__init__() missing 1 required positional argument: 'temperature'

[davidecarnevali]

I cloned the repository and run:
autoalbument-search --config-dir autoalbument/examples/cifar10/

But I got the following error (the same with imagenet and svhn)

Error executing job with overrides: []
Traceback (most recent call last):
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 62, in _call_target
return target(*args, **kwargs)
TypeError: init() missing 1 required positional argument: 'temperature'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/users/dcar/anaconda3/envs/pytorch/bin/autoalbument-search", line 8, in
sys.exit(main())
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/main.py", line 48, in decorated_main
_run_hydra(
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/utils.py", line 377, in _run_hydra
run_and_report(
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/utils.py", line 214, in run_and_report
raise ex
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/utils.py", line 211, in run_and_report
return func()
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/utils.py", line 378, in
lambda: hydra.run(
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/hydra.py", line 111, in run
_ = ret.return_value
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/core/utils.py", line 233, in return_value
raise self._return_value
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/core/utils.py", line 160, in run_job
ret.return_value = task_function(task_cfg)
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/autoalbument/cli/search.py", line 54, in main
searcher = instantiate(cfg.searcher, cfg=cfg)
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 180, in instantiate
return instantiate_node(config, *args, recursive=recursive, convert=convert)
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 245, in instantiate_node
value = instantiate_node(
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 266, in instantiate_node
cfg[key] = instantiate_node(
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 266, in instantiate_node
cfg[key] = instantiate_node(
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 223, in instantiate_node
items = [
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 224, in
instantiate_node(item, convert=convert, recursive=recursive)
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 249, in instantiate_node
return _call_target(target, *args, **kwargs)
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 64, in _call_target
raise type(e)(
File "/users/dcar/anaconda3/envs/pytorch/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 62, in _call_target
return target(*args, **kwargs)
TypeError: Error instantiating 'autoalbument.faster_autoaugment.models.policy_operations.ShiftRGB' : init() missing 1 required positional argument: 'temperature'

My versions are:
albumentations 1.0.3
autoalbument 0.4.0

Any hint?

Thx

[coallar]

Hi, do you solve this problem?

[davidecarnevali]

Hi,
yes, I solved this morning by using a fresh installation of pytorch 1.8.2 with cuda 10.2 in a new python virtual environment
I believe I had a system problem/conflict.

D

[adam-j-kelly]

Hi, I'm having this issue too but can't find pytorch 1.8.2, do you have any more details about how to solve the problem? They would be much appreciated!

[davidecarnevali]

Hi,
here you can find previous pytorch versions
https://pytorch.org/get-started/previous-versions/

However, I updated to 1.9 and it still works, thus I believe you should create a fresh python virtual environment with pytorch 1.9 and albumentations only, avoiding any conflict with other packages

[kompaso]

@adam-j-kelly

Did this solution help you? I tried a different version of torch, but it doesn't work. Log is the same.

[adam-j-kelly]

@kompaso eventually I did get it working, I think partly due to the above. I created a 3.9.7 venv with the following package versions, although my understanding is that your torchvision/cuda might need to be different depending on hardware:

absl-py==0.11.0
aiohttp==3.7.3
albumentations==0.5.2
antlr4-python3-runtime==4.8
async-timeout==3.0.1
attrs==20.3.0
autoalbument==0.4.0
cachetools==4.2.1
certifi==2020.12.5
chardet==3.0.4
click==7.1.2
colorama==0.4.4
cycler==0.10.0
decorator==4.4.2
efficientnet-pytorch==0.6.3
fsspec==0.8.5
future==0.18.2
google-auth==1.27.0
google-auth-oauthlib==0.4.2
grpcio==1.35.0
hydra-core==1.0.6
idna==2.10
imageio==2.9.0
imgaug==0.4.0
importlib-resources==5.1.0
kiwisolver==1.3.1
Markdown==3.3.3
matplotlib==3.3.4
multidict==5.1.0
munch==2.5.0
networkx==2.5
numpy==1.20.1
oauthlib==3.1.0
omegaconf==2.0.6
opencv-python==4.5.1.48
opencv-python-headless==4.5.1.48
Pillow==8.1.0
pretrainedmodels==0.7.4
protobuf==3.14.0
pyasn1==0.4.8
pyasn1-modules==0.2.8
pyparsing==2.4.7
python-dateutil==2.8.1
pytorch-lightning==1.1.8
PyWavelets==1.1.1
PyYAML==5.3.1
requests==2.25.1
requests-oauthlib==1.3.0
rsa==4.7.1
ruamel.yaml==0.16.12
ruamel.yaml.clib==0.2.2
scikit-image==0.18.1
scipy==1.6.1
segmentation-models-pytorch==0.1.3
Shapely==1.7.1
six==1.15.0
tensorboard==2.4.1
tensorboard-plugin-wit==1.8.0
tifffile==2021.2.1
timm==0.3.2
torch==1.9.1+cu111
torchaudio==0.9.1
torchvision==0.10.1+cu111
tqdm==4.57.0
typing-extensions==3.7.4.3
urllib3==1.26.3
Werkzeug==1.0.1
yarl==1.6.3

Good luck!

[kompaso]

@adam-j-kelly thanks a lot! In my case problem was in hydra-core

[ihamdi]

This is what I had to do to get the cifar10 example to work:

• Upgrade Python from 3.6.13 to 3.7.11
• Downgrade Pytorch from 1.10.0 to 1.8.0
• Downgrade Hydra-Core from 1.1.0 to 1.0.6
• Change line 6 in envs/name/lib/site-packages/timm/models/layers/helper.py from "from torch._six import container_abcs" to "import collections.abc as container_abcs"

[VLavado]

The solution by @ihamdi worked for me! Thanks a lot!

