Search results

  1. T

    GPU's that fit Optiplex 3070 sff?

    FWIW, I completed the build and got cpai cuda gpu working. Make times are now ~80msec average using all the same settings otherwise. So not the 20msec I was hoping for, but still a big improvement. I will play with substream for ai, as well as the medium and smaller models, and see how...
  2. T

    VPN Primer for Noobs

    Running a vpn on a router doesn't have anything to do with other perhaps more important security items, like open ports. Like even if your vpn server and client use a secured connection, you could still be hacked hacked if there is an open port on the router. I presume if you didn't mess with...
  3. T

    VPN Primer for Noobs

    In BI settings/Web server/Advanced..., I think you may need to uncheck "Use secure session keys and login page". As long as your VPN is setup properly, your LAN is otherwise secured, and you aren't port forwarding, it is OK to run this way.
  4. T

    GPU's that fit Optiplex 3070 sff?

    I have used both substream and mainstream for ai, and found only a slight diff using substream. Makes with mainstream average 280-320msec, and 220-260msec with substream.
  5. T

    GPU's that fit Optiplex 3070 sff?

    My make times are like 200-250msec avg which is fine most times. When I have several triggers coming all at once sometimes cpu gets pegged. My thought was taking the ai processing load off of the cpu and cutting make times down from 250msec to 25msec would reduce how often that happens.
  6. T

    GPU's that fit Optiplex 3070 sff?

    Thanks for the quick reply. I was afraid that would be the case, and dell's proprietary garbage psu's are always a problem. My current PC is gen3 and I wanted h265 ha, as well as os support beyond '25 (win11). I am glad I asked about the 1050 before buying one. I swear I read across something...
  7. T

    DeepStack How to alert on Delivery carriers

    Sorry almost missed this one from the previous page. That is pretty weird. I noticed CPAI sometimes can take a few minutes to settle down when certain changes are made. Have you given it some time? Have you tried stopping/restarting AI to see if it changes anything? Maybe after restarting they...
  8. T

    DeepStack How to alert on Delivery carriers

    Weird, those yellow stopwatch icons indicate that AI is tagging those objects as static, or occupied. The way this is supposed to work is AI compares the current trigger image from the preceding trigger image, and if it sees the same objects it calls them "static". If every object in the frame...
  9. T

    GPU's that fit Optiplex 3070 sff?

    I may have jumped the gun on purchasing an sff box. Now I'm looking at gpu's to use for AI, and it seems like the 1050's are a good value, however looking at the shop manual for my yet to arrive optiplex 3070 sff, it appears the 16x slot only fits 1-slot GPU's! Anyone use put a gpu in their sff...
  10. T

    DeepStack How to alert on Delivery carriers

    Not 100% sure, but I think AI test/tune gets greyed out if you are viewing a live feed of a cloned non-recording camera. That last image is way too green, hehe. Use the 3-dot menus to turn off/disable everything except "Object detection yolo". Only yolo objects should be green. The scene, face...
  11. T

    CodeProject AI insane lag

    If that is checked AI won't process any manual triggers. I leave it unchecked so I can use manual triggers for testing.
  12. T

    CPAI confirm times roughly doubled when "Default object detection" is unchecked in BI...

    5.6.7.3, which I believe is the latest release. CPAI is 1.6.8, which is also I think the latest release. This must have been it. I played more and observed memory go from 25% right after a reboot, to 38% after all of the models have been used. After the models were used a few times, confirm...
  13. T

    CPAI confirm times roughly doubled when "Default object detection" is unchecked in BI...

    The past few weeks I have been running BI with "Default object detection" enabled (checkbox in BI ai main settings page). All of my cameras have "objects:0" in their custom model list, along with ipcam-combined, license-plate, and delivery (depending on the camera's role). With these settings...
  14. T

    CodeProject AI insane lag

    Combined I think includes animal, so you can at least eliminate animal. Also I haven't used dark, since combined seems to work for me just as well regardless if it is day or night. So you might also be able to eliminate dark... or maybe setup profiles and scheduling to switch between dark and...
  15. T

    DeepStack How to alert on Delivery carriers

    Ah gotcha, yeah I think that walkway zone A method will work out better for you. I don't know much about how cpai uses gpu, but I understand cuda support is fairly new and proper working configs are widely known at this point. I was playing around and checked cuda in BI AI settings, and nothing...
  16. T

