Major Refactoring 0.3.8

Author: lambda-science

myoquant/.python-version renamed to .python-version

@@ -141,7 +141,6 @@ $ myoquant sdh-analysis [OPTIONS] IMAGE_PATH
 **Options**:
 
 - `--mask-path FILE`: The path to a binary mask to hide slide region during analysis. It needs to be of the same resolution as input image and only pixel marked as 1 will be analyzed.
-- `--model-path FILE`: The SDH model path to use for analysis. Will download latest one if no path provided.
 - `--cellpose-path FILE`: The pre-computed CellPose mask to use for analysis. Will run Cellpose if no path provided. Required as an image file.
 - `--output-path PATH`: The path to the folder to save the results. Will save in the current folder if not specified.
 - `--cellpose-diameter INTEGER`: Approximative single cell diameter in pixel for CellPose detection. If not specified, Cellpose will try to deduce it.

CLI_Documentation.md

@@ -27,30 +27,29 @@ An online demo with a web interface is available at [https://lbgi.fr/MyoQuant/](
 Using pip, you can simply install MyoQuant in a python environment with a simple: `pip install myoquant`
 
 ### Installing from sources (Developers)
-
+I recommend using UV for python environment management. See [UV documentation](https://github.com/astral-sh/uv/).
 1. Clone this repository using `git clone https://github.com/lambda-science/MyoQuant.git`
-2. Create a virtual environment by using `python -m venv .venv`
-3. Activate the venv by using `source .venv/bin/activate`
-4. Install MyoQuant by using `pip install -e .`
+2. Create a virtual environment by using `uv sync`
+3. Run Myoquant with `uv run myoquant --help`
 
 ## How to Use
 
-To use the command-line tool, first activate your venv in which MyoQuant is installed: `source .venv/bin/activate`  
-Then you can perform SDH or HE analysis. You can use the command `myoquant --help` to list available commands.
+To use the command-line tool, first activate your venv in which MyoQuant is installed: `source .venv/bin/activate` or simply install the package using UV.  
+Then you can perform SDH or HE analysis. You can use the command `myoquant --help` or `uv run myoquant --help` to list available commands.
 
-## 💡Full command documentation is avaliable here: [CLI Documentation](https://github.com/lambda-science/MyoQuant/blob/main/CLI_Documentation.md)
+## 💡Full command documentation is available here: [CLI Documentation](https://github.com/lambda-science/MyoQuant/blob/main/CLI_Documentation.md)
 
 - **For SDH Image Analysis** the command is:  
   `myoquant sdh-analysis IMAGE_PATH`  
   Don't forget to run `myoquant sdh-analysis --help` for information about options.
 - **For HE Image Analysis** the command is:  
   `myoquant he-analysis IMAGE_PATH`  
-   Don't forget to run `myoquant he-analysis --help` for information about options.
+  Don't forget to run `myoquant he-analysis --help` for information about options.
 - **For ATP Image Analysis** the command is:  
   `myoquant atp-analysis IMAGE_PATH`  
-   Don't forget to run `myoquant atp-analysis --help` for information about options.
+  Don't forget to run `myoquant atp-analysis --help` for information about options.
 
-_If you're running into an issue such as `myoquant: command not found` please check if you activated your virtual environment with the package installed. And also you can try to run it with the full command: `python -m myoquant sdh-analysis --help`_
+_If you're running into an issue such as `myoquant: command not found` please check if you activated your virtual environment with the package installed. And also you can try to run it with the full command: `python -m myoquant sdh-analysis --help` or `uv run myoquant sdh-analysis --help`  
 
 ## Contact
 
@@ -79,11 +78,6 @@ For ATP Staining analysis, you can download this sample image: [HERE](https://ww
 
 ## Advanced information
 
-### Model path and manual download
-
-For the SDH Analysis our custom model will be downloaded and placed inside the myoquant package directory. You can also download it manually here: [https://huggingface.co/corentinm7/MyoQuant-SDH-Model/resolve/main/model.h5](https://huggingface.co/corentinm7/MyoQuant-SDH-Model/resolve/main/model.h5) and then you can place it in the directory of your choice and provide the path to the model file using:  
-`myoquant sdh-analysis IMAGE_PATH --model_path /path/to/model.h5`
-
 ### HuggingFace🤗 repositories for Data and Model
 
 In a effort to push for open-science, MyoQuant [SDH dataset](https://huggingface.co/datasets/corentinm7/MyoQuant-SDH-Data) and [model](https://huggingface.co/corentinm7/MyoQuant-SDH-Model) and availiable on HuggingFace🤗

