Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Groups
Collapse
Brand Logo

ModalAI Forum

  1. ModalAI Support Forum
  2. Ask your questions right here!
  3. voxl-logger tflite

voxl-logger tflite

Scheduled Pinned Locked Moved Ask your questions right here!
4 Posts 2 Posters 881 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • KnightHawk06K Offline
    KnightHawk06K Offline
    KnightHawk06
    Contributor
    wrote on last edited by
    #1

    I'm trying to log the tflite data from the yolov8n model, I'm looking for the detections and confidence vs time. What's the best way to log this data for inspection?

    I am using this command which is creating data.raw and data.csv files but how do I parse the data.raw file?

    voxl-logger --raw tflite --samples 50
    
    KnightHawk06K 1 Reply Last reply
    0
    • KnightHawk06K KnightHawk06

      I'm trying to log the tflite data from the yolov8n model, I'm looking for the detections and confidence vs time. What's the best way to log this data for inspection?

      I am using this command which is creating data.raw and data.csv files but how do I parse the data.raw file?

      voxl-logger --raw tflite --samples 50
      
      KnightHawk06K Offline
      KnightHawk06K Offline
      KnightHawk06
      Contributor
      wrote on last edited by KnightHawk06
      #2

      @KnightHawk06 This data is not making a lot of sense to me, can voxl-logger not be used to capture tflite data?

      @Alex-Kushleyev are you familiar with how to log and parse tflite data on the voxl2?

      head -n 10 data.csv
      

      i,num_bytes
      0,40
      1,65536
      2,65536
      3,65536
      4,65536
      5,65536
      6,65536
      7,65536
      8,65536

      xxd -l 40 data.raw
      

      00000000: 4c58 4f56 4736 35cc bb05 0000 1528 0100 LXOVG65......(..
      00000010: 0004 0003 0000 2400 000c 0000 1428 7f00 ......$......(..
      00000020: 1501 0a00 1e00 0000 ........

      xxd -s 40 -l 64 data.raw
      

      00000028: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................
      00000038: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................
      00000048: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................
      00000058: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................

      KnightHawk06K 1 Reply Last reply
      0
      • KnightHawk06K KnightHawk06

        @KnightHawk06 This data is not making a lot of sense to me, can voxl-logger not be used to capture tflite data?

        @Alex-Kushleyev are you familiar with how to log and parse tflite data on the voxl2?

        head -n 10 data.csv
        

        i,num_bytes
        0,40
        1,65536
        2,65536
        3,65536
        4,65536
        5,65536
        6,65536
        7,65536
        8,65536

        xxd -l 40 data.raw
        

        00000000: 4c58 4f56 4736 35cc bb05 0000 1528 0100 LXOVG65......(..
        00000010: 0004 0003 0000 2400 000c 0000 1428 7f00 ......$......(..
        00000020: 1501 0a00 1e00 0000 ........

        xxd -s 40 -l 64 data.raw
        

        00000028: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................
        00000038: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................
        00000048: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................
        00000058: b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 b4b4 ................

        KnightHawk06K Offline
        KnightHawk06K Offline
        KnightHawk06
        Contributor
        wrote on last edited by
        #3

        @KnightHawk06

        I am able to save off the images that contain the bounding boxes and classification for each frame but not the binary data that has the bounding box coordinates, classification, and confidence for each frame. How are people ingesting this data into their flight software stack?

        voxl-logger --cam tflite --samples 100 --note "tflite_inference_log"
        
        T 1 Reply Last reply
        0
        • KnightHawk06K KnightHawk06

          @KnightHawk06

          I am able to save off the images that contain the bounding boxes and classification for each frame but not the binary data that has the bounding box coordinates, classification, and confidence for each frame. How are people ingesting this data into their flight software stack?

          voxl-logger --cam tflite --samples 100 --note "tflite_inference_log"
          
          T Offline
          T Offline
          teddy.zaremba
          Contributor
          wrote on last edited by teddy.zaremba
          #4

          Hi @KnightHawk06. If you're looking for all the data stored in the ai_detection_t struct we've done it in the past by opening up a libmodal pipe to the tflite detection path defined like this:

          #define TFLITE_DETECTION_PATH (MODAL_PIPE_DEFAULT_BASE_DIR "tflite_data/")

          Let me know if that suits your needs and if you need help opening the pipe.

          1 Reply Last reply
          1

          Hello! It looks like you're interested in this conversation, but you don't have an account yet.

          Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.

          With your input, this post could be even better 💗

          Register Login
          Reply
          • Reply as topic
          Log in to reply
          • Oldest to Newest
          • Newest to Oldest
          • Most Votes


          ModalAI
          Categories Recent Tags ModalAI.com Docs
          © 2026 ModalAI® · Accelerating autonomy for smaller, smarter, safer drones · Powered by NodeBB
          • Login

          • Login or register to search.
          • First post
            Last post
          0
          • Categories
          • Recent
          • Tags
          • Popular
          • Users
          • Groups