I needed to add a slight modification by doing pip install torch==1.8.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html to have a compatible CUDA runtime version.

In case it helps anybody:

absl-py==1.0.0
aiohttp==3.8.1
aiosignal==1.2.0
albumentations==1.1.0
antlr4-python3-runtime==4.8
async-timeout==4.0.1
attrs==21.2.0
autoalbument==0.4.0
boto3==1.20.8
botocore==1.23.8
cachetools==4.2.4
certifi==2021.10.8
charset-normalizer==2.0.7
click==8.0.3
colorama==0.4.4
cycler==0.11.0
efficientnet-pytorch==0.6.3
fonttools==4.28.1
frozenlist==1.2.0
fsspec==2021.11.0
future==0.18.2
google-auth==2.3.3
google-auth-oauthlib==0.4.6
grpcio==1.42.0
hydra-core==1.0.6
idna==3.3
imageio==2.11.0
importlib-metadata==4.8.2
importlib-resources==5.4.0
jmespath==0.10.0
joblib==1.1.0
kiwisolver==1.3.2
Markdown==3.3.6
matplotlib==3.5.0
multidict==5.2.0
munch==2.5.0
networkx==2.6.3
numpy==1.21.4
oauthlib==3.1.1
omegaconf==2.0.6
opencv-python-headless==4.5.4.58
packaging==21.3
Pillow==8.4.0
pretrainedmodels==0.7.4
protobuf==3.19.1
pyasn1==0.4.8
pyasn1-modules==0.2.8
pyparsing==3.0.6
python-dateutil==2.8.2
pytorch-lightning==1.1.8
PyWavelets==1.2.0
PyYAML==6.0
qudida==0.0.4
requests==2.26.0
requests-oauthlib==1.3.0
rsa==4.7.2
ruamel.yaml==0.17.17
ruamel.yaml.clib==0.2.6
s3transfer==0.5.0
scikit-image==0.18.3
scikit-learn==1.0.1
scipy==1.7.2
segmentation-models-pytorch==0.1.3
setuptools-scm==6.3.2
six==1.16.0
tensorboard==2.7.0
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.0
threadpoolctl==3.0.0
tifffile==2021.11.2
timm==0.3.2
tomli==1.2.2
torch==1.8.0+cu111
torchvision==0.9.0+cu111
tqdm==4.62.3
typing_extensions==4.0.0
urllib3==1.26.7
Werkzeug==2.0.2
yarl==1.7.2
zipp==3.6.0

[ihamdi]

The solution by @ihamdi worked for me! Thanks a lot!

I needed to add a slight modification by doing pip install torch==1.8.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html to have a compatible CUDA runtime version.

In case it helps anybody:

absl-py==1.0.0 aiohttp==3.8.1 aiosignal==1.2.0 albumentations==1.1.0 antlr4-python3-runtime==4.8 async-timeout==4.0.1 attrs==21.2.0 autoalbument==0.4.0 boto3==1.20.8 botocore==1.23.8 cachetools==4.2.4 certifi==2021.10.8 charset-normalizer==2.0.7 click==8.0.3 colorama==0.4.4 cycler==0.11.0 efficientnet-pytorch==0.6.3 fonttools==4.28.1 frozenlist==1.2.0 fsspec==2021.11.0 future==0.18.2 google-auth==2.3.3 google-auth-oauthlib==0.4.6 grpcio==1.42.0 hydra-core==1.0.6 idna==3.3 imageio==2.11.0 importlib-metadata==4.8.2 importlib-resources==5.4.0 jmespath==0.10.0 joblib==1.1.0 kiwisolver==1.3.2 Markdown==3.3.6 matplotlib==3.5.0 multidict==5.2.0 munch==2.5.0 networkx==2.6.3 numpy==1.21.4 oauthlib==3.1.1 omegaconf==2.0.6 opencv-python-headless==4.5.4.58 packaging==21.3 Pillow==8.4.0 pretrainedmodels==0.7.4 protobuf==3.19.1 pyasn1==0.4.8 pyasn1-modules==0.2.8 pyparsing==3.0.6 python-dateutil==2.8.2 pytorch-lightning==1.1.8 PyWavelets==1.2.0 PyYAML==6.0 qudida==0.0.4 requests==2.26.0 requests-oauthlib==1.3.0 rsa==4.7.2 ruamel.yaml==0.17.17 ruamel.yaml.clib==0.2.6 s3transfer==0.5.0 scikit-image==0.18.3 scikit-learn==1.0.1 scipy==1.7.2 segmentation-models-pytorch==0.1.3 setuptools-scm==6.3.2 six==1.16.0 tensorboard==2.7.0 tensorboard-data-server==0.6.1 tensorboard-plugin-wit==1.8.0 threadpoolctl==3.0.0 tifffile==2021.11.2 timm==0.3.2 tomli==1.2.2 torch==1.8.0+cu111 torchvision==0.9.0+cu111 tqdm==4.62.3 typing_extensions==4.0.0 urllib3==1.26.7 Werkzeug==2.0.2 yarl==1.7.2 zipp==3.6.0

Yeah please make sure you have the correct cudatoolkit according to your hardware.

Unfortunately the output in the json files isn't giving a rotation range but rather the same negative number as upper and lower limit. When I try to use the file to implement the generated augmentations, the code blows up because it is impossible to generate a random number between two numbers that are identical. I'm stumped and don't know how to proceed from there. I don't want to mess with the random just to make this work.

[PetrDvoracek]

Hi, I solved this problem on my machine by downgrading the hydra core version to hydra-core==1.0.6