Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6392 Discussions

mobilenet-ssd‘s some layers output is nan when use the size of image larger than 300×300

idata
Employee
1,233 Views

when the size of input image is larger than 300×300, my grah’s conv2 and topper layer‘s output is nan,why?

0 Kudos
12 Replies
idata
Employee
931 Views

@batigol If a model expects a specific input size and you do not perform an image resize before sending it for inference, you may receive errors or incorrect results.

 

Just curious if you using the Mobilnet SSD example found in the Ncappzoo (https://github.com/movidius/ncappzoo/tree/master/caffe/SSD_MobileNet). The model included in the Ncappzoo Mobilenet-SSD example expects an image input size of 300 x 300 and performs an image resize before sending it to the NCS for an inference.

 

Below you can find the image resizing code:

 

def preprocess_image(src): # scale the image NETWORK_WIDTH = 300 NETWORK_HEIGHT = 300 img = cv2.resize(src, (NETWORK_WIDTH, NETWORK_HEIGHT)) # adjust values to range between -1.0 and + 1.0 img = img - 127.5 img = img * 0.007843 return img
0 Kudos
idata
Employee
931 Views

thanks for ans, I have change this codes from 300_300 to 512_512, but still receive NaN at conv2 and topper layer out

0 Kudos
idata
Employee
931 Views

I have the same problem! Image with 300x300 is too small for some task, so I try to use 500,448,350, but all the output is nan!

 

@batigol, did you solve the problem?
0 Kudos
idata
Employee
931 Views

@batigol @z_huabao I have tested several images with resolution higher than 300 x 300 (500 x 500, 350 x 350, 450 x 450) and I was unable to reproduce your issue. SSD-MobileNet expects an image of size 300 x 300 and the included example in the NCAppZoo does image resizing so there should not be an issue. If you are using a different program, you may need to use the image resizing code provided in my post above to get the network to work.

0 Kudos
idata
Employee
931 Views

@Tome_at_Intel If resize the image to 300x300 before inference, it will be OK in my program too!

 

You say "SSD-MobileNet expects an image of size 300 x 300 ", but I have retrained a new SSD-MobileNet with 500x500 refer to "https://github.com/chuanqi305/MobileNet-SSD", you can reproduce it quickly(just initialize network and get *.caffemodel)

 

then mvNCCompile my 500x500 SSD-MobileNet to get "graph" ,

 

finally, modify and run the code as follow :

 

def preprocess_image(src): # scale the image img = cv2.resize(src, (500, 500)) # adjust values to range between -1.0 and + 1.0 img = img - 127.5 img = img * 0.007843 return img

 

Every thing seen to be right before I get the nan output !
0 Kudos
idata
Employee
931 Views

The same to @batigol , my grah’s conv2 and topper layer‘s output is nan, check output as follow:

 

zhb@zhb-pc:~/caffe-objects/MobileNet-SSD/example$ mvNCCheck MobileNetSSD_deploy.prototxt -w MobileNetSSD_deploy.caffemodel -s 12 -on conv1 mvNCCheck v02.00, Copyright @ Movidius Ltd 2016 /usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance "Consider reducing your data sizes for best performance\033[0m") USB: Transferring Data... USB: Myriad Execution Finished USB: Myriad Connection Closing. USB: Myriad Connection Closed. Result: (64, 256, 256) 1) 2048968 294.0 2) 2080868 286.5 3) 2089761 277.0 4) 2067065 276.5 5) 2059346 262.0 Expected: (64, 256, 256) 1) 2048968 293.75 2) 2080868 287.0 3) 2067065 276.75 4) 2089761 276.75 5) 2059346 262.0 ------------------------------------------------------------ Obtained values ------------------------------------------------------------ Obtained Min Pixel Accuracy: 0.21276595070958138% (max allowed=2%), Pass Obtained Average Pixel Accuracy: 0.002812110324157402% (max allowed=1%), Pass Obtained Percentage of wrong values: 0.0% (max allowed=0%), Pass Obtained Pixel-wise L2 error: 0.006101535874952356% (max allowed=1%), Pass Obtained Global Sum Difference: 34647.359375

 

