Hi.

Do I need to change the

image_channel_mean

and

anchor_box_config

in faster rcnn spec file based on my dataset?

Hi.

Do I need to change the

image_channel_mean

and

anchor_box_config

in faster rcnn spec file based on my dataset?

Image_channel_mean is the part of preprocessing. It is not needed to change.

For your own dataset, you can modify anchor_box_config to get new anchor sizes if needed.

For example,

case1:

anchor_box_config {

scale: 8.0

scale: 16.0

scale: 32.0

ratio: 1.0

ratio: 0.5

ratio: 2.0

}

The anchor will be

```
array([[[ 8. , 8. ],
[ 5.656854, 11.313708],
[11.313708, 5.656854]],
[[16. , 16. ],
[11.313708, 22.627417],
[22.627417, 11.313708]],
[[32. , 32. ],
[22.627417, 45.254833],
[45.254833, 22.627417]]], dtype=float32)
because
8*sqrt(1)= 8
8*sqrt(0.5)= 5.656854
8*sqrt(2) = 11.313708
16*sqrt(1)= 16
16*sqrt(0.5)= 11.313708
16*sqrt(2) = 22.627417
32*sqrt(1)= 32
32*sqrt(0.5)= 22.627417
32*sqrt(2) = 45.254833
```

case2:

anchor_box_config {

scale: 4.0

scale: 4.6

scale: 5.0

ratio: 1.0

ratio: 0.5

ratio: 2.0

}

It can cover anchor sizes like

4x4,

2.828x5.656

5.656x2.828

4.6x4.6

3.25x6.5

6.5x3.25

5x5

3.535x7.07

7.07x3.535

1 Like

Thank you.

How do I know what scale to use for my dataset?

TLT did not provide a tool to set exact scale/ratio.

You can calculate the resolution of the bboxes in your label files.

1 Like

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.