    CodeProject AI insane lag

    As a data point, my intel 3470 with 8gb with otherwise similar settings using ipcam-combined averages 300-500msec, but I'm setup with 3+ images. If I used 15 images I would expect it to take 5x longer. In my case 3+ is plenty... the triggers are setup where whatever object is usually very easy...
  17. T

    Review-Dahua/EmpireTech new doorbell cam Db6l 5mp

    I discovered something that may be of interest to those having frequent disconnects; the db6i appears to disconnect often when using 24VAC/40VA transformers. My existing doorbell transformer was a more common 16VAC/15VA unit. It had just 2 dropouts over a week of frequent use. Those 2 dropouts...
  18. T

    DeepStack How to alert on Delivery carriers

    I just noticed in my first pic I have zone G unchecked in the cam AI settings. That is likely to add to confusion... it works out OK without zone G in my case (because zone A covers all interesting areas for AI for this cam), but it also essentially disables the zone G trick. In your case you do...
  19. T

    DeepStack How to alert on Delivery carriers

    I attached images of everything relevant to ai on my system in hopes it helps. Note the directory where pt files are stored (red square in 2nd image) must match the "Use custom model folder" in BI AI settings (red square in the 3rd image). I also have "Use mainstream" checked (first image)...
  20. T

    DeepStack How to alert on Delivery carriers

    Hmm, so your VM was running smoothly with DS before, but having issues with CPAI? I wish I knew more about the back end on these AI servers to help with that. Hopefully it's just something that needs to be setup for the VM to work efficiently with cpai. Did you run both BI and DS on the same VM...
  21. T

    DeepStack How to alert on Delivery carriers

    In your second uploaded image, zone A appears to be blank? I did mention a lot of details so understandable it may have been overlooked... So again, zone A should still be a strip covering the street where the vehicles are stopping. Since you have zone A blank, you should not expect it to...
  22. T

    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/

    Yes, yes, and yes. Your alert action is likely already configured if it works with BI motion as is. You do need to check ONVIF and Extern for IVS events in both trigger and alerts. No changes should be needed to AI (it doesn't care where the trigger came from). "required objects": we'll assume...
  23. T

    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/

    It's called Dahua Smart PSS: DahuaWiki It supports playback of sdcard files, and can display IVS lines as well. It's actually a really nice alternative to using built in cam webui's for changing settings, and AFAIK plays well with secured/isolated networks.
  24. T

    DeepStack How to alert on Delivery carriers

    You are not alone. BI is a double edge sword for many casual users; it has lots of power and flexibility that comes with a steeper learning curve. I was already up to speed on other BI knowledge, then had to put in about a full days worth of reading/experimenting before I got to where I am...
  25. T

    DeepStack How to alert on Delivery carriers

    The first shot shows my motion setup... red square around the part I think may do what you are after: Below is a shot of that clone camera's AI setup. This is sorta OT from your post but may help with general AI setup. You may note I have zone G unchecked. That is because I don't need the...
  26. T

    DeepStack How to alert on Delivery carriers

    I live on a secondary road, but at times between vehicles, pedestrians, bikes, etc... my road facing cameras can see 10+ hits per minute. To keep up with times when 2 objects pass seconds apart, I have to make sure the triggers and AI reset very quick (less +images and lower msec interval for...
  27. T

    DeepStack How to alert on Delivery carriers

    I have been running delivery.pt with cpai for several days now, and it is mostly working well. From my limited experience, I found a couple of items that I feel could be improved upon. My one real gripe is likely due to user error, and is definitely not related to delivery.pt specifically. In...
  28. T

    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/

    I'm not sure how many others there are, but I actually do have a lot of these stinkhorn mushrooms popping up near where I cut down an apricot tree years ago: Now thanks to this thread, I'll think of Amazon next time I see them. Fortunately that's in my backyard, and the deliveries ai is only...
  29. T

    Review-Dahua/EmpireTech new doorbell cam Db6l 5mp

    Merry Christmas to all! That's interesting... do you have an electric chime? My mechanical chime emits a scary buzzing noise, indicating enough current to create problems before long... when I briefly had the chime kit disconnected. It was a bit tricky getting 2 wires under one screw without...
  30. T

    CPAI potential bugs?

    The last few days I noticed a lack of alerts, and logs indicating the ai server was not responding, and BI kept restarting it. During these times CPU and RAM usage would spike crazy high, like 99%/80% (i5-4650 w/ 8gb ram, using intel beta and substreams). Since that happened, I have thrown a...