ModuleNotFoundError: No module named 'dalle_pytorch'

[wolfgangmeyers]

Received this error after following instructions to run sampling:

python sample.py --model_path finetune.pt --batch_size 6 --text "a cyberpunk girl with a scifi neuralink device on her head | cyberpunk anime girl"
Traceback (most recent call last):
  File "sample.py", line 19, in <module>
    from dalle_pytorch import DiscreteVAE, VQGanVAE
ModuleNotFoundError: No module named 'dalle_pytorch'

[wolfgangmeyers]

After downloading and installing dalle_pytorch, a new error shows up:

python sample.py --model_path finetune.pt --batch_size 6 --text "a cyberpunk girl with a scifi neuralink device on her head | cyberpunk anime girl"
c:\users\wolfg\code\latent-diffusion\src\clip\clip\clip.py:24: UserWarning: PyTorch version 1.7.1 or higher is recommended
  warnings.warn("PyTorch version 1.7.1 or higher is recommended")
Using device: cuda:0
Traceback (most recent call last):
  File "sample.py", line 269, in <module>
    model, diffusion = create_model_and_diffusion(**model_config)
  File "C:\Users\wolfg\code\glid-3-xl\guided_diffusion\script_util.py", line 109, in create_model_and_diffusion
    model = create_model(
  File "C:\Users\wolfg\code\glid-3-xl\guided_diffusion\script_util.py", line 189, in create_model
    return UNetModel(
  File "C:\Users\wolfg\code\glid-3-xl\guided_diffusion\unet.py", line 603, in __init__
    self.clip_proj = nn.Linear(clip_embed_dim, time_embed_dim, dtype=self.dtype)
TypeError: __init__() got an unexpected keyword argument 'dtype'

[wolfgangmeyers]

I upgraded pytorch to 1.7.1 but the error persists...

[limiteinductive]

did you installed ldm from this repo: https://github.com/CompVis/latent-diffusion ?
if you did could you send the output of you pip freeze?

[limiteinductive]

and probably upgrading to pytorch 1.10 should solve your particular issue: https://pytorch.org/get-started/locally/

[wolfgangmeyers]

Pip freeze (in the current state):

