-
Notifications
You must be signed in to change notification settings - Fork 155
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
RuntimeError: Error(s) in loading state_dict for StreamingSVD: Unexpected key(s) in state_dict: "conditioner.embedders.0.open_clip.model.ln_final.bias" #62
Comments
Hi @jiyuwangbupt , please check this issue: #59 |
I created an image and ran it in a Docker container. pip freeze >> requirements.txt torch==2.0.1 Editable install with no version control (videosys==2.0.0) |
root@a2f93364212e:/mnt/host/data/StreamingT2V# pip install -r requirements.txt |
Due to my location in mainland China, I am unable to automatically download the Hugging Face model weights. Therefore, I downloaded them manually and stored them in a local path. I changed the model path to an absolute path and modified the pretrained_model path in diffusers/pipelines/pipeline_utils.py to an absolute path as well. I'm not sure if this will have any impact. |
Hi @jiyuwangbupt, unfortunately, I cannot reproduce your issue. |
--- START: Loading module: conditioner ---
�[93mWarning: Seems object conditioner was not build correct.�[0m
--- FINSHED: Loading module: conditioner ---
LOADING TRAINED WEIGHTS
Traceback (most recent call last):
File "/mnt/host/data/StreamingT2V/code/inference_i2v.py", line 218, in
generator = StreamingPipeline()
File "/mnt/host/data/StreamingT2V/code/inference_i2v.py", line 62, in init
return_dict = self.init_model(cli)
File "/mnt/host/data/StreamingT2V/code/inference_i2v.py", line 138, in init_model
model.load_state_dict(ckpt) # load trained model
File "/data/eas/ENV/lib/python3.9/site-packages/torch/nn/modules/module.py", line 2041, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for StreamingSVD:
Unexpected key(s) in state_dict: "conditioner.embedders.0.open_clip.model.ln_final.bias", "conditioner.embedders.0.open_clip.model.ln_final.weight"
The text was updated successfully, but these errors were encountered: