lucazanella/lavad
Official implementation of "Harnessing Large Language Models for Training-free Video Anomaly Detection", CVPR 2024
Python
Issues
- 3
RuntimeError: shape mismatch: value tensor of shape [4194304] cannot be broadcast to indexing result of shape [0]
#18 opened by Gerry048 - 5
- 5
About the randomness of LLMs
#14 opened by jorgeportilla202231013 - 4
Step4: 04_query_llm.sh AssertionError: no checkpoint files found in libs/llama/llama-2-13b-chat/
#16 opened by Puqi7 - 3
llama-2-13b-chat
#6 opened by JaneShiys - 2
question in src/eval.py
#11 opened by shenshenaini - 0
- 2
A problem about step2:creat_index for XD.
#13 opened by KirinHao - 4
Can not open the dowloaded data file
#10 opened by Xandra298 - 1
Step4: No module named fairscale.nn
#12 opened by witty1011 - 5
- 2
What is frame_interval in scripts/01_caption.sh?
#8 opened by ut21 - 2
Errors on my own dataset.
#7 opened by LBAMAD - 5
how did you run caption?
#5 opened by Justhuayu - 1
release code
#3 opened by zzxzzt333 - 1
Dataset development
#4 opened by Libyte - 2
Congrats on the nice work!
#2 opened by wyzjack - 1