test_features, test_labels_mask[:, :num_classes_1],
test_labels_mask[:, -num_classes_2:]
])
title = "basset_cor_hist_best_class_1.svg"
correlations_1 = plot_utils.plot_cors(
test_labels[test_tags == 1, :][:, :num_classes_1],
predicted_labels_1[test_tags == 1, :], output_directory, title)
title = "basset_cor_hist_best_class_2.svg"
correlations_2 = plot_utils.plot_cors(
test_labels[test_tags == 2, :][:, -num_classes_2:],
predicted_labels_2[test_tags == 2, :], output_directory, title)
quantile_indx_1 = plot_utils.plot_cors_piechart(
correlations_1, test_labels[test_tags == 1, :][:, :num_classes_1],
output_directory, 'basset_cor_pie_class_1.svg')
plot_utils.plot_random_predictions(
test_labels[test_tags == 1, :][:, :num_classes_1],
predicted_labels_1[test_tags == 1, :], correlations_1,
quantile_indx_1, test_names[test_tags == 1], output_directory,
len(class_names_1), class_names_1, 'class_1_')
plot_utils.plot_random_predictions(
test_labels[test_tags == 1, :][:, :num_classes_1],
predicted_labels_1[test_tags == 1, :],
correlations_1,
quantile_indx_1,
test_names[test_tags == 1],
output_directory,
len(class_names_1),
class_names_1,
predicted_labels = model.predict(np.stack(test_features))
title = "basset_cor_hist_latest.svg"
correlations = plot_utils.plot_cors(test_labels, predicted_labels,
output_directory, title)
# Using the Best weights
model = create_model(input_size, num_classes, learning_rate,
combined_loss_weight)
model.load_weights(checkpoint_path_weights)
model.save(output_directory + 'whole_model_best.h5')
predicted_labels = model.predict(np.stack(test_features))
title = "basset_cor_hist_best.svg"
correlations = plot_utils.plot_cors(test_labels, predicted_labels,
output_directory, title)
plot_utils.plot_corr_variance(test_labels, correlations, output_directory)
quantile_indx = plot_utils.plot_cors_piechart(correlations, test_labels,
output_directory)
plot_utils.plot_random_predictions(test_labels, predicted_labels, correlations,
quantile_indx, test_names, output_directory,
len(class_names), class_names)
# Save predictions, correlations and testset
np.save(output_directory + 'predictions.npy', predicted_labels)
np.save(output_directory + 'correlations.npy', correlations)
np.save(output_directory + 'test_data.npy', test_features)
np.save(output_directory + 'test_labels.npy', test_labels)
np.save(output_directory + 'test_OCR_names.npy', test_names)
# Clear out session
tf.keras.backend.clear_session()