working on CI

Nico-Curti · Nov 8, 2023 · a23a83f · a23a83f
1 parent 5f11224
commit a23a83f
Show file tree

Hide file tree

Showing 8 changed files with 18 additions and 5 deletions.
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -12,7 +12,7 @@ jobs:
 
     strategy:
       matrix:
-        python-version: [3.8]
+        python-version: [3.9]
 
     steps:
 

diff --git a/README.md b/README.md
@@ -122,7 +122,7 @@ The full list of available flags for the customization of the command line could
 
 ```bash
 $ deepskin --help
-usage: deepskin [-h] [--version] [--input FILEPATH] [--verbose]
+usage: deepskin [-h] [--version] [--input FILEPATH] [--verbose] [--mask] [--pwat]
 
 deepskin library - Wound analysis using smartphone images
 
@@ -133,6 +133,9 @@ optional arguments:
                         Input filename or path on which load the image. Ref
                         https://docs.opencv.org/4.x/d4/da8/group__imgcodecs.html for the list of supported formats.
   --verbose, -w         Enable/Disable the code logging
+  --mask, -m            Evaluate the semantic segmentation mask using the Deepskin model; the resulting mask will be
+                        saved to a png file in the same location of the input file
+  --pwat, -p            Compute the PWAT score of the given wound-image
 
 Deepskin Python package v0.0.1
 ```

diff --git a/deepskin/__main__.py b/deepskin/__main__.py
@@ -8,7 +8,7 @@
 # package version
 from .__version__ import __version__
 # segmentation model for wound identification
-from .model import wound_segmentation
+from .segmentation import wound_segmentation
 # constant values
 from .constants import GREEN_COLOR_CODE
 from .constants import RED_COLOR_CODE

diff --git a/docs/source/API/modules.rst b/docs/source/API/modules.rst
@@ -6,6 +6,7 @@ Python API
 
    imgproc
    model
+   segmentation
    features
    pwat
 
diff --git a/docs/source/API/segmentation.rst b/docs/source/API/segmentation.rst
@@ -0,0 +1,8 @@
+Deepskin segmentation
+---------------------
+
+.. automodule:: deepskin.segmentation
+   :members:
+   :show-inheritance:
+   :inherited-members:
+   :private-members:
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -72,3 +72,4 @@
 nbsphinx_input_prompt = 'In [%s]:'
 nbsphinx_kernel_name = 'python3'
 nbsphinx_output_prompt = 'Out[%s]:'
+nbsphinx_allow_errors = True
diff --git a/docs/source/notebooks/deepskin_pwat.ipynb b/docs/source/notebooks/deepskin_pwat.ipynb
@@ -136,7 +136,7 @@
    "metadata": {},
    "source": [
     "At the end of this step, you will have a set of numeric features which characterize both the wound and peri-wound areas identified by the segmentation model.\n",
-    "A detailed description of the features pre-computed by the `deepskin` model is discussed in the work of Curti et al. [1]().\n",
+    "A detailed description of the features pre-computed by the `deepskin` model is discussed in the work of Curti et al.\n",
     "\n",
     "For a faster evaluation, a re-organization of the features into a dataframe structure could help for the next step."
    ]

diff --git a/requirements.txt b/requirements.txt
@@ -1,4 +1,4 @@
 numpy
 mahotas
 opencv-python
-tensorflow==2.8.0
+tensorflow>=2.8.0