
+        if hasattr(text_encoder_type, "text_encoder_type"):
+            text_encoder_type = text_encoder_type.text_encoder_type
+        elif text_encoder_type.get("text_encoder_type", False):
+            text_encoder_type = text_encoder_type.get("text_encoder_type")
+        else:
+            raise ValueError(
+                "Unknown type of text_encoder_type: {}".format(type(text_encoder_type))
+            )
+    print("final text_encoder_type: {}".format(text_encoder_type))
+
+    tokenizer = AutoTokenizer.from_pretrained(text_encoder_type)
+    return tokenizer
+
+
+def get_pretrained_language_model(text_encoder_type):
+    if text_encoder_type == "bert-base-uncased":
+        return BertModel.from_pretrained(text_encoder_type)
+    if text_encoder_type == "roberta-base":
+        return RobertaModel.from_pretrained(text_encoder_type)
+    raise ValueError("Unknown text_encoder_type {}".format(text_encoder_type))