txh-mercury / cosa Goto Github PK

I got the pretrained model, how to run the test app for videocaption generation?

As the title says, when I run zero-shot inference with, for example, ActivityNet, from pre-trained weights, I get this warning once per batch. The final retrieval results seem plausible, so I'm wondering if this warning message is to be expected, or if it indicates some broken environment on my end.

Here is the information:
Traceback (most recent call last):
File "/opt/conda/lib/python3.8/runpy.py", line 185, in _run_module_as_main
mod_name, mod_spec, code = _get_module_details(mod_name, _Error)
File "/opt/conda/lib/python3.8/runpy.py", line 111, in _get_module_details
import(pkg_name)
File "COSA/env/lib/python3.8/site-packages/torch/init.py", line 527, in
class DoubleStorage(_C.DoubleStorageBase, _StorageBase):
AttributeError: module 'torch._C' has no attribute 'DoubleStorageBase'

I also tried different version of torch, got other errors

Thanks for your nice work! I notice that the bert-base-uncased-crossattn in your code seem to be different from the ones everyone uses (bert-base-uncased), and I find that the weight of cross attention is in your pytorch.bin, which we usually initialize it randomly.