Open AndrewZion opened 2 months ago
HI,
I will check that but I am not sure that I can find the original code. Because so much time has passed, the code for this project may have been deleted
If you are interested in the multimodal generation, you can also read our other paper: V2P: Vision-to-Prompt based Multi-Modal Product Summary Generation Adapting Generative Pretrained Language Model for Open-domain Multimodal Sentence Summarization. Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation.
For the img_encoder.pkl, we downloaded it from timm package.
train 62000 valid 2000 test 2000 Traceback (most recent call last): File "main.py", line 131, in
model = MultiModal_BART(config)
File "/home/xlb/code_work/multimodal_summarization/Vision-GPLM-main/fine-tuning/models.py", line 67, in init
self.img_encoder = torch.load("./img_encoder.pkl")
File "/home/xlb/.conda/envs/py36_env/lib/python3.6/site-packages/torch/serialization.py", line 594, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/xlb/.conda/envs/py36_env/lib/python3.6/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/xlb/.conda/envs/py36_env/lib/python3.6/site-packages/torch/serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './img_encoder.pkl'
Hello, in the fine-tuning training phase, in the file models.py, self.img_encoder = torch.load("./img_encoder.pkl"), I did not find the img_encoder.pkl file. After post-training training, I did not find the saved img_encoder.pkl file.