add monai-based scripts for dataset conversion, training, and inference #60

naga-karthik · 2023-07-14T14:46:34Z

This PR adds all the required scripts for bids-msd dataset conversion, training and running inference with MONAI models.

monai/main.py

monai/transforms.py

naga-karthik · 2023-10-09T13:52:05Z

Hey @jcohenadad, yes the PR is ready. We will be merging it this week. Meanwhile, the inference script is also ready to use.
For --chkp-path please use

/home/GRAMES.POLYMTL.CA/u114716/duke/projects/ivadomed/contrast-agnostic-seg/models/monai

as the model is currently stored there

monai/inference_instructions.md

jcohenadad · 2023-10-09T14:12:17Z

I'm having issues installing the deps:

Terminal output

(/Users/julien/code/contrast-agnostic-softseg-spinalcord/venv) julien-macbook:~/code/contrast-agnostic-softseg-spinalcord/monai $ pip install -r requirements_inference.txt 
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cpu
Collecting dynamic_network_architectures==0.2 (from -r requirements_inference.txt (line 1))
  Using cached dynamic_network_architectures-0.2.tar.gz (20 kB)
  Preparing metadata (setup.py) ... done
Collecting joblib==1.3.0 (from -r requirements_inference.txt (line 2))
  Obtaining dependency information for joblib==1.3.0 from https://files.pythonhosted.org/packages/1e/f2/6ec7eb9e48c88c750da04050a5ba8250ca9949dfcf6e624ccee12d2fc653/joblib-1.3.0-py3-none-any.whl.metadata
  Using cached joblib-1.3.0-py3-none-any.whl.metadata (5.4 kB)
Collecting loguru==0.7.0 (from -r requirements_inference.txt (line 3))
  Using cached loguru-0.7.0-py3-none-any.whl (59 kB)
Collecting monai[nibabel]==1.2.0 (from -r requirements_inference.txt (line 4))
  Obtaining dependency information for monai[nibabel]==1.2.0 from https://files.pythonhosted.org/packages/2e/39/444fc5b2fb0e9d9d432a2e1efaf75d68b0aee94d7559c8b9969e2f62c5a4/monai-1.2.0-202306081546-py3-none-any.whl.metadata
  Using cached monai-1.2.0-202306081546-py3-none-any.whl.metadata (10 kB)
Collecting scipy==1.11.2 (from -r requirements_inference.txt (line 5))
  Obtaining dependency information for scipy==1.11.2 from https://files.pythonhosted.org/packages/03/c3/5162f7d23a12c62cf0630f6cce20932f166fca7cb5513ed9af56b5618ba6/scipy-1.11.2-cp39-cp39-macosx_10_9_x86_64.whl.metadata
  Downloading scipy-1.11.2-cp39-cp39-macosx_10_9_x86_64.whl.metadata (54 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 54.1/54.1 kB 1.0 MB/s eta 0:00:00
Collecting numpy==1.24.4 (from -r requirements_inference.txt (line 6))
  Obtaining dependency information for numpy==1.24.4 from https://files.pythonhosted.org/packages/9a/cd/d5b0402b801c8a8b56b04c1e85c6165efab298d2f0ab741c2406516ede3a/numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl.metadata
  Downloading numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl.metadata (5.6 kB)
ERROR: Could not find a version that satisfies the requirement torch==2.0.0+cpu (from versions: 1.7.1, 1.8.0, 1.8.1, 1.9.0, 1.9.1, 1.10.0, 1.10.1, 1.10.2, 1.11.0, 1.12.0, 1.12.1, 1.13.0, 1.13.1, 2.0.0, 2.0.1, 2.1.0)
ERROR: No matching distribution found for torch==2.0.0+cpu
(/Users/julien/code/contrast-agnostic-softseg-spinalcord/venv) julien-macbook:~/code/contrast-agnostic-softseg-spinalcord/monai $ python
Python 3.9.18 (main, Sep 11 2023, 08:38:23) 
[Clang 14.0.6 ] :: Anaconda, Inc. on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> 
(/Users/julien/code/contrast-agnostic-softseg-spinalcord/venv) julien-macbook:~/code/contrast-agnostic-softseg-spinalcord/monai $ git log
commit 4694169352fb962f607e7684fe778677adc123dc (HEAD -> nk/monai, origin/nk/monai)
Author: Naga Karthik <[email protected]>
Date:   Sun Oct 8 15:49:00 2023 -0400

    fix bug with torch.clamp setting bg values to 0.5

valosekj · 2023-10-09T14:17:00Z

I'm having issues installing the deps:

