Autonomous_driving_application_Car_detection - AssertionError: Wrong value on scores [0.855 0.828]

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I have been working on Exercise 3 yolo_non_max_suppression. I have the below error

AssertionError Traceback (most recent call last)
in
25 scores2, boxes2, classes2 = yolo_non_max_suppression(scores, boxes, classes, iou_threshold = 0.15)
26
—> 27 assert np.allclose(scores2.numpy(), [0.855]), f"Wrong value on scores {scores2.numpy()}"
28 assert np.allclose(boxes2.numpy(), [[0.45, 0.2, 1.01, 2.6]]), f"Wrong value on boxes {boxes2.numpy()}"
29 assert np.array_equal(classes2.numpy(), [0]), f"Wrong value on classes {classes2.numpy()}"
AssertionError: Wrong value on scores [0.855 0.828]

One observation is that for the following

Append the resulting boxes into the partial result

Use tf.gather() with ‘selected_indices’ and nms_indices_label

I had switched the order nms_indices_label , selected_indices in the gather function as the re was an error other way around.

2

If this doesn’t help, please click my name and message your notebook as an attachment.