Missing 1 required positional argument: 'temperature'?

[ZeroOneGame]

I got this error:

But when i check the argument temperature in search.yaml , it does. So could someone give me a hand?

My platform is : Ubuntu18.04 with 4*2080Ti GPU, pytorch1.6.

(Tom_envs) Tom@Tom:~/code/Tom/Seg_AutoAlbument$ autoalbument-search --config-dir /home/Tom/code/Tom/Seg_AutoAlbument/sub_Seg_data_aug
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/autoalbument/cli/search.py:15: UserWarning: register_resolver() is deprecated.
See https://github.com/omry/omegaconf/issues/426 for migration instructions.

  OmegaConf.register_resolver("config_dir", get_config_dir)
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'hydra/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'logger/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'callbacks/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'optim/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'trainer/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'searcher/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'data/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'semantic_segmentation_model/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'classification_model/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/core/default_element.py:126: UserWarning: In 'policy_model/default': Usage of deprecated keyword in package header '# @package _group_'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
  See {url} for more information"""
_version: 2
task: semantic_segmentation
policy_model:
  task_factor: 0.1
  gp_factor: 10
  temperature: 0.05
  num_sub_policies: 25
  num_chunks: 4
  operation_count: 4
  operations:
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.ShiftRGB
    shift_r: true
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.ShiftRGB
    shift_g: true
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.ShiftRGB
    shift_b: true
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.RandomBrightness
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.RandomContrast
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.Solarize
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.HorizontalFlip
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.VerticalFlip
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.Rotate
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.ShiftX
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.ShiftY
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.Scale
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.CutoutFixedNumberOfHoles
  - _target_: autoalbument.faster_autoaugment.models.policy_operations.CutoutFixedSize
semantic_segmentation_model:
  _target_: autoalbument.faster_autoaugment.models.SemanticSegmentationModel
  num_classes: 3
  architecture: Unet
  encoder_architecture: resnet18
  pretrained: true
data:
  dataset:
    _target_: dataset.SearchDataset
  input_dtype: uint8
  preprocessing: null
  normalization:
    mean:
    - 0.485
    - 0.456
    - 0.406
    std:
    - 0.229
    - 0.224
    - 0.225
  dataloader:
    _target_: torch.utils.data.DataLoader
    batch_size: 4
    shuffle: true
    num_workers: 8
    pin_memory: true
    drop_last: true
searcher:
  _target_: autoalbument.faster_autoaugment.search.FasterAutoAugmentSearcher
trainer:
  _target_: pytorch_lightning.Trainer
  gpus: 3
  benchmark: true
  max_epochs: 20
  resume_from_checkpoint: null
optim:
  main:
    _target_: torch.optim.Adam
    lr: 0.001
    betas:
    - 0
    - 0.999
  policy:
    _target_: torch.optim.Adam
    lr: 0.001
    betas:
    - 0
    - 0.999
callbacks:
- _target_: autoalbument.callbacks.MonitorAverageParameterChange
- _target_: autoalbument.callbacks.SavePolicy
- _target_: pytorch_lightning.callbacks.ModelCheckpoint
  save_last: true
  dirpath: checkpoints
logger:
  _target_: pytorch_lightning.loggers.TensorBoardLogger
  save_dir: /home/Tom/code/Tom/Seg_AutoAlbument/sub_Seg_data_aug/outputs/2021-08-26/19-55-28/tensorboard_logs
seed: 42

Working directory: /home/Tom/code/Tom/Seg_AutoAlbument/sub_Seg_data_aug/outputs/2021-08-26/19-55-28
Error executing job with overrides: []
Traceback (most recent call last):
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/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 "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/autoalbument/cli/search.py", line 54, in main
    searcher = instantiate(cfg.searcher, cfg=cfg)
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 180, in instantiate
    return instantiate_node(config, *args, recursive=_recursive_, convert=_convert_)
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 246, in instantiate_node
    value, convert=convert, recursive=recursive
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 267, in instantiate_node
    value, convert=convert, recursive=recursive
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 267, in instantiate_node
    value, convert=convert, recursive=recursive
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 225, in instantiate_node
    for item in node._iter_ex(resolve=True)
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 225, in <listcomp>
    for item in node._iter_ex(resolve=True)
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 249, in instantiate_node
    return _call_target(_target_, *args, **kwargs)
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 66, in _call_target
    ).with_traceback(sys.exc_info()[2])
  File "/home/Tom/anaconda3/envs/Tom_envs/lib/python3.7/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'

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
(Tom_envs) Tom@Tom:~/code/Tom/Seg_AutoAlbument$

Here is my search.yaml:

# @package _global_

_version: 2  # An internal value that indicates a version of the config schema. This value is used by
# `autoalbument-search` and `autoalbument-migrate` to upgrade the config to the latest version if necessary.
# Please do not change it manually.


task: semantic_segmentation # Deep learning task. Should either be `classification` or `semantic_segmentation`.


policy_model:
  # Settings for Policy Model that searches augmentation policies.

  temperature: 0.05
  # Temperature for Relaxed Bernoulli distribution. The probability of applying a certain augmentation is sampled from
  # Relaxed Bernoulli distribution (because Bernoulli distribution is not differentiable). With lower values of
  # `temperature` Relaxed Bernoulli distribution behaves like Bernoulli distribution. In the paper, the authors
  # of Faster AutoAugment used 0.05 as a default value for `temperature`.

