Open ubless607 opened 4 months ago
I've set jit=False
when loading clip("VIT-B/32")
due to https://github.com/xukechun/Vision-Language-Grasping/issues/10.
Hi, it seems that the pretrained clip model is not loaded correctly. Did you download the clip VIT-B/32 model offline? BTW, we reorganize our codes with some bugs fixed. You can reclone the repo and run setup.py again without any new installation.
No, I used the integrated script.
Hi @xukechun,
I have a temporary fix for the issue. Adding the following line of code at line 489 makes the code run. Let me know if there’s anything else I can assist with to fix this issue.
state_dict["input_resolution"], state_dict["context_length"], state_dict["vocab_size"] = None, None, None
Hi, if you use the integrated script, you don't need to set jit=False.
I ran the evaluation code with pre-trained weight. Can you help me?