I had the same issue on my local macboook, I had to remove packages versions; see updated requirements from canproco repo.

Then I ran:

 conda create -n monai python=3.8
 conda activate monai
 pip install -r requirements.txt

jcohenadad · 2023-10-09T14:18:45Z

I'm having issues installing the deps:

I had the same issue on my local macboook, I had to remove packages versions; see updated requirements from canproco repo.

Then I ran:
 conda create -n monai python=3.8
 conda activate monai
 pip install -r requirements.txt

Thank you @valosekj -- there see to be some confusion about Python's version:
https://github.com/sct-pipeline/contrast-agnostic-softseg-spinalcord/pull/60/files#diff-45765be45b87970b013c24cdb66c4f4ad139e802f0f013e0bbf56ecf249478eeR12

jcohenadad · 2023-10-09T14:21:10Z

I have another error with python 3.8:

Terminal output

julien-macbook:~ $ conda create -n monai python=3.8
Collecting package metadata (current_repodata.json): done
Solving environment: done

## Package Plan ##

  environment location: /Users/julien/miniconda3/envs/monai

  added / updated specs:
    - python=3.8


The following packages will be downloaded:

    package                    |            build
    ---------------------------|-----------------
    pip-23.2.1                 |   py38hecd8cb5_0         2.6 MB
    python-3.8.18              |       h5ee71fb_0        14.4 MB
    setuptools-68.0.0          |   py38hecd8cb5_0         946 KB
    wheel-0.41.2               |   py38hecd8cb5_0         109 KB
    ------------------------------------------------------------
                                           Total:        18.0 MB

The following NEW packages will be INSTALLED:

  ca-certificates    pkgs/main/osx-64::ca-certificates-2023.08.22-hecd8cb5_0 
  libcxx             pkgs/main/osx-64::libcxx-14.0.6-h9765a3e_0 
  libffi             pkgs/main/osx-64::libffi-3.4.4-hecd8cb5_0 
  ncurses            pkgs/main/osx-64::ncurses-6.4-hcec6c5f_0 
  openssl            pkgs/main/osx-64::openssl-3.0.11-hca72f7f_2 
  pip                pkgs/main/osx-64::pip-23.2.1-py38hecd8cb5_0 
  python             pkgs/main/osx-64::python-3.8.18-h5ee71fb_0 
  readline           pkgs/main/osx-64::readline-8.2-hca72f7f_0 
  setuptools         pkgs/main/osx-64::setuptools-68.0.0-py38hecd8cb5_0 
  sqlite             pkgs/main/osx-64::sqlite-3.41.2-h6c40b1e_0 
  tk                 pkgs/main/osx-64::tk-8.6.12-h5d9f67b_0 
  wheel              pkgs/main/osx-64::wheel-0.41.2-py38hecd8cb5_0 
  xz                 pkgs/main/osx-64::xz-5.4.2-h6c40b1e_0 
  zlib               pkgs/main/osx-64::zlib-1.2.13-h4dc903c_0 