README.md

@@ -0,0 +1,8 @@
+from huggingface_hub import HfApi
+api = HfApi()
+api.upload_folder(
+    folder_path="src/myoquant/streamlit",
+    repo_id="corentinm7/MyoQuant",
+    repo_type="space",
+    ignore_patterns=["*.h5", "*.keras"]
+)

deploy_hf_space.py

@@ -30,7 +30,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from myoquant.src.common_func import is_gpu_availiable,load_cellpose,run_cellpose\n",
+    "from myoquant import is_gpu_availiable,load_cellpose,run_cellpose\n",
     "import matplotlib.pyplot as plt\n",
     "try:\n",
     "    from imageio.v2 import imread\n",
@@ -260,7 +260,7 @@
    "outputs": [],
    "source": [
     "%config InlineBackend.figure_format = 'retina'\n",
-    "from myoquant.src.common_func import label2rgb, blend_image_with_label\n",
+    "from myoquant import label2rgb, blend_image_with_label\n",
     "labelRGB_map = label2rgb(image_array, label_map)\n",
     "overlay_img = blend_image_with_label(image_array, labelRGB_map)\n",
     "\n",

myoquant/README.md

@@ -14,15 +14,15 @@
     "import numpy as np\n",
     "from PIL import Image\n",
     "\n",
-    "from myoquant.common_func import (\n",
+    "from common_func import (\n",
     "    load_cellpose,\n",
     "    load_sdh_model,\n",
     "    load_stardist,\n",
     "    run_cellpose,\n",
     "    run_stardist,\n",
     ")\n",
-    "from myoquant.HE_analysis import run_he_analysis\n",
-    "from myoquant.SDH_analysis import run_sdh_analysis\n",
+    "from HE_analysis import run_he_analysis\n",
+    "from SDH_analysis import run_sdh_analysis\n",
     "\n",
     "try:\n",
     "    from imageio.v2 import imread\n",
@@ -31,10 +31,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
     "# ANALYSE SDH\n",
     "\n",
@@ -43,14 +43,6 @@
     "output_path = image_path.parents[0]\n",
     "Path(output_path).mkdir(parents=True, exist_ok=True)\n",
     "\n",
-    "# Télécharger le modèle SDH\n",
-    "model_path_abs = Path(os.path.abspath(__file__)).parents[0] / \"model.h5\"\n",
-    "if not path.exists(model_path_abs):\n",
-    "    urllib.request.urlretrieve(\n",
-    "        \"https://huggingface.co/corentinm7/MyoQuant-SDH-Model/resolve/main/model.h5\",\n",
-    "        model_path_abs,\n",
-    "    )\n",
-    "model_path = model_path_abs\n",
     "\n",
     "# Charger Cellpose\n",
     "model_cellpose = load_cellpose()\n",
@@ -64,7 +56,7 @@
     "Image.fromarray(mask_cellpose).save(output_path / cellpose_mask_filename)\n",
     "\n",
     "# Faire tourner le modèle SDH sur l'image et récupérer le tableau de sommaire (result_df)\n",
-    "model_SDH = load_sdh_model(model_path)\n",
+    "model_SDH = load_sdh_model()\n",
     "result_df, full_label_map = run_sdh_analysis(\n",
     "    image_ndarray_sdh, model_SDH, mask_cellpose\n",
     ")\n",
@@ -78,10 +70,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
     "# ANALYSE HE\n",
     "\n",

myoquant/streamlit/google_colab_deploy.ipynb

@@ -1,6 +1,6 @@
 [project]
 name = "myoquant"
-version = "0.3.5"
+version = "0.3.8"
 description = "MyoQuant🔬: a tool to automatically quantify pathological features in muscle fiber histology images."
 authors = [{name="Corentin Meyer", email="contact@cmeyer.fr"}]
 maintainers = [{name="Corentin Meyer", email="contact@cmeyer.fr"}]
@@ -13,9 +13,9 @@ requires-python = "<3.13, >=3.10"
 dependencies = [
     "tensorflow>=2.19.0",
     "keras>=3.9.0",
-    "cellpose>=3.1.1.1",
+    "cellpose<4.0.0",
     "stardist>=0.9.1",
-    "numpy<=2.1.0",
+    "numpy<2.0.0",
     "csbdeep>=0.8.1",
     "imageio>=2.37.0",
     "scikit-image>=0.25.2",
@@ -31,6 +31,7 @@ dependencies = [
     "ipykernel>=6.29.5",
     "pillow>=11.1.0",
     "tifffile>=2025.3.13",
+    "huggingface-hub>=0.32.4",
 ]
 
 [project.scripts]
@@ -45,6 +46,7 @@ dev-dependencies = [
     "pre-commit",
     "mkdocstrings",
     "mypy",
+    "tensorflow-metal>=1.2.0",
 ]
 
 [project.urls]