- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
What does that error indicate?
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Sloved: the "num_output" cannot be less than 8 when using kernel size 3.
I wonder why it is set to be perform that? Seems doesn't make sense for many networks with single image as output (num_output = 1 or 3, < 8).
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@incredibleup Thank you for bringing this to our attention. Could you provide a sample of the network or a similar network?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Maybe this issue is related to this one?
https://ncsforum.movidius.com/discussion/184/bug-crash-on-small-networks-num-inputs-8#latest
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Tome_at_Intel I'm seeing trying to run FaceBoxes on the stick. Would it help to provide you with the prototxt and compiled weights?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@dspasojevic Yes that would be great if you can provide those.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@dspasojevic I was able to reproduce your issue. I solved it by including a .conf file with the same name as your network's prototxt file. So if your network prototxt file is named faceboxes.prototxt then you would create an empty file named faceboxes.conf and add in the following lines to your conf file. This conf file chooses a generic spatial convolution function to create a work around because by default the SDK requires the output channels to be >= 8. Make sure that there is an extra line after the last line in the conf file or it may not parse correctly.
Inception3/conv/loc1
generic_spatial
Inception3/conv/conf1
generic_spatial
Inception3/conv/loc2
generic_spatial
Inception3/conv/conf2
generic_spatial
Inception3/conv/loc3
generic_spatial
Inception3/conv/conf3
generic_spatial
conv6/loc
generic_spatial
conv6/conf
generic_spatial
conv7/loc
generic_spatial
conv7/conf
generic_spatial
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Tome_at_Intel I came across the same problem (using the prototxt linked above) and added the configuration file as you suggested. Unfortunately, I am still seeing the same error (_[Error 25] Myriad Error: "3x3 Convolution outputChannels Dimension too small."._) when running mvNCCheck or when loading the graph file into a C++ program. Since mvNCCheck and mvNCCompile print lines like _"Layer conv7/conf/perm/flat use the generic optimisations which is: 0x80000000 0 0x80000000"_ I assume the configuration file is parsed correctly and the generic optimizations are applied. I also tried using generic optimizations on all 3x3 convolutions to make sure I did not miss any, but the result is still the same. I am using the latest version of the SDK.
Just to make sure I am doing this correctly:
- I cloned the FaceBoxes repo (which has the prototxt and caffemodel files)
- I added a file named _'faceboxes_deploy.conf'_ containing the configuration.
- run _mvNCCheck faceboxes_deploy.prototxt -w FaceBoxes_1024x1024.caffemodel_ (or mvNCCompile)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@PixR2 I haven't tried this with NCSDK v2 yet, but I'll give it a shot and let you know if I get the same results. Thanks.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@enjoyXG Can you please send me a link to your Caffe model files? It would save me a lot of time when debugging your network. Thanks.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The model is about 80MB, the download link is as follow
Google drive
BaiduYun
You can try both of the above links.
Thanks.
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page