Proceed ([y]/n)? y


Downloading and Extracting Packages
                                                                                                    
Preparing transaction: done                                                                         
Verifying transaction: done                                                                         
Executing transaction: done                                                                         
#
# To activate this environment, use
#
#     $ conda activate monai
#
# To deactivate an active environment, use
#
#     $ conda deactivate

julien-macbook:~ $ conda activate monai
(monai) julien-macbook:~ $ cd code/contrast-agnostic-softseg-spinalcord/
(monai) julien-macbook:~/code/contrast-agnostic-softseg-spinalcord $ cd monai/
(monai) julien-macbook:~/code/contrast-agnostic-softseg-spinalcord/monai $ pip install -r requirements_inference.txt 
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cpu
Collecting dynamic_network_architectures==0.2 (from -r requirements_inference.txt (line 1))
  Using cached dynamic_network_architectures-0.2.tar.gz (20 kB)
  Preparing metadata (setup.py) ... done
Collecting joblib==1.3.0 (from -r requirements_inference.txt (line 2))
  Obtaining dependency information for joblib==1.3.0 from https://files.pythonhosted.org/packages/1e/f2/6ec7eb9e48c88c750da04050a5ba8250ca9949dfcf6e624ccee12d2fc653/joblib-1.3.0-py3-none-any.whl.metadata
  Using cached joblib-1.3.0-py3-none-any.whl.metadata (5.4 kB)
Collecting loguru==0.7.0 (from -r requirements_inference.txt (line 3))
  Using cached loguru-0.7.0-py3-none-any.whl (59 kB)
Collecting monai[nibabel]==1.2.0 (from -r requirements_inference.txt (line 4))
  Obtaining dependency information for monai[nibabel]==1.2.0 from https://files.pythonhosted.org/packages/2e/39/444fc5b2fb0e9d9d432a2e1efaf75d68b0aee94d7559c8b9969e2f62c5a4/monai-1.2.0-202306081546-py3-none-any.whl.metadata
  Using cached monai-1.2.0-202306081546-py3-none-any.whl.metadata (10 kB)
ERROR: Ignored the following versions that require a different python version: 1.11.0 Requires-Python <3.13,>=3.9; 1.11.0rc1 Requires-Python <3.13,>=3.9; 1.11.0rc2 Requires-Python <3.13,>=3.9; 1.11.1 Requires-Python <3.13,>=3.9; 1.11.2 Requires-Python <3.13,>=3.9; 1.11.3 Requires-Python <3.13,>=3.9
ERROR: Could not find a version that satisfies the requirement scipy==1.11.2 (from versions: 0.8.0, 0.9.0, 0.10.0, 0.10.1, 0.11.0, 0.12.0, 0.12.1, 0.13.0, 0.13.1, 0.13.2, 0.13.3, 0.14.0, 0.14.1, 0.15.0, 0.15.1, 0.16.0, 0.16.1, 0.17.0, 0.17.1, 0.18.0, 0.18.1, 0.19.0, 0.19.1, 1.0.0, 1.0.1, 1.1.0, 1.2.0, 1.2.1, 1.2.2, 1.2.3, 1.3.0, 1.3.1, 1.3.2, 1.3.3, 1.4.0, 1.4.1, 1.5.0, 1.5.1, 1.5.2, 1.5.3, 1.5.4, 1.6.0, 1.6.1, 1.6.2, 1.6.3, 1.7.0, 1.7.1, 1.7.2, 1.7.3, 1.8.0rc1, 1.8.0rc2, 1.8.0rc3, 1.8.0rc4, 1.8.0, 1.8.1, 1.9.0rc1, 1.9.0rc2, 1.9.0rc3, 1.9.0, 1.9.1, 1.9.2, 1.9.3, 1.10.0rc1, 1.10.0rc2, 1.10.0, 1.10.1)
ERROR: No matching distribution found for scipy==1.11.2

jcohenadad · 2023-10-09T14:21:56Z

same issue when targetting requirements.txt instead of requirements_inference.txt

