5.5.8 - June 13, 2022 - Code Project’s SenseAI Version 1 - See V2 here https://ipcamtalk.com/threads/codeproject-ai-version-2-0.68030/

rdxny

Getting the hang of it
Joined
Oct 15, 2022
Messages
139
Reaction score
81
Location
ny
cp.png also, the GPU no longer shows as active in the CPAI .NET server as it did before...
 

rdxny

Getting the hang of it
Joined
Oct 15, 2022
Messages
139
Reaction score
81
Location
ny
Don't you still need the Cuda box checked....at least that was the only way I could make mine work.
I think only if you have a separate GPU. I have only the one in the built-in Intel CPU and the .NET version was supposed to enable that.
The CP dashboard no longer says CPU/GPU but Blue Iris is showing CPU:10% GPU 6% RAM 8.06M... so maybe it is still using the gpu?
 

Tinman

Known around here
Joined
Nov 2, 2015
Messages
1,208
Reaction score
1,472
Location
USA
I think only if you have a separate GPU. I have only the one in the built-in Intel CPU and the .NET version was supposed to enable that.
The CP dashboard no longer says CPU/GPU but Blue Iris is showing CPU:10% GPU 6% RAM 8.06M... so maybe it is still using the gpu?
You would think that, but I don't have a GPU as well, but when I check that box then CPAI will show it is running DirectML.

Screenshot 2023-01-24 192329.png

Screenshot 2023-01-24 192134.png

Also my BI test machine shows the custom models...my main BI machine does not ??

Screenshot 2023-01-24 191306.png
 

Tinman

Known around here
Joined
Nov 2, 2015
Messages
1,208
Reaction score
1,472
Location
USA
That worked. I was able to install License Plate Reader.

Now, if I could just get BI to recognize the modules being used.
Well, I found that if I start BI as a service it will not see the custom models. It does use them correctly , just don't see them. I then tried starting BI NOT using service mode and it all works. I then switched back to running as a service and the issue returns.
 

wittaj

IPCT Contributor
Joined
Apr 28, 2019
Messages
24,433
Reaction score
47,557
Location
USA
Well, I found that if I start BI as a service it will not see the custom models. It does use them correctly , just don't see them. I then tried starting BI NOT using service mode and it all works. I then switched back to running as a service and the issue returns.
Make sure you report that to BI.
 

rdxny

Getting the hang of it
Joined
Oct 15, 2022
Messages
139
Reaction score
81
Location
ny
I think only if you have a separate GPU. I have only the one in the built-in Intel CPU and the .NET version was supposed to enable that.
The CP dashboard no longer says CPU/GPU but Blue Iris is showing CPU:10% GPU 6% RAM 8.06M... so maybe it is still using the gpu?
You would think that, but I don't have a GPU as well, but when I check that box then CPAI will show it is running DirectML.

View attachment 151879

View attachment 151880

Also my BI test machine shows the custom models...my main BI machine does not ??

View attachment 151881
Yes, I am seeing the same thing now. I need CUDA checked to see GPU active in .NET in CPAI (without a separate GPU)
 
Joined
Oct 16, 2018
Messages
1,659
Reaction score
5,466
Location
Florida, USA
Well, I found that if I start BI as a service it will not see the custom models. It does use them correctly , just don't see them. I then tried starting BI NOT using service mode and it all works. I then switched back to running as a service and the issue returns.
I stopped BI as a service, started BI locally and, as you wrote, BI recognized the modules. I then restarted the server, changed BI to run as a service and now BI is “talking” with CPAI. Before I did this, BI was not receiving the response from CPAI.
 

MikeLud1

IPCT Contributor
Joined
Apr 5, 2017
Messages
2,141
Reaction score
4,118
Location
Brooklyn, NY
I started a new thread for all topic CodeProject.AI version 2.0.

 

CrazyAsYou

Getting comfortable
Joined
Mar 28, 2018
Messages
246
Reaction score
262
Location
England, Near Sheffield
I started a new thread for all topic CodeProject.AI version 2.0.

Can a mod lock this thread now that we have a new one for v2 ?
 
Top