st = time.time()
output_image = sess.run(network, feed_dict={input: input_image})
output_image = np.array(output_image[0, :, :, :])
output_image = helpers.reverse_one_hot(output_image)
out_eval_image = output_image[:, :, 0]
out_vis_image = helpers.colour_code_segmentation(output_image)
accuracy = utils.compute_avg_accuracy(out_eval_image, gt)
class_accuracies = utils.compute_class_accuracies(
out_eval_image, gt, num_classes)
prec = utils.precision(out_eval_image, gt)
rec = utils.recall(out_eval_image, gt)
f1 = utils.f1score(out_eval_image, gt)
iou = utils.compute_mean_iou(out_eval_image, gt)
file_name = utils.filepath_to_name(val_input_names[ind])
target.write("%s, %f, %f, %f, %f, %f" %
(file_name, accuracy, prec, rec, f1, iou))
for item in class_accuracies:
target.write(", %f" % (item))
target.write("\n")
scores_list.append(accuracy)
class_scores_list.append(class_accuracies)
precision_list.append(prec)
recall_list.append(rec)
f1_list.append(f1)
iou_list.append(iou)
output_image = sess.run(network, feed_dict={z: input_image})
gt_map = cv2.imread(test_output_names[ind],
-1)[:args.crop_height, :args.crop_width]
output_image = np.array(output_image[0, :, :, :])
output_image = helpers.reverse_one_hot(output_image)
output_image = output_image[:, :, 0]
out_vis_image = helpers.colour_code_segmentation(output_image)
accuracy = utils.compute_avg_accuracy(output_image, gt_map)
class_accuracies = utils.compute_class_accuracies(output_image, gt_map)
prec = utils.precision(output_image, gt_map)
rec = utils.recall(output_image, gt_map)
f1 = utils.f1score(output_image, gt_map)
iou = utils.compute_mean_iou(output_image, gt_map)
file_name = utils.filepath_to_name(test_input_names[ind])
target.write("%s, %f, %f, %f, %f, %f" %
(file_name, accuracy, prec, rec, f1, iou))
for item in class_accuracies:
target.write(", %f" % (item))
target.write("\n")
scores_list.append(accuracy)
class_scores_list.append(class_accuracies)
precision_list.append(prec)
recall_list.append(rec)
f1_list.append(f1)
iou_list.append(iou)