Terminal output

(monai) julien-macbook:~/code/contrast-agnostic-softseg-spinalcord/monai $ pip install -r requirements.txt 
Collecting dynamic_network_architectures==0.2 (from -r requirements.txt (line 1))
  Using cached dynamic_network_architectures-0.2.tar.gz (20 kB)
  Preparing metadata (setup.py) ... done
Collecting joblib==1.3.0 (from -r requirements.txt (line 2))
  Obtaining dependency information for joblib==1.3.0 from https://files.pythonhosted.org/packages/1e/f2/6ec7eb9e48c88c750da04050a5ba8250ca9949dfcf6e624ccee12d2fc653/joblib-1.3.0-py3-none-any.whl.metadata
  Using cached joblib-1.3.0-py3-none-any.whl.metadata (5.4 kB)
Collecting loguru==0.7.0 (from -r requirements.txt (line 3))
  Using cached loguru-0.7.0-py3-none-any.whl (59 kB)
Collecting matplotlib==3.7.2 (from -r requirements.txt (line 4))
  Obtaining dependency information for matplotlib==3.7.2 from https://files.pythonhosted.org/packages/b2/b6/c6596fbc30899e6da31450053054d7da61a21a3f510544fb7cb7658a3de3/matplotlib-3.7.2-cp38-cp38-macosx_10_12_x86_64.whl.metadata
  Downloading matplotlib-3.7.2-cp38-cp38-macosx_10_12_x86_64.whl.metadata (5.6 kB)
Collecting monai[all]==1.2.0 (from -r requirements.txt (line 5))
  Obtaining dependency information for monai[all]==1.2.0 from https://files.pythonhosted.org/packages/2e/39/444fc5b2fb0e9d9d432a2e1efaf75d68b0aee94d7559c8b9969e2f62c5a4/monai-1.2.0-202306081546-py3-none-any.whl.metadata
  Using cached monai-1.2.0-202306081546-py3-none-any.whl.metadata (10 kB)
Collecting numpy==1.24.4 (from -r requirements.txt (line 6))
  Obtaining dependency information for numpy==1.24.4 from https://files.pythonhosted.org/packages/11/10/943cfb579f1a02909ff96464c69893b1d25be3731b5d3652c2e0cf1281ea/numpy-1.24.4-cp38-cp38-macosx_10_9_x86_64.whl.metadata
  Downloading numpy-1.24.4-cp38-cp38-macosx_10_9_x86_64.whl.metadata (5.6 kB)
Collecting pytorch_lightning==2.0.4 (from -r requirements.txt (line 7))
  Obtaining dependency information for pytorch_lightning==2.0.4 from https://files.pythonhosted.org/packages/e9/70/9c2587d7a566c1e656b5fcdbc1d01afd34675d8418b8fc4da3eb4d9bc808/pytorch_lightning-2.0.4-py3-none-any.whl.metadata
  Downloading pytorch_lightning-2.0.4-py3-none-any.whl.metadata (23 kB)
Collecting scikit_learn==1.3.0 (from -r requirements.txt (line 8))
  Obtaining dependency information for scikit_learn==1.3.0 from https://files.pythonhosted.org/packages/33/cb/0e41fad5b30fd66925e47952ddc720d078bdfd8397584a4873ec1cf590ca/scikit_learn-1.3.0-cp38-cp38-macosx_10_9_x86_64.whl.metadata
  Downloading scikit_learn-1.3.0-cp38-cp38-macosx_10_9_x86_64.whl.metadata (11 kB)
ERROR: Ignored the following versions that require a different python version: 1.11.0 Requires-Python <3.13,>=3.9; 1.11.0rc1 Requires-Python <3.13,>=3.9; 1.11.0rc2 Requires-Python <3.13,>=3.9; 1.11.1 Requires-Python <3.13,>=3.9; 1.11.2 Requires-Python <3.13,>=3.9; 1.11.3 Requires-Python <3.13,>=3.9; 1.25.0 Requires-Python >=3.9; 1.25.0rc1 Requires-Python >=3.9; 1.25.1 Requires-Python >=3.9; 1.25.2 Requires-Python >=3.9; 1.26.0 Requires-Python <3.13,>=3.9; 1.26.0b1 Requires-Python <3.13,>=3.9; 1.26.0rc1 Requires-Python <3.13,>=3.9; 3.8.0 Requires-Python >=3.9; 3.8.0rc1 Requires-Python >=3.9
ERROR: Could not find a version that satisfies the requirement scipy==1.11.2 (from versions: 0.8.0, 0.9.0, 0.10.0, 0.10.1, 0.11.0, 0.12.0, 0.12.1, 0.13.0, 0.13.1, 0.13.2, 0.13.3, 0.14.0, 0.14.1, 0.15.0, 0.15.1, 0.16.0, 0.16.1, 0.17.0, 0.17.1, 0.18.0, 0.18.1, 0.19.0, 0.19.1, 1.0.0, 1.0.1, 1.1.0, 1.2.0, 1.2.1, 1.2.2, 1.2.3, 1.3.0, 1.3.1, 1.3.2, 1.3.3, 1.4.0, 1.4.1, 1.5.0, 1.5.1, 1.5.2, 1.5.3, 1.5.4, 1.6.0, 1.6.1, 1.6.2, 1.6.3, 1.7.0, 1.7.1, 1.7.2, 1.7.3, 1.8.0rc1, 1.8.0rc2, 1.8.0rc3, 1.8.0rc4, 1.8.0, 1.8.1, 1.9.0rc1, 1.9.0rc2, 1.9.0rc3, 1.9.0, 1.9.1, 1.9.2, 1.9.3, 1.10.0rc1, 1.10.0rc2, 1.10.0, 1.10.1)
ERROR: No matching distribution found for scipy==1.11.2