absl-py==1.0.0
aiohttp==3.8.1
aiosignal==1.2.0
albumentations==0.4.3
altair==4.2.0
antlr4-python3-runtime==4.8
argon2-cffi==21.3.0
argon2-cffi-bindings==21.2.0
asttokens==2.0.5
async-timeout==4.0.2
atomicwrites==1.4.0
attrs==21.4.0
axial-positional-embedding==0.2.1
backcall==0.2.0
backports.zoneinfo==0.2.1
beautifulsoup4==4.11.1
bleach==5.0.0
blinker==1.4
blobfile==1.3.0
braceexpand==0.1.7
cachetools==5.0.0
certifi==2021.10.8
cffi==1.15.0
charset-normalizer==2.0.12
click==8.0.4
-e git+https://github.com/openai/CLIP.git@b4ae44927b78d0093b556e3ce43cbdcff422017a#egg=clip
colorama==0.4.4
Cython==0.29.28
DALL-E==0.1
-e git+https://github.com/lucidrains/DALLE-pytorch.git@fcd35de4571b50e2d051826514dafc0bd0c69d98#egg=dalle_pytorch
dataclasses==0.6
debugpy==1.6.0
decorator==5.1.1
defusedxml==0.7.1
einops==0.4.1
entrypoints==0.4
executing==0.8.3
fastjsonschema==2.15.3
filelock==3.6.0
frozenlist==1.3.0
fsspec==2022.3.0
ftfy==6.1.1
future==0.18.2
gitdb==4.0.9
GitPython==3.1.27
google-auth==2.6.6
google-auth-oauthlib==0.4.6
grpcio==1.44.0
-e git+https://github.com/Jack000/glid-3-xl.git@a0b5be4b04378d4d4779240d3e0a599360c1a133#egg=guided_diffusion
idna==3.3
imageio==2.9.0
imageio-ffmpeg==0.4.2
imgaug==0.2.6
importlib-metadata==4.11.3
importlib-resources==5.7.1
iniconfig==1.1.1
ipykernel==6.13.0
ipython==8.3.0
ipython-genutils==0.2.0
ipywidgets==7.7.0
jedi==0.18.1
Jinja2==3.1.2
joblib==1.1.0
jsonschema==4.4.0
jupyter-client==7.3.0
jupyter-core==4.10.0
jupyterlab-pygments==0.2.2
jupyterlab-widgets==1.1.0
-e git+https://github.com/CompVis/latent-diffusion.git@5a6571e384f9a9b492bbfaca594a2b00cad55279#egg=latent_diffusion
Markdown==3.3.6
MarkupSafe==2.1.1
matplotlib-inline==0.1.3
mistune==0.8.4
mkl-fft==1.3.0
mkl-random==1.1.1
mkl-service==2.3.0
multidict==6.0.2
mypy==0.950
mypy-extensions==0.4.3
nbclient==0.6.0
nbconvert==6.5.0
nbformat==5.3.0
nest-asyncio==1.5.5
networkx==2.8
notebook==6.4.11
numpy @ file:///C:/ci/numpy_and_numpy_base_1603466732592/work
oauthlib==3.2.0
omegaconf==2.1.1
opencv-python==4.1.2.30
opencv-python-headless==4.5.5.64
packaging==21.3
pandas==1.4.2
pandocfilters==1.5.0
parso==0.8.3
pickleshare==0.7.5
Pillow==9.0.1
pluggy==1.0.0
prometheus-client==0.14.1
prompt-toolkit==3.0.29
protobuf==3.20.1
psutil==5.9.0
pudb==2019.2
pure-eval==0.2.2
py==1.11.0
pyarrow==7.0.0
pyasn1==0.4.8
pyasn1-modules==0.2.8
pycparser==2.21
pycryptodomex==3.14.1
pydeck==0.7.1
pyDeprecate==0.3.1
Pygments==2.12.0
Pympler==1.0.1
pyparsing==3.0.8
pyrsistent==0.18.1
pytest==7.1.2
python-dateutil==2.8.2
pytorch-lightning==1.4.2
pytz==2022.1
pytz-deprecation-shim==0.1.0.post0
PyWavelets==1.3.0
pywin32==303
pywinpty==2.0.5
PyYAML==6.0
pyzmq==22.3.0
regex==2022.4.24
requests==2.27.1
requests-oauthlib==1.3.1
rotary-embedding-torch==0.1.5
rsa==4.8
sacremoses==0.0.49
scikit-image==0.19.2
scipy==1.8.0
semver==2.13.0
Send2Trash==1.8.0
six @ file:///tmp/build/80754af9/six_1644875935023/work
smmap==5.0.0
soupsieve==2.3.2.post1
stack-data==0.2.0
streamlit==1.8.1
-e git+https://github.com/CompVis/taming-transformers.git@24268930bf1dce879235a7fddd0b2355b84d7ea6#egg=taming_transformers
taming-transformers-rom1504==0.0.6
tensorboard==2.9.0
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.1
terminado==0.13.3
test-tube==0.7.5
tifffile==2022.4.28
tinycss2==1.1.1
tokenizers==0.10.3
toml==0.10.2
tomli==2.0.1
toolz==0.11.2
torch==1.7.1
torch-fidelity==0.3.0
torchmetrics==0.6.0
torchvision==0.8.1
tornado==6.1
tqdm==4.64.0
traitlets==5.1.1
transformers==4.3.1
typing-extensions @ file:///opt/conda/conda-bld/typing_extensions_1647553014482/work
tzdata==2022.1
tzlocal==4.2
urllib3==1.26.9
urwid==2.1.2
validators==0.18.2
watchdog==2.1.7
wcwidth==0.2.5
webdataset==0.2.5
webencodings==0.5.1
Werkzeug==2.1.2
widgetsnbextension==3.6.0
wincertstore==0.2
xmltodict==0.12.0
yarl==1.7.2
youtokentome==1.0.6
zipp==3.8.0

[wolfgangmeyers]

installing pytorch 1.11, I'll let you know how that goes

[wolfgangmeyers]

new error:

python sample.py --model_path finetune.pt --batch_size 6 --text "a cyberpunk girl with a scifi neuralink device on her head | cyberpunk anime girl"
Using device: cuda:0
C:\Users\wolfg\anaconda3\envs\ldm\lib\site-packages\torch\nn\__init__.py
100%|███████████████████████████████████████| 890M/890M [02:40<00:00, 5.80MiB/s]
  0%|                                                                                           | 0/27 [00:00<?, ?it/s]Traceback (most recent call last):
  File "sample.py", line 522, in <module>
    do_run()
  File "sample.py", line 517, in do_run
    save_sample(i, sample)
  File "sample.py", line 470, in save_sample
    with open(npy_filename, 'wb') as outfile:
FileNotFoundError: [Errno 2] No such file or directory: 'output_npy/00000.npy'

After creating output_npy:

python sample.py --model_path finetune.pt --batch_size 6 --text "a cyberpunk girl with a scifi neuralink device on her head | cyberpunk anime girl"
Using device: cuda:0
C:\Users\wolfg\anaconda3\envs\ldm\lib\site-packages\torch\nn\__init__.py
  0%|                                                                                           | 0/27 [00:00<?, ?it/s]Traceback (most recent call last):
  File "sample.py", line 522, in <module>
    do_run()
  File "sample.py", line 517, in do_run
    save_sample(i, sample)
  File "sample.py", line 476, in save_sample
    out.save(filename)
  File "C:\Users\wolfg\anaconda3\envs\ldm\lib\site-packages\PIL\Image.py", line 2209, in save
    fp = builtins.open(filename, "w+b")
FileNotFoundError: [Errno 2] No such file or directory: 'output/00000.png'

[wolfgangmeyers]

I created a couple of output folders, and got the sampling working. Probably worth adding (if not exists, create folder) logic, and updating the docs to mention need for updated pytorch (latent diffusion installs an old version)

[wolfgangmeyers]

I updated to pytorch 1.11. And the sampling is working! Thanks for the help.