------------------------------------------------------------

 

zhb@zhb-pc:~/caffe-objects/MobileNet-SSD/example$ mvNCCheck MobileNetSSD_deploy.prototxt -w MobileNetSSD_deploy.caffemodel -s 12 -on conv2/dw mvNCCheck v02.00, Copyright @ Movidius Ltd 2016 /usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance "Consider reducing your data sizes for best performance\033[0m") USB: Transferring Data... USB: Myriad Execution Finished USB: Myriad Connection Closing. USB: Myriad Connection Closed. Result: (64, 128, 128) 1) 510139 261.0 2) 515273 248.38 3) 509039 244.12 4) 522444 233.38 5) 519339 232.62 Expected: (64, 128, 128) 1) 775922 124.88 2) 777241 120.12 3) 783205 118.88 4) 783859 110.19 5) 781361 108.5 ------------------------------------------------------------ Obtained values ------------------------------------------------------------ Obtained Min Pixel Accuracy: 221.6341257095337% (max allowed=2%), Fail Obtained Average Pixel Accuracy: 7.541597634553909% (max allowed=1%), Fail Obtained Percentage of wrong values: 76.00011825561523% (max allowed=0%), Fail Obtained Pixel-wise L2 error: 13.444180850892486% (max allowed=1%), Fail Obtained Global Sum Difference: 9875038.0

 

------------------------------------------------------------

 

zhb@zhb-pc:~/caffe-objects/MobileNet-SSD/example$ mvNCCheck MobileNetSSD_deploy.prototxt -w MobileNetSSD_deploy.caffemodel -s 12 -on conv2 mvNCCheck v02.00, Copyright @ Movidius Ltd 2016 /usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance "Consider reducing your data sizes for best performance\033[0m") USB: Transferring Data... USB: Myriad Execution Finished USB: Myriad Connection Closing. USB: Myriad Connection Closed. Result: (128, 128, 128) 1) 2097151 nan 2) 881284 nan 3) 881272 nan 4) 881273 nan 5) 881274 nan Expected: (128, 128, 128) 1) 1609215 294.5 2) 1618142 288.5 3) 1611612 280.75 4) 1610329 278.75 5) 1620793 274.5 /usr/local/bin/ncsdk/Controllers/Metrics.py:75: RuntimeWarning: invalid value encountered in greater diff)) / total_values * 100 ------------------------------------------------------------ Obtained values ------------------------------------------------------------ Obtained Min Pixel Accuracy: nan% (max allowed=2%), Fail Obtained Average Pixel Accuracy: nan% (max allowed=1%), Fail Obtained Percentage of wrong values: 39.70165252685547% (max allowed=0%), Fail Obtained Pixel-wise L2 error: nan% (max allowed=1%), Fail Obtained Global Sum Difference: nan ------------------------------------------------------------
0 Kudos
idata
Employee
931 Views

@z_huabao Thanks for explaining that in detail. Can you supply your model so that I can test it? Thanks.

0 Kudos
idata
Employee
931 Views

@Tome_at_Intel yes, here are my prototxt and caffemodel : https://1drv.ms/f/s!AkW0b0sxkXkhgl5Xg7SGPnFhAOvG

0 Kudos
idata
Employee
931 Views

@Tome_at_Intel I have same problem. I simply modified 300x300 to 400x400 then SSD returns nothing.

 

def preprocess_image(src): # scale the image NETWORK_WIDTH = 400 NETWORK_HEIGHT = 400 img = cv2.resize(src, (NETWORK_WIDTH, NETWORK_HEIGHT)) # adjust values to range between -1.0 and + 1.0 img = img - 127.5 img = img * 0.007843 return img

 

Do you mean I have to use only 300x300 for SDD?

 

The caffemodel and prototxt I used are from Ncappzoo.

 

What should I do to change the model input size?

0 Kudos
idata
Employee
931 Views

@hra.kim At the moment, you can only use 300x300 input size with SSD MobileNet. This is an issue that we are aware of and are working to fix at the moment.

0 Kudos
idata
Employee
931 Views

Have you found the way to fix issue with higher resolution input? The latest version of NCSDK v1 still doesn't allow to use images with resolution higher than 300x300 for mobilenet ssd. I tried the model trained on 400x400 and 500x500, the mvNCCheck of movidius model returns nan . When using 300x300 everything is ok. This model was used https://github.com/chuanqi305/MobileNet-SSD

0 Kudos
idata
Employee
931 Views

@Tome_at_Intel Do you finished resolve this issue that we just can use 300x300 image size in ssd to inference in NCS

0 Kudos
Reply