naga-karthik · 2023-10-09T14:21:56Z

@jcohenadad can you try installing the dependencies now? I think the +cpu in torch package was causing the issue. I removed it in latest commit.

Please stick to python=3.9 as my code is based on 3.9. (however, for simply running the inference script, the python versions shouldn't matter much, as we're using basic python commands. But using 3.9 will keep it consistent with the rest of the monai code)

jcohenadad · 2023-10-09T14:25:00Z

2e35282 fixed it 🎉

Terminal output

(py39) julien-macbook:~/code/contrast-agnostic-softseg-spinalcord/monai $ pip install -r requirements_inference.txt 
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cpu
Collecting dynamic_network_architectures==0.2 (from -r requirements_inference.txt (line 1))
  Using cached dynamic_network_architectures-0.2.tar.gz (20 kB)
  Preparing metadata (setup.py) ... done
Collecting joblib==1.3.0 (from -r requirements_inference.txt (line 2))
  Obtaining dependency information for joblib==1.3.0 from https://files.pythonhosted.org/packages/1e/f2/6ec7eb9e48c88c750da04050a5ba8250ca9949dfcf6e624ccee12d2fc653/joblib-1.3.0-py3-none-any.whl.metadata
  Using cached joblib-1.3.0-py3-none-any.whl.metadata (5.4 kB)
Collecting loguru==0.7.0 (from -r requirements_inference.txt (line 3))
  Using cached loguru-0.7.0-py3-none-any.whl (59 kB)
Collecting monai[nibabel]==1.2.0 (from -r requirements_inference.txt (line 4))
  Obtaining dependency information for monai[nibabel]==1.2.0 from https://files.pythonhosted.org/packages/2e/39/444fc5b2fb0e9d9d432a2e1efaf75d68b0aee94d7559c8b9969e2f62c5a4/monai-1.2.0-202306081546-py3-none-any.whl.metadata
  Using cached monai-1.2.0-202306081546-py3-none-any.whl.metadata (10 kB)
Collecting scipy==1.11.2 (from -r requirements_inference.txt (line 5))
  Obtaining dependency information for scipy==1.11.2 from https://files.pythonhosted.org/packages/03/c3/5162f7d23a12c62cf0630f6cce20932f166fca7cb5513ed9af56b5618ba6/scipy-1.11.2-cp39-cp39-macosx_10_9_x86_64.whl.metadata
  Using cached scipy-1.11.2-cp39-cp39-macosx_10_9_x86_64.whl.metadata (54 kB)
Collecting numpy==1.24.4 (from -r requirements_inference.txt (line 6))
  Obtaining dependency information for numpy==1.24.4 from https://files.pythonhosted.org/packages/9a/cd/d5b0402b801c8a8b56b04c1e85c6165efab298d2f0ab741c2406516ede3a/numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl.metadata
  Using cached numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl.metadata (5.6 kB)
Collecting torch==2.0.0 (from -r requirements_inference.txt (line 8))
  Downloading https://download.pytorch.org/whl/cpu/torch-2.0.0-cp39-none-macosx_10_9_x86_64.whl (139.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 139.8/139.8 MB 6.1 MB/s eta 0:00:00
Collecting nibabel (from monai[nibabel]==1.2.0->-r requirements_inference.txt (line 4))
  Using cached nibabel-5.1.0-py3-none-any.whl (3.3 MB)
Collecting filelock (from torch==2.0.0->-r requirements_inference.txt (line 8))
  Obtaining dependency information for filelock from https://files.pythonhosted.org/packages/5e/5d/97afbafd9d584ff1b45fcb354a479a3609bd97f912f8f1f6c563cb1fae21/filelock-3.12.4-py3-none-any.whl.metadata
  Downloading filelock-3.12.4-py3-none-any.whl.metadata (2.8 kB)
Collecting typing-extensions (from torch==2.0.0->-r requirements_inference.txt (line 8))
  Obtaining dependency information for typing-extensions from https://files.pythonhosted.org/packages/24/21/7d397a4b7934ff4028987914ac1044d3b7d52712f30e2ac7a2ae5bc86dd0/typing_extensions-4.8.0-py3-none-any.whl.metadata
  Downloading typing_extensions-4.8.0-py3-none-any.whl.metadata (3.0 kB)
Collecting sympy (from torch==2.0.0->-r requirements_inference.txt (line 8))
  Downloading https://download.pytorch.org/whl/sympy-1.12-py3-none-any.whl (5.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.7/5.7 MB 12.9 MB/s eta 0:00:00
Collecting networkx (from torch==2.0.0->-r requirements_inference.txt (line 8))
  Using cached networkx-3.1-py3-none-any.whl (2.1 MB)
Collecting jinja2 (from torch==2.0.0->-r requirements_inference.txt (line 8))
  Downloading https://download.pytorch.org/whl/Jinja2-3.1.2-py3-none-any.whl (133 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 133.1/133.1 kB 4.6 MB/s eta 0:00:00
Collecting MarkupSafe>=2.0 (from jinja2->torch==2.0.0->-r requirements_inference.txt (line 8))
  Obtaining dependency information for MarkupSafe>=2.0 from https://files.pythonhosted.org/packages/62/9b/4908a57acf39d8811836bc6776b309c2e07d63791485589acf0b6d7bc0c6/MarkupSafe-2.1.3-cp39-cp39-macosx_10_9_x86_64.whl.metadata
  Downloading MarkupSafe-2.1.3-cp39-cp39-macosx_10_9_x86_64.whl.metadata (3.0 kB)
Collecting packaging>=17 (from nibabel->monai[nibabel]==1.2.0->-r requirements_inference.txt (line 4))
  Obtaining dependency information for packaging>=17 from https://files.pythonhosted.org/packages/ec/1a/610693ac4ee14fcdf2d9bf3c493370e4f2ef7ae2e19217d7a237ff42367d/packaging-23.2-py3-none-any.whl.metadata
  Downloading packaging-23.2-py3-none-any.whl.metadata (3.2 kB)
Collecting mpmath>=0.19 (from sympy->torch==2.0.0->-r requirements_inference.txt (line 8))
  Downloading https://download.pytorch.org/whl/mpmath-1.3.0-py3-none-any.whl (536 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 536.2/536.2 kB 9.1 MB/s eta 0:00:00
Downloading joblib-1.3.0-py3-none-any.whl (301 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 301.9/301.9 kB 3.0 MB/s eta 0:00:00
Downloading scipy-1.11.2-cp39-cp39-macosx_10_9_x86_64.whl (37.2 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 37.2/37.2 MB 12.1 MB/s eta 0:00:00
Downloading numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl (19.8 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 19.8/19.8 MB 12.8 MB/s eta 0:00:00
Using cached filelock-3.12.4-py3-none-any.whl (11 kB)
Downloading monai-1.2.0-202306081546-py3-none-any.whl (1.3 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 10.7 MB/s eta 0:00:00
Downloading typing_extensions-4.8.0-py3-none-any.whl (31 kB)
Using cached MarkupSafe-2.1.3-cp39-cp39-macosx_10_9_x86_64.whl (13 kB)
Downloading packaging-23.2-py3-none-any.whl (53 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 53.0/53.0 kB 4.8 MB/s eta 0:00:00
Building wheels for collected packages: dynamic_network_architectures
  Building wheel for dynamic_network_architectures (setup.py) ... done
  Created wheel for dynamic_network_architectures: filename=dynamic_network_architectures-0.2-py3-none-any.whl size=27245 sha256=6ab117e4881bee8c041e31e1b89ae820e4eac0ed4e321d9101965a4da927b482
  Stored in directory: /Users/julien/Library/Caches/pip/wheels/4e/c0/70/740949411012a24276008fa6e920f42701ae6fa18ce6122eb5
Successfully built dynamic_network_architectures
Installing collected packages: mpmath, typing-extensions, sympy, packaging, numpy, networkx, MarkupSafe, loguru, joblib, filelock, scipy, nibabel, jinja2, torch, monai, dynamic_network_architectures
Successfully installed MarkupSafe-2.1.3 dynamic_network_architectures-0.2 filelock-3.12.4 jinja2-3.1.2 joblib-1.3.0 loguru-0.7.0 monai-1.2.0 mpmath-1.3.0 networkx-3.1 nibabel-5.1.0 numpy-1.24.4 packaging-23.2 scipy-1.11.2 sympy-1.12 torch-2.0.0 typing-extensions-4.8.0

