Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Beginner
20 Views

[MTCNN] Variable input size

Jump to solution

Hi,

The MTCNN P-net will change input size several times, but the OpenVINO model didn't accept different input size in early release.

In R3 version, I see some posts said that we should change input shape before load into plugin like this:

net = IENetwork.from_ir(model=path_to_the_xml, weights=path_to_the_bin)
input_layer = next(iter(net.inputs))
n, c, h, w = net.inputs[input_layer]
net.reshape({input_layer: (n, c, h*2, w*2)}]

But if it does this every time, it should spend much time.

Is there another way to to this?

 

Thanks.

David

 

 

 

0 Kudos

Accepted Solutions
Highlighted
Employee
20 Views

Hi,

 One way to solve this is to create multiple networks with different size. AFAIK MTCNN has about 6 different scales, that would mean about 6 networks.

/Yury

View solution in original post

0 Kudos
1 Reply
Highlighted
Employee
21 Views

Hi,

 One way to solve this is to create multiple networks with different size. AFAIK MTCNN has about 6 different scales, that would mean about 6 networks.

/Yury

View solution in original post

0 Kudos