Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Tsin__Ross
New Contributor I
101 Views

The NCS2 produces totally different results compared to nVidia GeFore GTX 1060 from the beginning

Hi Guys in Intel,

I just wanted to find out the reason NCS2 does not produce same outputs as expected, and made a simple experiment.

I created  a very simple IR model which contains only one layer, like this( I also attach the model)

<?xml version="1.0" ?>
<net batch="1" name="areca" version="4">
  <layers>
    <layer id="0" name="inputs" precision="FP16" type="Input">
        <output>
          <port id = "0">
            <dim>1</dim>
            <dim>3</dim>
            <dim>416</dim>
            <dim>416</dim>
          </port>
        </output>
    </layer>
    <layer id="1" name="layer01.convolution" precision="FP16" type="Convolution">
      <data auto_pad="same_upper" dilations="1,1" group="1" kernel="3,3" output="16" pads_begin="1,1" pads_end="1,1" strides="1,1"/>
      <input>
        <port id="0">
          <dim>1</dim>
          <dim>3</dim>
          <dim>416</dim>
          <dim>416</dim>
        </port>
      </input>
      <output>
        <port id="3">
          <dim>1</dim>
          <dim>16</dim>
          <dim>416</dim>
          <dim>416</dim>
        </port>
      </output>
      <blobs>
        <weights offset="0"  size="864" />
        <biases offset="864"  size="32" />
      </blobs>
    </layer> 
  </layers>
  <edges>
    <edge from-layer="0" from-port="0" to-layer="1" to-port="0"/> 
  </edges>
  <meta_data>
  </meta_data>
</net>

 

and load image data from input.bin (in the attachment),  the NCS produce totally different results compared to that I produce in nVidia GeForce 1060( with datatype FP16), as below:

comparision.jpg

This also leads to a totally different detection result on GPU

outputs.jpg

I also attach the visual studio 2015 project and the source file for your reference.

Please help me to fix this problem, many thanks.

 

0 Kudos
1 Reply
Shubha_R_Intel
Employee
101 Views

Dear Tsin, Ross,

Can you kindly try the OpenVino Python Sample object_detection_demo_yolov3_async on this image ? That sample accepts images for -i . Please let me know what happens.

Thanks,

Shubha

 

Reply