## Eazyml Image Explainable AI
  
This package focuses on segmentation prediction, explainability, active learning and online learning for image dataset.
### Features
- Active learning focuses on reducing the amount of labeled data required to train the model while maximizing performance, making it particularly useful when labeling data is expensive or time-consuming. By prioritizing uncertain or diverse examples, active learning accelerates model improvement and enhances efficiency.
- Online learning is a machine learning approach where models are trained incrementally as data becomes available, rather than using a fixed, pre-existing dataset. This method is well-suited for dynamic environments, enabling real-time updates and adaptability to new patterns or changes in data streams.
### APIs
It provides following apis :
1. ez_image_active_learning :
This API sorts test images based on explainability scores for the model’s predictions. If a “query count” is specified in the options, it returns the indices and corresponding scores for that number of inputs.
```python
ez_image_active_learning(
filenames=['..', '..'],
model_path='path_of_model',
predicted_filenames=['path_of_model_prediction_file_names'],
options={
"query_count": 10,
"training_data_path": "path/to/training/data.csv",
"score_strategy": "weighted-moments",
"al_strategy": "pool-based",
"xai_strategy": "gradcam",
"gradcam_layer": "layer_name",
"model_num": "1"
}
)
2. ez_image_model_evaluate :
This API validates a model using provided data and returns the model evaluation.
```python
ez_image_model_evaluate(
validation_data_path='path_of_new_data_for_validation',
model_path='path_of_model',
options={
"required_functions": {
"loss_fn": '...',
"metric_fns": '...',
"input_preprocess_fn": '',
"label_preprocess_fn": '',
"output_process_fn": ''
},
"batch_size": 32,
"log_file": "path/to/log/file"
})
3. ez_image_online_learning :
This API updates a given model using new training data and saves the updated model. The update process adapts based on the Online Learning strategy or optimizes performance on provided validation data.
```python
ez_image_online_learning(
validation_data_path='path_of_new_data_for_validation',
model_path='path_of_model',
options={
"required_functions": {
"loss_fn": '...',
"metric_fns": '...',
"input_preprocess_fn": '',
"label_preprocess_fn": '',
"output_process_fn": ''
},
"batch_size": 32,
"log_file": "path/to/log/file"
}
)
4. ez_xai_image_explain :
This API provides confidence scores and image explanations for model predictions. It can process a single image or multiple images, returning explanations for all predictions.
```python
ez_xai_image_explain(
filenames=['..', '..'],
model_path='path_of_model',
predicted_filenames=['path_of_model_prediction_file_names'],
options={
"training_data_path": "...",
"score_strategy": "weighted-moments",
"xai_strategy": "gradcam",
"xai_image_path": "...",
"gradcam_layer": "layer_name",
"model_num": "1",
"required_functions": {...}
}
)
Raw data
{
"_id": null,
"home_page": "https://eazyml.com/",
"name": "eazyml-xai-image",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "python",
"author": "Eazyml",
"author_email": "admin@ipsoftlabs.com",
"download_url": "https://files.pythonhosted.org/packages/b1/70/feed9c889bc90f5dd24256c7de7ef37237941b1fdb81d95f7c54f4eb5138/eazyml_xai_image-0.0.9.tar.gz",
"platform": null,
"description": "## Eazyml Image Explainable AI \n  \n\nThis package focuses on segmentation prediction, explainability, active learning and online learning for image dataset.\n\n### Features\n- Active learning focuses on reducing the amount of labeled data required to train the model while maximizing performance, making it particularly useful when labeling data is expensive or time-consuming. By prioritizing uncertain or diverse examples, active learning accelerates model improvement and enhances efficiency.\n- Online learning is a machine learning approach where models are trained incrementally as data becomes available, rather than using a fixed, pre-existing dataset. This method is well-suited for dynamic environments, enabling real-time updates and adaptability to new patterns or changes in data streams.