Skip to content
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

Update on the config.yaml of the pretrained unet #249

Closed
zwep opened this issue May 11, 2023 · 1 comment · Fixed by #250
Closed

Update on the config.yaml of the pretrained unet #249

zwep opened this issue May 11, 2023 · 1 comment · Fixed by #250
Labels
bug Something isn't working

Comments

@zwep
Copy link

zwep commented May 11, 2023

Describe the bug
When I solved the previous issue, and still in the same setting, other errors came up that relate to my first issue.

These include errors such as

omegaconf.errors.ConfigKeyError: Key 'scaling_key' not in 'TransformsConfig'
    full_key: inference.dataset.transforms.scaling_key
    reference_type=BaseConfig
    object_type=TransformsConfig

To resolve these I needed to adapt the provided config.yaml file that I downloaded from the model-zoo to the following:

...
inference:
  dataset:
    name: CalgaryCampinas
    lists: []
    regex_filter: null
    transforms:
      cropping:
        crop: null
        crop_type: uniform
        image_center_crop: true
      sensitivity_map_estimation:
        estimate_sensitivity_maps: true
        sensitivity_maps_gaussian: 0.7
      estimate_body_coil_image: false      
      pad_coils: null
      normalization:
        scaling_key: masked_kspace
      masking:
        name: ???
        accelerations:
        - 4
        center_fractions:
        - 0.08
        uniform_range: false
        image_center_crop: false
        val_accelerations:
        - 4
        - 8
        val_center_fractions:
        - 0.08
        - 0.04
    text_description: inference
    input_kspace_key: null
    input_image_key: null
    kspace_context: 0
    pass_mask: false
    crop_outer_slices: true
  batch_size: 8
...

Here I paste only the relevant part that contained the changes.

Environment
dlup version: Not installed.
direct version: 1.0.5.dev0
How installed: using conda
Python version: 3.9
Operating System:
NAME="Debian GNU/Linux"
VERSION_ID="11"
VERSION="11 (bullseye)"
VERSION_CODENAME=bullseye

@zwep zwep added the bug Something isn't working label May 11, 2023
@georgeyiasemis
Copy link
Contributor

Will be fixed so that the config works

@georgeyiasemis georgeyiasemis linked a pull request Jun 25, 2023 that will close this issue
jonasteuwen pushed a commit that referenced this issue Jun 28, 2023
…, #247, #249)

Minor code fixes:
* Fix transforms creation for inference using `dict_flatten`

Config fixes:
* Update projects/<configs>  to new transforms config:
``` 
cropping:
    crop: null
sensitivity_map_estimation:
    estimate_sensitivity_maps: true  # Estimate the sensitivity map on the ACS
normalization:
    scaling_key: masked_kspace
```

Documentation fixes:
* Update some documentation files
georgeyiasemis added a commit to georgeyiasemis/direct-ssl that referenced this issue Aug 31, 2023
…I-AI#244, NKI-AI#245, NKI-AI#246, NKI-AI#247, NKI-AI#249) (#3)

Minor code fixes:
* Fix transforms creation for inference using `dict_flatten`

Config fixes:
* Update projects/<configs>  to new transforms config:
``` 
cropping:
    crop: null
sensitivity_map_estimation:
    estimate_sensitivity_maps: true  # Estimate the sensitivity map on the ACS
normalization:
    scaling_key: masked_kspace
```

Documentation fixes:
* Update some documentation files
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants