Address #6 (and possibly closes it).

This is a quick fix attempt to close #6. In theory what you expressed should have been enough, in practice let's see if adding more specificity to the setup helps. Worth a try - works for me on Linux.

Another cause of this issue might be some local configuration that doesn't allow for nifti files of files bigger than x MB.

Trying to run the jupyter notebook.

I am getting this error:

ModuleNotFoundError: No module named 'tensorflow.python.tools'

See the traceback and the output of pip list below

Also: I had to place the notebook in the root of the repo to find the DeepMReye module.

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
/tmp/ipykernel_5653/3206132536.py in <module>
      8 
      9 # DeepMReye imports
---> 10 from deepmreye import architecture, train, analyse, preprocess
     11 from deepmreye.util import util, data_generator, model_opts
     12 

~/github/DeepMReye/deepmreye/__init__.py in <module>
----> 1 from . import util
      2 from . import preprocess
      3 from . import architecture
      4 from . import train
      5 from . import analyse

~/github/DeepMReye/deepmreye/util/__init__.py in <module>
----> 1 from . import util
      2 from . import model_opts
      3 from . import data_generator
      4 from . import data_io

~/github/DeepMReye/deepmreye/util/util.py in <module>
      6 from sklearn.metrics import r2_score
      7 import warnings
----> 8 import tensorflow.keras.backend as K
      9 from tensorflow.keras.callbacks import LearningRateScheduler
     10 import tensorflow as tf

~/github/DeepMReye/env/lib/python3.8/site-packages/tensorflow/__init__.py in <module>
     39 import sys as _sys
     40 
---> 41 from tensorflow.python.tools import module_util as _module_util
     42 from tensorflow.python.util.lazy_loader import LazyLoader as _LazyLoader
     43 

ModuleNotFoundError: No module named 'tensorflow.python.tools'

Package                      Version
---------------------------- ---------
absl-py                      1.0.0
antspyx                      0.2.9
anyio                        3.3.4
argon2-cffi                  21.1.0
astunparse                   1.6.3
attrs                        21.2.0
Babel                        2.9.1
backcall                     0.2.0
bleach                       4.1.0
cachetools                   4.2.4
certifi                      2021.10.8
cffi                         1.15.0
charset-normalizer           2.0.7
chart-studio                 1.1.0
cycler                       0.11.0
debugpy                      1.5.1
decorator                    5.1.0
defusedxml                   0.7.1
entrypoints                  0.3
flatbuffers                  2.0
fonttools                    4.28.1
gast                         0.4.0
google-auth                  2.3.3
google-auth-oauthlib         0.4.6
google-pasta                 0.2.0
grpcio                       1.42.0
h5py                         3.6.0
idna                         3.3
imageio                      2.10.5
importlib-metadata           4.8.2
importlib-resources          5.4.0
ipykernel                    6.5.0
ipython                      7.29.0
ipython-genutils             0.2.0
jedi                         0.18.1
Jinja2                       3.0.3
joblib                       1.1.0
json5                        0.9.6
jsonschema                   4.2.1
jupyter-client               7.0.6
jupyter-core                 4.9.1
jupyter-server               1.11.2
jupyterlab                   3.2.4
jupyterlab-pygments          0.1.2
jupyterlab-server            2.8.2
keras                        2.7.0
Keras-Preprocessing          1.1.2
kiwisolver                   1.3.2
libclang                     12.0.0
Markdown                     3.3.6
MarkupSafe                   2.0.1
matplotlib                   3.5.0
matplotlib-inline            0.1.3
mistune                      0.8.4
nbclassic                    0.3.4
nbclient                     0.5.8
nbconvert                    6.3.0
nbformat                     5.1.3
nest-asyncio                 1.5.1
networkx                     2.6.3
nibabel                      3.2.1
notebook                     6.4.6
numpy                        1.21.4
oauthlib                     3.1.1
opt-einsum                   3.3.0
packaging                    21.2
pandas                       1.3.4
pandocfilters                1.5.0
parso                        0.8.2
patsy                        0.5.2
pexpect                      4.8.0
pickleshare                  0.7.5
Pillow                       8.4.0
pip                          21.3.1
plotly                       5.4.0
prometheus-client            0.12.0
prompt-toolkit               3.0.22
protobuf                     3.19.1
ptyprocess                   0.7.0
pyasn1                       0.4.8
pyasn1-modules               0.2.8
pycparser                    2.21
Pygments                     2.10.0
pyparsing                    2.4.7
pyrsistent                   0.18.0
python-dateutil              2.8.2
pytz                         2021.3
PyWavelets                   1.2.0
PyYAML                       6.0
pyzmq                        22.3.0
requests                     2.26.0
requests-oauthlib            1.3.0
retrying                     1.3.3
rsa                          4.7.2
scikit-image                 0.18.3
scikit-learn                 1.0.1
scipy                        1.7.2
Send2Trash                   1.8.0
setuptools                   58.2.0
setuptools-scm               6.3.2
six                          1.16.0
sniffio                      1.2.0
statsmodels                  0.13.1
tenacity                     8.0.1
tensorboard                  2.7.0
tensorboard-data-server      0.6.1
tensorboard-plugin-wit       1.8.0
tensorflow                   2.7.0
tensorflow-estimator         2.7.0
tensorflow-io-gcs-filesystem 0.22.0
termcolor                    1.1.0
terminado                    0.12.1
testpath                     0.5.0
threadpoolctl                3.0.0
tifffile                     2021.11.2
tomli                        1.2.2
tornado                      6.1
traitlets                    5.1.1
typing_extensions            4.0.0
urllib3                      1.26.7
wcwidth                      0.2.5
webcolors                    1.11.1
webencodings                 0.5.1
websocket-client             1.2.1
Werkzeug                     2.0.2
wheel                        0.37.0
wrapt                        1.13.3
zipp                         3.6.0

Would require relaxing the requirements on tenserflow. https://discuss.tensorflow.org/t/support-python-3-10/124

Could possibly consider removing python 3.7 or wait for its end of life: https://endoflife.date/python

Changes summary

• Runs the pretrained-weight notebook in CI to use as a "system test".
• Simplifies running the demo by facilitating data download from OSF

Details

• [x] add makefile to facilitate downloading some of the data from OSF in the demo folder
• [x] adapt notebooks to run with demos in the notebook folders so users do not have to manually change the path
• [x] update notebooks to explain how the data has to be structure
• [x] add github action workflow to test the notebook with the nbmake pytest plugin
• [x] lint notebooks content with nb-balck
• [x] replace path creation using string concatenation with using os.path.join
• [x] run on macOS
• [x] install from upstream after merging of #10

Note

This does not run the "full" training notebook in CI

After a

pip install git+https://github.com/DeepMReye/DeepMReye.git

I get this when trying to load the masks.

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/tmp/ipykernel_31249/7865041.py in <module>
      1 # Preload masks to save time within participant loop
----> 2 (eyemask_small, eyemask_big, dme_template, mask, x_edges, y_edges, z_edges) = preprocess.get_masks()

~/github/CPP_deepMReye/code/env/lib/python3.8/site-packages/deepmreye/preprocess.py in get_masks(data_path)
    118         Edges of mask in z-dimension
    119     """     
--> 120     eyemask_small = ants.image_read(data_path + 'eyemask_small.nii')
    121     eyemask_big = ants.image_read(data_path + 'eyemask_big.nii')
    122     dme_template = ants.image_read(data_path + 'dme_template.nii')

~/github/CPP_deepMReye/code/env/lib/python3.8/site-packages/ants/core/ants_image_io.py in image_read(filename, dimension, pixeltype, reorient)
    513         filename = os.path.expanduser(filename)
    514         if not os.path.exists(filename):
--> 515             raise ValueError("File %s does not exist!" % filename)
    516 
    517         hinfo = image_header_info(filename)

ValueError: File ../deepmreye/masks/eyemask_small.nii does not exist!

Given the default of get_masks and I am not sure that they get "installed" (or at all) by the pip install

get_masks(data_path='../deepmreye/masks/'):

Will pass a value to the path to the masks in the repo on my local machine but there may be a smarter way of doing this.

Address #6. This is a first and quick attempt at setting up a configuration file (to have a package-like setup) and solve the missing masks in some setups. ~It's still a WIP (I need to fix a couple of errors).~

The real part that you need is in lines 42-50, that expressively adds files in the masks folder.

• [x] sets up makefile to help build wheel locally and push to pypi
• [x] update config and remove extra dependencies
• [x] add github action to push to pypi when making a github release

tried to install and got the following error

this seems to be due to the fact that I am using an M1 apple computer: see here

pip install git+https://github.com/DeepMReye/DeepMReye.git
Collecting git+https://github.com/DeepMReye/DeepMReye.git
  Cloning https://github.com/DeepMReye/DeepMReye.git to /private/var/folders/4s/b4y96bxd7n979w298f1q3nm40000gq/T/pip-req-build-f3a6j20h
  Running command git clone -q https://github.com/DeepMReye/DeepMReye.git /private/var/folders/4s/b4y96bxd7n979w298f1q3nm40000gq/T/pip-req-build-f3a6j20h
  Resolved https://github.com/DeepMReye/DeepMReye.git to commit 1c349e1c8477e4261f0de685c2d5ccb180dd7266
Collecting numpy
  Using cached numpy-1.23.3-cp39-cp39-macosx_11_0_arm64.whl (13.4 MB)
Collecting pandas
  Using cached pandas-1.5.0-cp39-cp39-macosx_11_0_arm64.whl (10.9 MB)
Collecting matplotlib
  Using cached matplotlib-3.6.0-cp39-cp39-macosx_11_0_arm64.whl (7.2 MB)
Collecting scipy
  Using cached scipy-1.9.1-cp39-cp39-macosx_12_0_arm64.whl (29.9 MB)
Collecting ipython
  Using cached ipython-8.5.0-py3-none-any.whl (752 kB)
Collecting plotly
  Using cached plotly-5.10.0-py2.py3-none-any.whl (15.2 MB)
Collecting scikit-learn
  Using cached scikit_learn-1.1.2-cp39-cp39-macosx_12_0_arm64.whl (7.7 MB)
Collecting antspyx
  Using cached antspyx-0.3.3.tar.gz (7.0 MB)
ERROR: Could not find a version that satisfies the requirement tensorflow<2.7 (from deepmreye) (from versions: none)
ERROR: No matching distribution found for tensorflow<2.7

Hi,

I have installed the packages and the conda environment (python 3.7) according to your instruction. I downloaded your example data and tried to run deepmreye_example_usage.ipynb, but I kept getting the error of Segmentation fault when reaching preprocess.run_participant(fp_func, dme_template, eyemask_big, eyemask_small, x_edges, y_edges, z_edges) (there is no other error):

Running participant sub-NDARAA948VFH
Segmentation fault (core dumped)

I have a GPU under this environment. Do you have any ideas or solutions about it? Thank you.

I've tried to run the demo but many bugs appeared: Code test:

# Import modules and add library to path
import sys
sys.path.insert(0, "/Users/admin/Desktop/Github")
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0" # Change to os.environ["CUDA_VISIBLE_DEVICES"] = "" if you dont have access to a GPU
import numpy as np 
import pandas as pd
import pickle

# DeepMReye imports
from deepmreye import architecture, train, analyse, preprocess
from deepmreye.util import util, data_generator, model_opts

# Initialize plotly figures
from plotly.offline import init_notebook_mode 
init_notebook_mode(connected = True)

# Make sure the output width is adjusted for better export as HTML
from IPython.core.display import display, HTML
display(HTML("<style>.container { width:70% !important; }</style>"))
display(HTML("<style>.output_result { max-width:70% !important; }</style>"))

# Autoreload modules
%load_ext autoreload
%autoreload 2

Bug report:

ImportError                               Traceback (most recent call last)
/var/folders/w3/l91cnb1d7dvdh581bynsm_n80000gp/T/ipykernel_22011/2184068996.py in <module>
      9 
     10 # DeepMReye imports
---> 11 from deepmreye import architecture, train, analyse, preprocess
     12 from deepmreye.util import util, data_generator, model_opts
     13 

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/deepmreye/__init__.py in <module>
      1 from . import util
----> 2 from . import preprocess
      3 from . import architecture
      4 from . import train
      5 from . import analyse

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/deepmreye/preprocess.py in <module>
      2 import pickle
      3 import numpy as np
----> 4 import ants
      5 import matplotlib.pyplot as plt
      6 from mpl_toolkits.axes_grid1.axes_divider import make_axes_locatable

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/__init__.py in <module>
      5     pass
      6 
----> 7 from .core import *
      8 from .utils import *
      9 from .segmentation import *

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/core/__init__.py in <module>
      1 
----> 2 from .ants_image import *
      3 from .ants_image_io import *
      4 
      5 from .ants_transform import *

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/core/ants_image.py in <module>
     27 import inspect
     28 
---> 29 from .. import registration, segmentation, utils, viz
     30 from . import ants_image_io as iio2
     31 

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/registration/__init__.py in <module>
      1 
      2 
----> 3 from .affine_initializer import *
      4 from .apply_transforms import *
      5 from .create_jacobian_determinant_image import *

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/registration/affine_initializer.py in <module>
      5 from tempfile import mktemp
      6 
----> 7 from .. import utils
      8 
      9 def affine_initializer(fixed_image, moving_image, search_factor=20,

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/utils/__init__.py in <module>
      1 from .add_noise_to_image import *
----> 2 from .bias_correction import *
      3 from .channels import *
      4 from .convert_nibabel import *
      5 from .crop_image import *

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/utils/bias_correction.py in <module>
      2 
      3 
----> 4 from . import process_args as pargs
      5 from .get_mask import get_mask
      6 from .iMath import iMath

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/utils/process_args.py in <module>
     12 
     13 from ..core import ants_image as iio
---> 14 from .. import lib
     15 
     16 _short_ptype_map = {

~/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/lib/__init__.py in <module>
      1 ## LOCAL ##
----> 2 from .addNoiseToImage import *
      3 from .antiAlias import *
      4 from .antsImage import *
      5 from .antsImageClone import *

ImportError: dlopen(/Users/admin/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/lib/addNoiseToImage.cpython-37m-darwin.so, 0x0002): Library not loaded: /opt/X11/lib/libpng16.16.dylib
  Referenced from: /Users/admin/miniconda3/envs/deepmreye/lib/python3.7/site-packages/ants/lib/addNoiseToImage.cpython-37m-darwin.so
  Reason: tried: '/opt/X11/lib/libpng16.16.dylib' (no such file), '/usr/local/lib/libpng16.16.dylib' (no such file), '/usr/lib/libpng16.16.dylib' (no such file)

Python version: Python 3.7.13

Pip list:

Package Version

absl-py 0.15.0 antspyx 0.3.3 appnope 0.1.3 argon2-cffi 21.3.0 argon2-cffi-bindings 21.2.0 astunparse 1.6.3 attrs 21.4.0 backcall 0.2.0 bcrypt 3.2.2 beautifulsoup4 4.11.1 bleach 5.0.1 cached-property 1.5.2 cachetools 4.2.4 certifi 2022.6.15 cffi 1.15.1 charset-normalizer 2.1.0 chart-studio 1.1.0 clang 5.0 cmake 3.22.5 cryptography 37.0.2 cycler 0.11.0 debugpy 1.6.0 decorator 5.1.1 deepmreye 0.1.dev147+gcabc3f0 defusedxml 0.7.1 entrypoints 0.4 fastjsonschema 2.15.3 flatbuffers 1.12 fonttools 4.33.3 gast 0.4.0 google-auth 1.35.0 google-auth-oauthlib 0.4.6 google-pasta 0.2.0 grpcio 1.47.0 h5py 3.1.0 idna 3.3 imageio 2.19.3 importlib-metadata 4.12.0 importlib-resources 5.8.0 ipykernel 6.15.0 ipython 7.34.0 ipython-genutils 0.2.0 ipywidgets 7.7.1 jedi 0.18.1 Jinja2 3.1.2 joblib 1.1.0 jsonschema 4.6.1 jupyter 1.0.0 jupyter-client 7.3.4 jupyter-console 6.4.4 jupyter-core 4.10.0 jupyterlab-pygments 0.2.2 jupyterlab-widgets 1.1.1 keras 2.6.0 Keras-Preprocessing 1.1.2 kiwisolver 1.4.3 Markdown 3.3.7 MarkupSafe 2.1.1 matplotlib 3.5.2 matplotlib-inline 0.1.3 mistune 0.8.4 nbclient 0.6.6 nbconvert 6.5.0 nbformat 5.4.0 nest-asyncio 1.5.5 networkx 2.6.3 nibabel 4.0.1 notebook 6.4.12 numpy 1.19.5 oauthlib 3.2.0 opt-einsum 3.3.0 packaging 21.3 pandas 1.3.5 pandocfilters 1.5.0 paramiko 2.11.0 parso 0.8.3 patsy 0.5.2 pexpect 4.8.0 pickleshare 0.7.5 Pillow 9.2.0 pip 21.2.2 plotly 5.9.0 prometheus-client 0.14.1 prompt-toolkit 3.0.30 protobuf 3.19.4 psutil 5.9.1 ptyprocess 0.7.0 pyasn1 0.4.8 pyasn1-modules 0.2.8 pycparser 2.21 Pygments 2.12.0 PyNaCl 1.5.0 pyparsing 3.0.9 pyrsistent 0.18.1 python-dateutil 2.8.2 pytz 2022.1 PyWavelets 1.3.0 PyYAML 6.0 pyzmq 23.2.0 qtconsole 5.3.1 QtPy 2.1.0 requests 2.28.1 requests-oauthlib 1.3.1 retrying 1.3.3 rsa 4.8 scikit-image 0.19.3 scikit-learn 1.0.2 scipy 1.7.3 Send2Trash 1.8.0 setuptools 61.2.0 six 1.15.0 soupsieve 2.3.2.post1 statsmodels 0.13.2 tenacity 8.0.1 tensorboard 2.6.0 tensorboard-data-server 0.6.1 tensorboard-plugin-wit 1.8.1 tensorflow 2.6.5 tensorflow-estimator 2.6.0 termcolor 1.1.0 terminado 0.15.0 threadpoolctl 3.1.0 tifffile 2021.11.2 tinycss2 1.1.1 tornado 6.2 traitlets 5.3.0 typing-extensions 3.10.0.2 urllib3 1.26.9 wcwidth 0.2.5 webcolors 1.12 webencodings 0.5.1 Werkzeug 2.1.2 wheel 0.37.1 widgetsnbextension 3.6.1 wrapt 1.12.1 zipp 3.8.0

Links I've tried:

Stackoverflow Homebrew

ok this should be the actual fix for #6

To test it, make sure that the MWE mention in here does produce the bug.

Then uninstall deepmreye install the version from my branch with the fix:

pip uninstall deepmreye
pip install git+https://github.com/Remi-Gau/[email protected]_masks

And rerun the "test" to make sure the masks and templates are found.

launch iPython

ipython

try to get the masks

from deepmreye import preprocess
(
    eyemask_small,
    eyemask_big,
    dme_template,
    mask,
    x_edges,
    y_edges,
    z_edges,
) = preprocess.get_masks()

related to #31

• Dockerfile will use deepmreye from pypi
• dev Dockerfile will use the local version of pypi
• update default model to use in docker and notebooks

We are aware of installation issues of DeepMReye on Apple MacBooks with M1 or M2 chips.

The DeepLabCut team made us aware of a potential solution: Use miniconda3 instead of anaconda. https://github.com/DeepLabCut/DeepLabCut/blob/main/docs/installation.md#install-anaconda-or-use-miniconda3-ideal-for-macos-users

We will be testing this soon, but if you have an M1/M2 MacBook and run into issues, please try out the suggested solution and let us know if it works.

Hello, first of all thank you for this library! I wanted to ask how would you recommend to implement the calibration data acquired through the Matlab code you published. Should I need to turn the edf Eyelink files to a specificformat (asc, csvor other)? I am also confused at which part of the main Python script (as shown on the exemplary data on the Jupyter Notebook) the calibration data is used?

Tackle after merging of #18

the other errors came either from changing v2->v3 or from matrix os (I guess the latter).

yes most likely the latter because the way it is set up now, all tests are only run on Linux

See this workflow that is supposed to run on MacOS but actually ran on Ubuntu https://github.com/DeepMReye/DeepMReye/runs/7576038296?check_suite_focus=true#step:1:3

So I would suggest merging this and fixing the CI for OS in another PR after that.

Originally posted by @Remi-Gau in https://github.com/DeepMReye/DeepMReye/issues/18#issuecomment-1200162849

Current notebooks only support regression targets, therefore we should:

• Add Jupyter notebook with code for model training eyes open vs. eyes closed (or other classification targets)
• Add model weights to OSF