Official implementation for the paper "Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation", published at ICCV'23.
I have encountered an issue that seems difficult to resolve. Could you kindly take a look and assist me with it? Thank you very much!
Traceback (most recent call last):
File "src/main.py", line 158, in
main(params)
File "src/main.py", line 40, in main
model = MODEL(params)
File "src/models/model.py", line 24, in init
self.clip = M_CLIP(params)
File "src/models/clip_comb.py", line 13, in init
self.text_encoder, self.text_preprocessor = MClip.from_pretrained(model_name_or_path), AutoTokenizer.from_pretrained(model_name_or_path)
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/modeling_utils.py", line 2959, in from_pretrained
model = cls(config, *model_args, *model_kwargs)
File "src/models/mclip.py", line 7, in init
super().init(config, args, **kwargs)
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/multilingual_clip/pt_multilingual_clip.py", line 11, in init
self.transformer = transformers.AutoModel.from_pretrained(config.modelBase)
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/models/auto/auto_factory.py", line 527, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/models/auto/configuration_auto.py", line 1039, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/models/auto/configuration_auto.py", line 734, in getitem
raise KeyError(key)
KeyError: 'M-CLIP'
Hello,
I have encountered an issue that seems difficult to resolve. Could you kindly take a look and assist me with it? Thank you very much!
Traceback (most recent call last): File "src/main.py", line 158, in
main(params)
File "src/main.py", line 40, in main
model = MODEL(params)
File "src/models/model.py", line 24, in init
self.clip = M_CLIP(params)
File "src/models/clip_comb.py", line 13, in init
self.text_encoder, self.text_preprocessor = MClip.from_pretrained(model_name_or_path), AutoTokenizer.from_pretrained(model_name_or_path)
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/modeling_utils.py", line 2959, in from_pretrained
model = cls(config, *model_args, *model_kwargs)
File "src/models/mclip.py", line 7, in init
super().init(config, args, **kwargs)
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/multilingual_clip/pt_multilingual_clip.py", line 11, in init
self.transformer = transformers.AutoModel.from_pretrained(config.modelBase)
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/models/auto/auto_factory.py", line 527, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/models/auto/configuration_auto.py", line 1039, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/home/xutianjiao/miniconda3/envs/cliptrans/lib/python3.8/site-packages/transformers/models/auto/configuration_auto.py", line 734, in getitem
raise KeyError(key)
KeyError: 'M-CLIP'