error raise when finetuning groundingdino 微调groudingdino train test报错

[xuans29]

i downloaded branch dev-3.x and builded the environment with following commands on ubuntu system：

conda create --name mmdet python=3.8 -y conda activate mmdet pip install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu118 pip install -U openmim mim install mmengine mim install "mmcv>=2.0.0" mim install mmdet mim install mmdet[multimodal] then i downloaded the catdataset and copied following codes to grounding_dino_swin-t_finetune_16xb2_1x_coco.py for i cant connect to hugginface directly: ` base = [ '../base/datasets/coco_detection.py', '../base/schedules/schedule_1x.py', '../base/default_runtime.py' ] load_from = 'https://download.openmmlab.com/mmdetection/v3.0/grounding_dino/groundingdino_swint_ogc_mmdet-822d7e9d.pth' # noqa lang_model_name = 'bert-base-uncased' ################ from transformers import BertConfig, BertModel from transformers import AutoTokenizer

config = BertConfig.from_pretrained("bert-base-uncased") model = BertModel.from_pretrained("bert-base-uncased", add_pooling_layer=False, config=config) tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")

config.save_pretrained("E:\pythonProject\post_graduate\mmdet\mmdetection-dev-3.x\bert-base-uncased") model.save_pretrained("E:\pythonProject\post_graduate\mmdet\mmdetection-dev-3.x\bert-base-uncased") tokenizer.save_pretrained("E:\pythonProject\post_graduate\mmdet\mmdetection-dev-3.x\bert-base-uncased") ################# model = dict( type='GroundingDINO', num_queries=900, with_box_refine=True, ........ **i tried to run the code on 3090 GPU:** cd mmdetection-dev-3.x python tools/test.py configs/grounding_dino/grounding_dino_swin-t_finetune_8xb2_20e_cat.py https://download.openmmlab.com/mmdetection/v3.0/grounding_dino/groundingdino_swint_ogc_mmdet-822d7e9d.pth ` whatever train or test,the same error occurs:

Traceback (most recent call last): File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf/pytree/pytree_utils.py", line 113, in ParseCodeToTree tree = parser_driver.parse_string(code, debug=False) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf_third_party/_ylib2to3/pgen2/driver.py", line 188, in parse_string return self.parse_tokens(tokens, debug) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf_third_party/_ylib2to3/pgen2/driver.py", line 157, in parse_tokens if p.addtoken(type, value, (prefix, start)): File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf_third_party/_ylib2to3/pgen2/parse.py", line 230, in addtoken return self._addtoken(ilabel, type, value, context) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf_third_party/_ylib2to3/pgen2/parse.py", line 313, in _addtoken raise ParseError('bad input', type, value, context) yapf_third_party._ylib2to3.pgen2.parse.ParseError: bad input: type=20, value='<', context=('', (1, 14))

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf/yapflib/yapf_api.py", line 198, in FormatCode tree = pytree_utils.ParseCodeToTree(unformatted_source) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf/pytree/pytree_utils.py", line 116, in ParseCodeToTree ast.parse(code) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/ast.py", line 47, in parse return compile(source, filename, mode, flags, File "<unknown>", line 1 AutoTokenizer=<class 'transformers.models.auto.tokenization_auto.AutoTokenizer'> ^ SyntaxError: invalid syntax

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/mmengine/config/config.py", line 1483, in pretty_text text, _ = FormatCode(text, style_config=yapf_style) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/yapf/yapflib/yapf_api.py", line 201, in FormatCode raise errors.YapfError(errors.FormatErrorMsg(e)) yapf.yapflib.errors.YapfError: <unknown>:1:15: invalid syntax

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "tools/test.py", line 149, in <module> main() File "tools/test.py", line 131, in main runner = Runner.from_cfg(cfg) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/mmengine/runner/runner.py", line 462, in from_cfg runner = cls( File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/mmengine/runner/runner.py", line 403, in init self._log_env(env_cfg) File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/mmengine/runner/runner.py", line 2388, in _log_env self.logger.info(f'Config:\n{self.cfg.pretty_text}') File "/home/dell/Software/Anaconda3/envs/mmdet/lib/python3.8/site-packages/mmengine/config/config.py", line 1488, in pretty_text raise SyntaxError('Failed to format the config file, please ' SyntaxError: Failed to format the config file, please check the syntax of: AutoTokenizer=<class 'transformers.models.auto.tokenization_auto.AutoTokenizer'> BertConfig=<class 'transformers.models.bert.configuration_bert.BertConfig'> BertModel=<class 'transformers.models.bert.modeling_bert.BertModel'> auto_scale_lr=dict( base_batch_size=16, enable=False) backend_args=None class_name=( 'cat', ) data_root='data/' dataset_type='CocoDataset' default_hooks=dict( checkpoint=dict( .........

i think there might be something wrong in my steps,but i cant figure it out,i also tried to run on windows with different torch versions,but the error still occurs,maybe i didnt put the bert-base-uncased code in the correct position,looking forward to your reply