mlclassifier is a package with custom algorithms to classify data using ml. It currently only supports image classification.
To install it, use pip install mlclassifier.
To classify images, you must have a dataset for the images with this folder structure
dataset_folder/
├── class1/
│ ├── image1.jpg
│ ├── image2.jpg
│ └── ...
└── class2/
├── image1.jpg
├── image2.jpg
└── ...
The image names or class names don't matter. The classifier assigns a class number in the order of classes from top to bottom.
To classify images, you first need to train the model using ImageClassifierTrainer.
from mlclassifier import ImageClassifierTrainer # import the trainer
import mlclassifier # import the package
trainer = ImageClassifierTrainer("<the_path_to_your_dataset", method=mlclassifier.PICK_BEST, # Create the ImageClassiferTrainerObject
resize_size=(128, 128), model_path="<path_you_want_to_save_the_model>",
n_runs=5)
trainer.fit() # train the model
The method parameter is used to specify which feature extraction method to use.
You can use HOG (mlclassifier.HOG), or ORB (mlclassifier.ORB), or LBP (mlclassifier.LBP), or you can make it run all 3 and save the best one using mlclassifier.PICK_BEST.
The resize_size parameter is the size you want to resize all the images to for consistency
The n_runs parameter is used to set the number of times you want to train the classifier. It will pick the best trained one out of all the runs and save it.
The model_path parameter must be a .pkl file.
At the end of the training cycle, it will print the Average FPS if you were to stream images to it, the time it took per image, and the score.
After training, you can start classifying images using ImageClassifier.
from mlclassifier import ImageClassifier # import the ImageClassifier
import cv2 # import cv2
classifier = ImageClassifier("<model_path>") # create the classifier object
image = cv2.imread("<path_to_your_image") # read the image
predicted_class = classifier.predict(image) # predict the class
print(predicted_class) # print the predicted class
Metadata
Release files for mlclassifier 1.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mlclassifier-1.1.0.tar.gz | 6.6 kB | Without provenance | Details for mlclassifier-1.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mlclassifier-1.1.0-py3-none-any.whl | Python 3 | none | any | Details for mlclassifier-1.1.0-py3-none-any.whl |
Total release size: 14.0 kB
Release files / mlclassifier-1.1.0.tar.gz
| Download URL | mlclassifier-1.1.0.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7f0d1412ca4f1b71be827f32ad3f9fe231efbf4e93ab4e1036e6b9b559db736f
|
|
BLAKE2b-256 checksum How to use checksums |
1125fae18cf30c71d9e22c6c52d8b21e705817631129f56e546794048a9c1946
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|
Release files / mlclassifier-1.1.0-py3-none-any.whl
| Download URL | mlclassifier-1.1.0-py3-none-any.whl |
|---|---|
| Size | 7.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e5ed82295f58a88827dcfcecf333d1ffd5ece021d7ef056c070868c908f12b68
|
|
BLAKE2b-256 checksum How to use checksums |
b236f91a8ab6bb3864d0474c2c1d01261d6872ccbc76300befa41577dc4fe7e3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|
Security for mlclassifier 1.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.