  task_factor: 0.1
  # Multiplier for segmentation loss of a model. Faster AutoAugment uses segmentation loss to prevent augmentations
  # from transforming images of a particular class to another class.

  gp_factor: 10
  # Multiplier for the gradient penalty for WGAN-GP training. 10 is the default value that was proposed in
  # `Improved Training of Wasserstein GANs`.


  num_sub_policies: 25
  # Number of augmentation sub-policies. When an image passes through an augmentation pipeline, Faster AutoAugment
  # randomly chooses one sub-policy and uses augmentations from that sub-policy to transform an input image. A larger
  # number of sub-policies leads to a more diverse set of augmentations and better performance of a model trained on
  # augmented images. However, an increase in the number of sub-policies leads to the exponential growth of a search
  # space of augmentations, so you need more training data for Policy Model to find good augmentation policies.

  num_chunks: 4
  # Number of chunks in a batch. Faster AutoAugment splits each batch of images into `num_chunks` chunks. Then it
  # applies the same sub-policy with the same parameters to each image in a chunk. This parameter controls the tradeoff
  # between the speed of augmentation search and diversity of augmentations. Larger `num_chunks` values will lead to
  # faster searching but less diverse set of augmentations. Note that this parameter is used only in the searching
  # phase. When you train a model with found sub-policies, Albumentations will apply a distinct set of transformations
  # to each image separately.

  operation_count: 4
  # Number of consecutive augmentations in each sub-policy. Faster AutoAugment will sequentially apply `operation_count`
  # augmentations from a sub-policy to an image. Larger values of `operation_count` lead to better performance of
  # a model trained on augmented images. Simultaneously, larger values of `operation_count` affect the speed of search
  # and increase the searching time.

semantic_segmentation_model:
# Settings for Semantic Segmentation Model that is used for two purposes:
# 1. As a model that performs semantic segmentation of input images.
# 2. As a Discriminator for Policy Model.
  _target_: autoalbument.faster_autoaugment.models.SemanticSegmentationModel
    # By default, AutoAlbument uses an instance of `autoalbument.faster_autoaugment.models.SemanticSegmentationModel` as
  # a semantic segmentation model.
  # This model takes four parameters: `num_classes`, `architecture`, `encoder_architecture` and `pretrained`.

  num_classes: 3
  # The number of classes in the dataset. The dataset implementation should return a mask as a NumPy array with
  # the shape [height, width, num_classes]. In a case of binary segmentation you can set `num_classes` to 1.

  architecture: Unet
  # The architecture of Semantic Segmentation Model. AutoAlbument uses models from
  # https://github.com/qubvel/segmentation_models.pytorch. Please refer to its documentation to get a list of available
  # models - https://github.com/qubvel/segmentation_models.pytorch#models-.

  encoder_architecture: resnet18
  # The architecture of encoder in Semantic Segmentation Model. Please refer to Segmentation Models' documentation to
  # get a list of available encoders - https://github.com/qubvel/segmentation_models.pytorch#encoders-

  pretrained: true
  # Either boolean flag or string with that indicates whether the selected encoder architecture should load pretrained
  # weights or use randomly initialized weights.
  # - In the case of boolean flag `true` means using pretrained weights from ImageNet and `false` means using randomly
  #   initialized weights.
  # - In the case of string the value should specify the name of the weights. For the list of available weights please
  #   refer to https://github.com/qubvel/segmentation_models.pytorch#encoders-


data:
  dataset:
    _target_: dataset.SearchDataset
  # Class for instantiating a PyTorch dataset.

  normalization:
    mean: [0.485, 0.456, 0.406]
    std: [0.229, 0.224, 0.225]
  # Normalization values for images. For each image, the search pipeline will subtract `mean` and divide by `std`.
  # Normalization is applied after transforms defined in `preprocessing`. Note that regardless of `input_dtype`,
  # the normalization function will always receive a `float32` input with values in the range [0.0, 1.0], so you should
  # define `mean` and `std` values accordingly. ImageNet normalization is used by default.


  dataloader:
    batch_size: 4
trainer:
  gpus: 3
  # Number of GPUs to train on. Set to `0` or None` to use CPU for training.
  # More detailed description - https://pytorch-lightning.readthedocs.io/en/stable/common/trainer.html#gpus

  benchmark: true
  # If true enables cudnn.benchmark.
  # More detailed description - https://pytorch-lightning.readthedocs.io/en/stable/common/trainer.html#benchmark

  max_epochs: 20
  # Number of epochs to search for augmentation parameters.
  # More detailed description - https://pytorch-lightning.readthedocs.io/en/stable/common/trainer.html#max-epochs

[PickHub]

Think this is a hydra-core issue. Got fixed for me by
pip install hydra-core==1.0.6

[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"

[fbosshard]

With the release of segmentation-models-pytorch version 0.3.0 on 29.07.22, a new error occurs

cannot import name 'ByoModelCfg' from 'timm.models' (/home/user/.venv/envname/lib/python3.8/site-packages/timm/models/__init__.py) when loading module 'autoalbument.faster_autoaugment.search.FasterAutoAugmentSearcher

This can be fixed by using the older version:
pip install segmentation-models-pytorch==0.2.1