Weak Segments Performance

.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "vision/auto_checks/model_evaluation/plot_weak_segments_performance.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_vision_auto_checks_model_evaluation_plot_weak_segments_performance.py: .. _vision__weak_segments_performance: Weak Segments Performance ************************* This notebook provides an overview for using and understanding the weak segment performance check. **Structure:** * `What is the purpose of the check? <#what-is-the-purpose-of-the-check>`__ * `Automatically detecting weak segments <#automatically-detecting-weak-segments>`__ * `Generate Dataset <#generate-dataset>`__ * `Run the check <#run-the-check>`__ * `Define a condition <#define-a-condition>`__ What is the purpose of the check? ================================== The check is designed to easily identify the model's weakest segments. The segments are characterized by the :ref:`image properties ` such as contrast and aspect ratio. Automatically detecting weak segments ===================================== The check performs several steps: #. We calculate the image properties for each sample. The properties to calculate can be passed explicitly or resort to the default image properties. #. We calculate loss for each sample in the dataset using the provided model or predictions, the loss function can be passed explicitly or set to a default based on the task type. #. We train multiple simple tree based models, each one is trained using two properties to predict the per sample error calculated before. #. We extract the corresponding data samples for each of the leaves in each of the trees (data segments) and calculate the model performance on them. For the weakest data segments detected we also calculate the model's performance on data segments surrounding them. .. GENERATED FROM PYTHON SOURCE LINES 46-54 Generate Dataset ================= .. note:: In this example, we use the pytorch version of the coco dataset and model. In order to run this example using tensorflow, please change the import statements to:: from deepchecks.vision.datasets.detection import coco_tensorflow as coco .. GENERATED FROM PYTHON SOURCE LINES 54-60 .. code-block:: default from deepchecks.vision.checks import WeakSegmentsPerformance from deepchecks.vision.datasets.detection import coco_torch as coco coco_data = coco.load_dataset(train=False, object_type='VisionData') .. GENERATED FROM PYTHON SOURCE LINES 61-63 Run the check ============= .. GENERATED FROM PYTHON SOURCE LINES 63-67 .. code-block:: default check = WeakSegmentsPerformance() result = check.run(coco_data) result .. rst-class:: sphx-glr-script-out .. code-block:: none Processing Batches: | | 0/1 [Time: 00:00] Processing Batches: |█████| 1/1 [Time: 00:00] Processing Batches: |█████| 1/1 [Time: 00:00] Computing Check: | | 0/1 [Time: 00:00] Computing Check: |█████| 1/1 [Time: 00:00] Computing Check: |█████| 1/1 [Time: 00:00] .. raw:: html

.. GENERATED FROM PYTHON SOURCE LINES 68-69 To display the results in an IDE like PyCharm, you can use the following code: .. GENERATED FROM PYTHON SOURCE LINES 69-72 .. code-block:: default # result.show_in_window() .. GENERATED FROM PYTHON SOURCE LINES 73-74 The result will be displayed in a new window. .. GENERATED FROM PYTHON SOURCE LINES 76-83 Observe the check's output -------------------------- We see in the results that the check indeed found several segments on which the model performance is below average. In the heatmap display we can see the model's performance on the weakest segments and their environment with respect to the two segmentation features. In order to get the full list of weak segments found we can look at the ``result.value`` attribute. Shown below are the 3 segments with the worst performance. .. GENERATED FROM PYTHON SOURCE LINES 83-87 .. code-block:: default result.value['weak_segments_list'].head(3) .. raw:: html

	Mean IoU	Feature1	Feature1 Range	Feature2	Feature2 Range	% of Data	Samples in Segment
0	0.510713	Brightness	(125.55977249145508, inf)	RMS Contrast	(-inf, 54.26441764831543)	7.81	[12, 24, 36, 42, 48]
1	0.516387	RMS Contrast	(-inf, 69.78135681152344)	Mean Red Relative Intensity	(-inf, 0.3166673481464386)	10.94	[1, 3, 9, 10, 17, 36, 62]
2	0.518545	Aspect Ratio	(0.66796875, inf)	Mean Red Relative Intensity	(0.32986657321453094, 0.34265194833278656)	12.50	[8, 31, 33, 37, 41, 45, 48, 60]

.. GENERATED FROM PYTHON SOURCE LINES 88-90 Now we will run a check with properties and minimum segment size ratio (the minimal fraction of the data to be considered as a segment) different from the defaults. .. GENERATED FROM PYTHON SOURCE LINES 90-98 .. code-block:: default from deepchecks.vision.utils.image_properties import brightness, texture_level properties = [{'name': 'brightness', 'method': brightness, 'output_type': 'numerical'}, {'name': ' texture', 'method': texture_level, 'output_type': 'numerical'}] check = WeakSegmentsPerformance(segment_minimum_size_ratio=0.03, image_properties=properties) result = check.run(coco_data) result.show() .. rst-class:: sphx-glr-script-out .. code-block:: none Processing Batches: | | 0/1 [Time: 00:00] Processing Batches: |█████| 1/1 [Time: 00:00] Processing Batches: |█████| 1/1 [Time: 00:00] Computing Check: | | 0/1 [Time: 00:00] Computing Check: |█████| 1/1 [Time: 00:00] Computing Check: |█████| 1/1 [Time: 00:00] .. raw:: html

Weak Segments Performance

.. GENERATED FROM PYTHON SOURCE LINES 99-105 Define a condition ================== We can add a condition that will validate the model's performance on the weakest segment detected is above a certain threshold. A scenario where this can be useful is when we want to make sure that the model is not under performing on a subset of the data that is of interest to us. .. GENERATED FROM PYTHON SOURCE LINES 105-111 .. code-block:: default # Let's add a condition and re-run the check: check.add_condition_segments_relative_performance_greater_than(0.1) result = check.run(coco_data) result.show(show_additional_outputs=False) .. rst-class:: sphx-glr-script-out .. code-block:: none Processing Batches: | | 0/1 [Time: 00:00] Processing Batches: |█████| 1/1 [Time: 00:00] Processing Batches: |█████| 1/1 [Time: 00:00] Computing Check: | | 0/1 [Time: 00:00] Computing Check: |█████| 1/1 [Time: 00:00] Computing Check: |█████| 1/1 [Time: 00:00] .. raw:: html

Weak Segments Performance

.. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 2.860 seconds) .. _sphx_glr_download_vision_auto_checks_model_evaluation_plot_weak_segments_performance.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_weak_segments_performance.py ` .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_weak_segments_performance.ipynb ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_