# Particle Classification
Python scripts for particle classification
Used by particle trieur to perform model training.
## Installation
```
conda create -n miso python=3.9
conda activate miso
conda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0
pip install tensorflow==2.10.1
pip install miso
```
## Updating
```
conda activate miso
pip install -U miso
```
## Command line interface (CLI)
### Train a model
TBD
### Classify a folder of images
Classifies a folder of images and saves the result in a CSV. This CSV can be imported into Particle Trieur. If the images are organised by sample into subfolders it will use the subfolder name as the sample name, else specify the sample name manually.
```
Usage: python -m miso classify-folder [OPTIONS]
Classify images in a folder and output the results to a CSV file.
Options:
-m, --model PATH Path to the model information. [required]
-i, --input PATH Path to the directory containing images.
[required]
-o, --output PATH Path where the output CSV will be saved.
[required]
-b, --batch_size INTEGER Batch size for processing images. [default:
32]
-s, --sample TEXT Default sample name if not using
subdirectories. [default: unknown]
-u, --unsure_threshold FLOAT Threshold below which predictions are
considered unsure. [default: 0.0]
```
### Morphology of a folder of plankton images
Does morphology on a folder of plankton images and saves the result in a CSV. This CSV can be imported into Particle Trieur as parameters. If the images are organised by sample into subfolders it will use the subfolder name as the sample name, else specify the sample name manually.
The plankton model must first be downloaded from here: https://1drv.ms/f/s!AiQM7sVIv7fanuNzfcw2O8kAnDU26Q?e=NA5ztG
Make sure to put the `model.onnx` and the `model_info.xml` files in the same folder
```
Usage: python -m miso segment-folder [OPTIONS]
Segment images in a folder and output the results.
Options:
-m, --model PATH Path to the model information. [required]
-i, --input PATH Path to the folder containing images. [required]
-o, --output PATH Path where the morphology csv will be saved.
[required]
-b, --batch_size INTEGER Batch size for processing images. [default: 32]
-s, --sample TEXT Default sample name [default: unknown]
-t, --threshold FLOAT Threshold for segmentation. [default: 0.5]
--save-contours Whether to save contours or not.
```
Raw data
{
"_id": null,
"home_page": "https://github.com/microfossil/particle-classification",
"name": "miso",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.9,<=3.11",
"maintainer_email": "",
"keywords": "microfossil,cnn",
"author": "Ross Marchant",
"author_email": "ross.g.marchant@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/8b/3d/d37b7d628d1570631c4451868204936b321b7a050fcc74c4f1a7a9f4f4bf/miso-3.1.24.tar.gz",
"platform": null,
"description": "# Particle Classification\nPython scripts for particle classification\n\nUsed by particle trieur to perform model training.\n\n## Installation\n\n```\nconda create -n miso python=3.9\nconda activate miso\nconda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0\npip install tensorflow==2.10.1\npip install miso\n```\n\n## Updating\n\n```\nconda activate miso\npip install -U miso\n```\n\n## Command line interface (CLI)\n\n### Train a model\n\nTBD\n\n### Classify a folder of images\n\nClassifies a folder of images and saves the result in a CSV. This CSV can be imported into Particle Trieur. If the images are organised by sample into subfolders it will use the subfolder name as the sample name, else specify the sample name manually.\n\n```\nUsage: python -m miso classify-folder [OPTIONS]\n\n Classify images in a folder and output the results to a CSV file.\n\nOptions:\n -m, --model PATH Path to the model information. [required]\n -i, --input PATH Path to the directory containing images.\n [required]\n -o, --output PATH Path where the output CSV will be saved.\n [required]\n -b, --batch_size INTEGER Batch size for processing images. [default:\n 32]\n -s, --sample TEXT Default sample name if not using\n subdirectories. [default: unknown]\n -u, --unsure_threshold FLOAT Threshold below which predictions are\n considered unsure. [default: 0.0]\n```\n\n### Morphology of a folder of plankton images\n\nDoes morphology on a folder of plankton images and saves the result in a CSV. This CSV can be imported into Particle Trieur as parameters. If the images are organised by sample into subfolders it will use the subfolder name as the sample name, else specify the sample name manually.\n\nThe plankton model must first be downloaded from here: https://1drv.ms/f/s!AiQM7sVIv7fanuNzfcw2O8kAnDU26Q?e=NA5ztG\n\nMake sure to put the `model.onnx` and the `model_info.xml` files in the same folder\n\n```\nUsage: python -m miso segment-folder [OPTIONS]\n\n Segment images in a folder and output the results.\n\nOptions:\n -m, --model PATH Path to the model information. [required]\n -i, --input PATH Path to the folder containing images. [required]\n -o, --output PATH Path where the morphology csv will be saved.\n [required]\n -b, --batch_size INTEGER Batch size for processing images. [default: 32]\n -s, --sample TEXT Default sample name [default: unknown]\n -t, --threshold FLOAT Threshold for segmentation. [default: 0.5]\n --save-contours Whether to save contours or not.\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Python scripts for training CNNs for particle classification",
"version": "3.1.24",
"project_urls": {
"Homepage": "https://github.com/microfossil/particle-classification",
"Paper": "https://jm.copernicus.org/articles/39/183/2020/",
"Source": "https://github.com/microfossil/particle-classification"
},
"split_keywords": [
"microfossil",
"cnn"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a97240f8109344ac8aa8f5da68090ca07f192032a0bf5839fbae31701f23d6c0",
"md5": "75cfd740b01f78e7a43465936a866b95",
"sha256": "dcc411b86b64bae01d0d92b87126c910b4afa5cccf2011f1ae12141d09cd73ca"
},
"downloads": -1,
"filename": "miso-3.1.24-py3-none-any.whl",
"has_sig": false,
"md5_digest": "75cfd740b01f78e7a43465936a866b95",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9,<=3.11",
"size": 106021,
"upload_time": "2024-02-20T11:52:56",
"upload_time_iso_8601": "2024-02-20T11:52:56.477193Z",
"url": "https://files.pythonhosted.org/packages/a9/72/40f8109344ac8aa8f5da68090ca07f192032a0bf5839fbae31701f23d6c0/miso-3.1.24-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "8b3dd37b7d628d1570631c4451868204936b321b7a050fcc74c4f1a7a9f4f4bf",
"md5": "ff9c8c8341a0fbb0c21a04c060aa2023",
"sha256": "072adb5be9b0c2412d781ac040a04f2e9c2205ba4f84b8ffc368911b97c176d9"
},
"downloads": -1,
"filename": "miso-3.1.24.tar.gz",
"has_sig": false,
"md5_digest": "ff9c8c8341a0fbb0c21a04c060aa2023",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9,<=3.11",
"size": 84450,
"upload_time": "2024-02-20T11:52:58",
"upload_time_iso_8601": "2024-02-20T11:52:58.440802Z",
"url": "https://files.pythonhosted.org/packages/8b/3d/d37b7d628d1570631c4451868204936b321b7a050fcc74c4f1a7a9f4f4bf/miso-3.1.24.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-20 11:52:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "microfossil",
"github_project": "particle-classification",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "miso"
}
JSON
