Closed Z-MU-Z closed 1 year ago
After I reconfigured the environment following the official steps, the above bug seems to have been fixed. However, a new bug has emerged.
Traceback (most recent call last):
File "guide_gligen.py", line 587, in
Hi,
you should include --file_save
in the script to run guide_gligen.py
Hi! Thanks for your great work! when I run this command python guide_gligen.py --ckpt weights/gligen/diffusion_pytorch_model.bin --type counting --box_pickle data_evaluate_LLM/gpt_generated_box/counting.p
it throws the below error: Traceback (most recent call last): File "/mnt/nas/share/home/zmz/code/attention-refocusing/guide_gligen.py", line 539, in
models = load_ckpt(meta_list[0]["ckpt"])
File "/mnt/nas/share/home/zmz/code/attention-refocusing/guide_gligen.py", line 88, in load_ckpt
text_encoder.load_state_dict( saved_ckpt["text_encoder"] )
File "/home/zmz/miniconda3/envs/fsdet110/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1482, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for FrozenCLIPEmbedder:
Unexpected key(s) in state_dict: "transformer.text_model.embeddings.position_ids".
Do you know how to fix this?