panel_segmentation.panel_detection.PanelDetection.testBatch

PanelDetection.testBatch(test_data, test_mask=None, batch_size=16, model=None)[source]

This function is used to predict the mask of a batch of test satellite images. Use this to test a batch of images greater than 4.

Parameters

  • test_data (nparray float) – The satellite images

  • test_mask (nparray int or float) – The mask ground truth corresponding to the test_data

  • batch_size (int) – The batch size of the test_data.

  • model (tf.keras.model.object) – A custom model can be provided as input or we can use the initialized model

Returns

  • test_res (nparray float) – The predicted masks

  • accuracy (float) – The accuarcy of prediction as compared with the ground truth if provided