jcohenadad · 2023-10-09T14:30:21Z

I understand the benefits in duplicating code to isolate other projects (eg https://github.com/ivadomed/canproco/pull/44/files), but it comes at a cost of a lack of testing/feedback from the team. I strongly suggest to keep only one codebase/documentation, and iterate on that codebase/documentation.

monai/inference_instructions.md

jcohenadad · 2023-10-09T14:33:11Z

monai/inference_instructions.md

+```
+
+`--path-img` - Path to the image to be segmented
+`--chkp-path` - Path to the model checkpoint. This folder should contain the `best_model_loss.ckpt`


where can we find this? pls include a temporary path to the latest model so we can test it-- until we upload as a release asset

I mentioned that path to the model here #60 (comment)

…eline/contrast-agnostic-softseg-spinalcord#60

valosekj · 2023-10-09T14:34:58Z

@jcohenadad can you try installing the dependencies now? I think the +cpu in torch package was causing the issue. I removed it in latest commit.

Please stick to python=3.9 as my code is based on 3.9. (however, for simply running the inference script, the python versions shouldn't matter much, as we're using basic python commands. But using 3.9 will keep it consistent with the rest of the monai code)

Working for me as well! Thanks! I updated the canproco files in ivadomed/canproco@688d1a0 to be in line with this PR.

naga-karthik · 2023-10-09T22:15:45Z

merging to Sandrine's branch -- discussed in the internal meeting

naga-karthik added 16 commits July 9, 2023 20:51

add dataset conversion script for monai training

2fa8821

add file for loss functions

9395732

add transforms

f109634

add util functions

d11a99c

add working monai training script

6590125

change nearest interp to linear for labels in spacingD

cc244ae

fix bug in train/val/test metrics accumulation

7e8261a

update plot_slices()