\n\n### APIs\nIt provides following apis :\n\n1. ez_image_active_learning :\nThis API sorts test images based on explainability scores for the model\u2019s predictions. If a \u201cquery count\u201d is specified in the options, it returns the indices and corresponding scores for that number of inputs.\n\n ```python\n ez_image_active_learning(\n filenames=['..', '..'],\n model_path='path_of_model',\n predicted_filenames=['path_of_model_prediction_file_names'],\n options={\n \"query_count\": 10,\n \"training_data_path\": \"path/to/training/data.csv\",\n \"score_strategy\": \"weighted-moments\",\n \"al_strategy\": \"pool-based\",\n \"xai_strategy\": \"gradcam\",\n \"gradcam_layer\": \"layer_name\",\n \"model_num\": \"1\"\n }\n )\n\n2. ez_image_model_evaluate :\nThis API validates a model using provided data and returns the model evaluation.\n ```python\n ez_image_model_evaluate(\n validation_data_path='path_of_new_data_for_validation',\n model_path='path_of_model',\n options={\n \"required_functions\": {\n \"loss_fn\": '...',\n \"metric_fns\": '...',\n \"input_preprocess_fn\": '',\n \"label_preprocess_fn\": '',\n \"output_process_fn\": ''\n },\n \"batch_size\": 32,\n \"log_file\": \"path/to/log/file\"\n })\n\n3. ez_image_online_learning :\nThis API updates a given model using new training data and saves the updated model. The update process adapts based on the Online Learning strategy or optimizes performance on provided validation data.\n ```python\n ez_image_online_learning(\n validation_data_path='path_of_new_data_for_validation',\n model_path='path_of_model',\n options={\n \"required_functions\": {\n \"loss_fn\": '...',\n \"metric_fns\": '...',\n \"input_preprocess_fn\": '',\n \"label_preprocess_fn\": '',\n \"output_process_fn\": ''\n },\n \"batch_size\": 32,\n \"log_file\": \"path/to/log/file\"\n }\n )\n\n4. ez_xai_image_explain :\nThis API provides confidence scores and image explanations for model predictions. It can process a single image or multiple images, returning explanations for all predictions.\n ```python\n ez_xai_image_explain(\n filenames=['..', '..'],\n model_path='path_of_model',\n predicted_filenames=['path_of_model_prediction_file_names'],\n options={\n \"training_data_path\": \"...\",\n \"score_strategy\": \"weighted-moments\",\n \"xai_strategy\": \"gradcam\",\n \"xai_image_path\": \"...\",\n \"gradcam_layer\": \"layer_name\",\n \"model_num\": \"1\",\n \"required_functions\": {...}\n }\n )\n\n",
"bugtrack_url": null,
"license": null,
"summary": "eazyml image explain api",
"version": "0.0.9",
"project_urls": {
"Documentation": "https://eazyml-docs.readthedocs.io/en/latest/",
"Homepage": "https://eazyml.com/"
},
"split_keywords": [
"python"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "49be93bfb40a3f48f8af46de99d0ba5ffd94f7da5d2f4d595284c9e74b5d80bb",
"md5": "79fe49d924b5a13d123d92e20e762a85",
"sha256": "80885a9c61584df2266fab2b5ef768fef0c6e27b99a597822a90d12c5865e6ea"
},
"downloads": -1,
"filename": "eazyml_xai_image-0.0.9-py3-none-any.whl",
"has_sig": false,
"md5_digest": "79fe49d924b5a13d123d92e20e762a85",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 26509212,
"upload_time": "2024-12-19T06:33:11",
"upload_time_iso_8601": "2024-12-19T06:33:11.006393Z",
"url": "https://files.pythonhosted.org/packages/49/be/93bfb40a3f48f8af46de99d0ba5ffd94f7da5d2f4d595284c9e74b5d80bb/eazyml_xai_image-0.0.9-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b170feed9c889bc90f5dd24256c7de7ef37237941b1fdb81d95f7c54f4eb5138",
"md5": "7789d0f2d47bc456d0d6c3a9b87d9d67",
"sha256": "8068e52d71d6eab4e2ea174ad4c6babd808f93ae738103785f80bb2fc2feeccd"
},
"downloads": -1,
"filename": "eazyml_xai_image-0.0.9.tar.gz",
"has_sig": false,
"md5_digest": "7789d0f2d47bc456d0d6c3a9b87d9d67",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 26254244,
"upload_time": "2024-12-19T06:33:25",
"upload_time_iso_8601": "2024-12-19T06:33:25.038888Z",
"url": "https://files.pythonhosted.org/packages/b1/70/feed9c889bc90f5dd24256c7de7ef37237941b1fdb81d95f7c54f4eb5138/eazyml_xai_image-0.0.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-19 06:33:25",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "eazyml-xai-image"
}
JSON