- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi there,
I'm having difficulty getting equivalent results from the ncs and cpu, and was wondering if anyone else has encountered similar issues?
Steps to reproduce:
- Take the AlexNet example from the ncappzoo: https://github.com/movidius/ncappzoo/tree/ncsdk2/caffe/AlexNet
- Run make all, a deploy.prototxt and bvlc_alexnet.caffemodel weights file will appear
- Take deploy.prototxt and remove everything after the conv1 layer - expected output size is now 96 x 55 x 55
- Generate a new graph using mvNCCompile
- Run the graph on the stick, and store the output of 290,440 floats ( use script similar to this: https://1drv.ms/u/s!AosBHN3IHTLWhoJ7Hk3DnpRZMOo31w )
- Run the model on the cpu, and store the output of 290.440 floats ( use script similar to this: https://1drv.ms/u/s!AosBHN3IHTLWhoJ840l2yBCQlVo-aA )
- Compare results in something like Matlab, Octave, or Python
- Output looks like this: https://1drv.ms/u/s!AosBHN3IHTLWhoJ9GmzKhS7sIxurqw
Environment:
NCSDK v2.05.00.02
Caffe v1.0.0
Ubuntu v18.04 in VirtualBox 5.2.16
Many thanks..
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Jay Have you tried compaing the results from the ncappzoo Alexnet example (https://github.com/movidius/ncappzoo/blob/ncsdk2/caffe/AlexNet/run.py) instead of the example at https://1drv.ms/u/s!AosBHN3IHTLWhoJ7Hk3DnpRZMOo31w? I'm curious to know what the results would be. I wonder if it could be a preprocessing issue since none of the appzoo examples use the transpose preprocessing step seen in the python scripts above img = img.transpose((2,0,1))
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi @Tome_at_Intel,
Thanks for that - it seems to have fixed things! The new histograms are here:
NCS Version:
https://1drv.ms/u/s!AosBHN3IHTLWhoMCk3rqG5v6z2-Crw
PC Version:
https://1drv.ms/u/s!AosBHN3IHTLWhoMBzM8rCJ1h_NztIQ
All the best!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
:)
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page