d361b73

fix cuda memory leak issues; remove unused variables

11f3ac5

add PolyLR scheduler

e88afbc

swap order of spacingD and cropForegroundD

b7ecd0a

add empty patch filtering; change LR scheduler

f73f22e

add requirements

5bb5315

add option to load from joblib for ivadomed comparison

c7a0281

add elastic and biasfield transforms

11961e7

change empty image patch filter to label patch

d230e59

jcohenadad reviewed Jul 17, 2023

View reviewed changes

monai/main.py Outdated Show resolved Hide resolved

jcohenadad reviewed Jul 17, 2023

View reviewed changes

monai/transforms.py Outdated Show resolved Hide resolved

jcohenadad reviewed Jul 17, 2023

View reviewed changes

monai/transforms.py Outdated Show resolved Hide resolved

naga-karthik added 11 commits July 17, 2023 16:52

add initial verson of infeerence script

56dfff3

add ref to chkpt loading for inference

ad3d847

remove duplicated test transforms

407ae04

add feature to plot more slices

e67427f

minor fixes and improvements

72ac6fe

update code to do inference on various datasets

0540c1f

fix diceLoss; add DiceCE loss

5d93f9a

change to explicitly normalizing the logits

bd81aca

add option for attentionunet

29825f9

remove todo; update args for path-data

6b43c59

remove RobustCELoss; update DiceCELoss

ac2572c

valosekj mentioned this pull request Oct 9, 2023

Segment SC using contrast agnostic model ivadomed/canproco#44

Merged

jcohenadad reviewed Oct 9, 2023

View reviewed changes

monai/inference_instructions.md Outdated Show resolved Hide resolved

remove +cpu from torch version

2e35282

jcohenadad reviewed Oct 9, 2023

View reviewed changes

monai/inference_instructions.md Outdated Show resolved Hide resolved

jcohenadad reviewed Oct 9, 2023

View reviewed changes

valosekj added a commit to ivadomed/canproco that referenced this pull request Oct 9, 2023

Update requirements.txt and python version to be in line with sct-pip…

688d1a0

…eline/contrast-agnostic-softseg-spinalcord#60

naga-karthik added 6 commits October 9, 2023 10:51

renamed as README, removed usage instructions

5e3f97a

cleaned by removing unused code

bdb3e98

add cupy for inference on gpu

5cce1e8

add args for contrast,label-type for per-contrast,hard/soft training

2151b23

fix same crop size of train/val

227ba30

clean code

990c357

naga-karthik marked this pull request as ready for review October 9, 2023 22:13

sandrinebedard changed the base branch from main to sb/remove_crop_preprocessing October 9, 2023 22:13

naga-karthik requested a review from sandrinebedard October 9, 2023 22:13

sandrinebedard approved these changes Oct 9, 2023

View reviewed changes

naga-karthik merged commit 112b450 into sb/remove_crop_preprocessing Oct 9, 2023

naga-karthik deleted the nk/monai branch October 9, 2023 22:16

joshuacwnewton mentioned this pull request Jan 18, 2024

Integrate nnUNet/MONAI models into DeepSeg CLI (contrast-agnostic, SCI, rootlets, Zurich mouse) spinalcordtoolbox/spinalcordtoolbox#4345

Merged

14 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

add monai-based scripts for dataset conversion, training, and inference #60

add monai-based scripts for dataset conversion, training, and inference #60

naga-karthik commented Jul 14, 2023

naga-karthik commented Oct 9, 2023 •

edited

Loading

jcohenadad commented Oct 9, 2023

valosekj commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

naga-karthik commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

jcohenadad commented Oct 9, 2023 •

edited

Loading

jcohenadad Oct 9, 2023

naga-karthik Oct 9, 2023

valosekj commented Oct 9, 2023

naga-karthik commented Oct 9, 2023

add monai-based scripts for dataset conversion, training, and inference #60

add monai-based scripts for dataset conversion, training, and inference #60

Conversation

naga-karthik commented Jul 14, 2023

naga-karthik commented Oct 9, 2023 • edited Loading

jcohenadad commented Oct 9, 2023

valosekj commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

naga-karthik commented Oct 9, 2023

jcohenadad commented Oct 9, 2023

jcohenadad commented Oct 9, 2023 • edited Loading

jcohenadad Oct 9, 2023

Choose a reason for hiding this comment

naga-karthik Oct 9, 2023

Choose a reason for hiding this comment

valosekj commented Oct 9, 2023

naga-karthik commented Oct 9, 2023

naga-karthik commented Oct 9, 2023 •

edited

Loading

jcohenadad commented Oct 9, 2023 •

edited

Loading