NameError: name 'trainer' is not defined about dreambooth-stable-diffusion HOT 9 CLOSED

Just got this as well but not sure the source is the same

Traceback (most recent call last):
  File "main.py", line 670, in <module>
    model = load_model_from_config(config, opt.actual_resume)
  File "main.py", line 30, in load_model_from_config
    pl_sd = torch.load(ckpt, map_location="cpu")
  File "/opt/conda/lib/python3.7/site-packages/torch/serialization.py", line 699, in load
    with _open_file_like(f, 'rb') as opened_file:
  File "/opt/conda/lib/python3.7/site-packages/torch/serialization.py", line 230, in _open_file_like
    return _open_file(name_or_buffer, mode)
  File "/opt/conda/lib/python3.7/site-packages/torch/serialization.py", line 211, in __init__
    super(_open_file, self).__init__(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'model.ckpt'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "main.py", line 888, in <module>
    if trainer.global_rank == 0:
NameError: name 'trainer' is not defined

from dreambooth-stable-diffusion.

You do not have stable diffusion model downloaded to directory of the repo :)
You need have model.ckpt in folder.
@Mozoloa

from dreambooth-stable-diffusion.

I've always had it since I'm using the same environment since the beginning, that wasn't the glitch.

Apparently, shutting down the kernel and turning it back on was the solution ? odd

from dreambooth-stable-diffusion.

folder ./src/taming_transformers wasn't downloaded.

from dreambooth-stable-diffusion.

try to make your library version same as in enviroment.yaml file

dependencies:

• python=3.8.10
• pip=20.3
• cudatoolkit=11.3
• pytorch=1.10.2
• torchvision=0.11.3
• numpy=1.22.3
• pip:
  • albumentations==1.1.0
  • opencv-python==4.2.0.34
  • pudb==2019.2
  • imageio==2.14.1
  • imageio-ffmpeg==0.4.7
  • pytorch-lightning==1.5.9
  • omegaconf==2.1.1
  • test-tube>=0.7.5
  • streamlit>=0.73.1
  • setuptools==59.5.0
  • pillow==9.0.1
  • einops==0.4.1
  • torch-fidelity==0.3.0
  • transformers==4.18.0
  • torchmetrics==0.6.0
  • kornia==0.6
  • -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
  • -e git+https://github.com/openai/CLIP.git@main#egg=clip
  • -e .

from dreambooth-stable-diffusion.

Got the same error, and could not find a way to fix it:

File "/venv/lib/python3.10/site-packages/torch/cuda/init.py", line 217, in _lazy_init
torch._C._cuda_init()
RuntimeError: No CUDA GPUs are available

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/workspace/Dreambooth-Stable-Diffusion/main.py", line 896, in
if trainer.global_rank == 0:
NameError: name 'trainer' is not defined. Did you mean: 'Trainer'?

from dreambooth-stable-diffusion.

Looks like you are using python 3.10, try python=3.8.10

from dreambooth-stable-diffusion.

How can I do it when using colab notebook ?

from dreambooth-stable-diffusion.

Potentially related (NameError: name 'trainer' is not defined):

• #28
• #53
• #86
• #87

I went to line 896 on Main.py, and changed "trainer" for "Trainer", now it's working

Originally posted by @Pegaxsus in #86 (comment)

from dreambooth-stable-diffusion.