- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello
In my view the to run an network on NCS, we convert it into graph. I am using Python APIs to code my app
Check for device
Open Device
allocategrah
loadtensor
get result
deallocate graph
close device
Can i allocate new graph with new inputs using load tensor and execute it, with out closing & re opening device.
It gave me error to load tensor input?
Any feedback on the above output.
Link Copied
4 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@murthysristi Please see my response @ https://ncsforum.movidius.com/discussion/327/executing-multiple-graphs-on-a-stick and https://ncsforum.movidius.com/discussion/507/mvncallocategraph-fails-after-some-deallocs-allocs/p1.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Tome_at_Intel Thank you for your response
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@murthysristi We do plan to add support for this feature soon so please stay tuned!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Tome_at_Intel It is cool, i will look forward for this feature
![](/skins/images/872293744008A34B36F8ABF94A46CC66/responsive_peak/images/icon_anonymous_message.png)
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page