ModalAI Forum
    • Categories
    • Recent
    • Tags
    • Popular
    • Users
    • Groups
    • Register
    • Login

    Can anyone recommend a Tflite Colab Notebook for VOXL2 Training

    Ask your questions right here!
    4
    53
    4880
    Loading More Posts
    • 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.
    • tomT
      tom admin @sansoy
      last edited by

      @sansoy @Thomas-Patton is the ML expert here and I'll let him comment on that front

      1 Reply Last reply Reply Quote 0
      • S
        sansoy @tom
        last edited by

        @tom Ubuntu 22.04.3 LTS

        tomT 1 Reply Last reply Reply Quote 0
        • tomT
          tom admin @sansoy
          last edited by

          @sansoy Huh, okay, that's what I run as well.

          What groups are your default user in? For example, here is mine:

           ~  groups                                               ok | 10:20:36 AM 
          tom adm dialout cdrom sudo dip plugdev lpadmin lxd sambashare docker
          
          S 1 Reply Last reply Reply Quote 0
          • S
            sansoy @tom
            last edited by

            @tom eve@eve:~$ groups
            eve adm cdrom sudo dip plugdev lpadmin lxd sambashare

            tomT 1 Reply Last reply Reply Quote 0
            • tomT
              tom admin @sansoy
              last edited by

              @sansoy Can you try adding your user to the dialout group and seeing if that fixes the issue?

              sudo usermod -a -G dialout $USER

              S 1 Reply Last reply Reply Quote 0
              • S
                sansoy @tom
                last edited by

                @tom did that and still no inference.
                tflite_1705069939.png

                tomT 1 Reply Last reply Reply Quote 0
                • tomT
                  tom admin @sansoy
                  last edited by

                  @sansoy That was for fixing the fastboot issue, unrelated

                  ? 1 Reply Last reply Reply Quote 0
                  • ?
                    A Former User @tom
                    last edited by

                    @sansoy

                    When I get some time today I'll try to download your .tflite models and see what's going on. The good news is that the server is at least running! It very well may just be an issue with how the tensor is being parsed.

                    Thomas
                    thomas.patton@modalai.com

                    ? 1 Reply Last reply Reply Quote 0
                    • ?
                      A Former User @Guest
                      last edited by

                      @sansoy

                      Hey, they just gave me access to the Google Drive folder. Can you confirm that the edgetpu.tflite in the root directory is the file you want me to try and get working?

                      Thomas

                      S 1 Reply Last reply Reply Quote 0
                      • S
                        sansoy @Guest
                        last edited by

                        @thomas i just checked permissions and you have access to all the files and yes to

                        edgetpu.tflit
                        ssd-mobilenet-v2-fpnlite-640_quant.tflite
                        ssd-mobilenet-v2-fpnlite-640.tflite
                        saved_models/saved_model.pb

                        ? 1 Reply Last reply Reply Quote 0
                        • ?
                          A Former User @sansoy
                          last edited by

                          @sansoy

                          Of these 4 models which is the custom trained YOLO model you mentioned above? I can't even get the edgetpu.tflite model to load so I need a little bit more information on how each of these files was generated.

                          Thomas

                          S 1 Reply Last reply Reply Quote 0
                          • S
                            sansoy @Guest
                            last edited by

                            @thomas here's a yolov5 trained model.
                            https://drive.google.com/file/d/1wRbIXdylgx-EOGDLnuWnsytGd2DcTNeY/view?usp=drive_link

                            I used this instruction set to train a yolov5 model which works well on my mac, rPI4, linux box and nvidia jetson.
                            https://docs.ultralytics.com/yolov5/tutorials/train_custom_data/#23-organize-directories

                            S 1 Reply Last reply Reply Quote 0
                            • S
                              sansoy @sansoy
                              last edited by

                              @thomas here's the colab notebook i used to create the tflites and quantized tflites
                              https://colab.research.google.com/drive/1QdgpSl63OSQdLTnFwOyP8dxLQ7W0HtmW?usp=sharing

                              ? 1 Reply Last reply Reply Quote 0
                              • ?
                                A Former User @sansoy
                                last edited by

                                @sansoy

                                I found the bug in our code that's causing the issue. You can see on this line that a for YOLO models a former employee hardcoded the number of classes to be 80 leading to a segfault when we only have a single class like in your case. Here's what your model looks like on our server with the fix:

                                7b4e7252-e3f7-4204-be81-abacde3b5c4b-image.png

                                What I'm going to do is write a patch for voxl-tflite-server that more intelligently reads the number from the labels file. This will be available in our SDK Nightlies and so you'll be able to use the fix tomorrow morning. If you'd like the fix sooner, what I can do is package the new voxl-tflite-server into a .deb so you can deploy it manually to your VOXL. I can help you out with this process if you're not familiar.

                                Thanks,
                                Thomas Patton
                                thomas.patton@modalai.com

                                ? S 2 Replies Last reply Reply Quote 1
                                • ?
                                  A Former User @Guest
                                  last edited by

                                  @thomas

                                  https://gitlab.com/voxl-public/voxl-sdk/services/voxl-tflite-server/-/merge_requests/22

                                  Here's the merge request with the fix, this will be published both in tonight's nightly and new SDK releases.

                                  Thomas

                                  S 1 Reply Last reply Reply Quote 1
                                  • S
                                    sansoy @Guest
                                    last edited by

                                    @thomas you rock! awesome! thanks for troubleshooting.

                                    1 Reply Last reply Reply Quote 0
                                    • S
                                      sansoy @Guest
                                      last edited by

                                      @thomas thanks thomas. will download tomorrow and test either in evening or next day. Really appreciate your help with this.
                                      Great job! Sabri

                                      ? 1 Reply Last reply Reply Quote 0
                                      • ?
                                        A Former User @sansoy
                                        last edited by

                                        @sansoy

                                        Yeah of course, glad I could be of assistance! Be sure to let me know if you need any more help with this.

                                        Two things I was thinking about on my drive home that you should know - First, when you're on that page I linked above for the software nightlies make sure you sort the files by date descending so that you get the most recent one. I always make the mistake of getting the wrong one. Secondly, when you flash that nightly SDK it will overwrite anything not in the /data/ directory and so you will need to put your model file and labels txt back into /usr/bin/dnn/.

                                        Thomas

                                        S 1 Reply Last reply Reply Quote 0
                                        • S
                                          sansoy @Guest
                                          last edited by

                                          @thomas Morning Thomas, just getting back to this. I couldnt find any SDK that had a 2024 stamp. Was this uploaded somewhere else?
                                          Sabri

                                          ? 1 Reply Last reply Reply Quote 0
                                          • ?
                                            A Former User @sansoy
                                            last edited by

                                            @sansoy

                                            Here's the one from last night:

                                            https://console.cloud.google.com/storage/browser/_details/platform-nightlies/voxl2/voxl2_SDK_nightly_20240117.tar.gz?pageState=("StorageObjectListTable":("s":[("i":"objectListDisplayFields%2FtimeLastModified","s":"1"),("i":"displayName","s":"0")%5D))&organizationId=517175400245&project=modalai-core-services

                                            You just have to make sure when you're on this page that you sort date modified by descending.

                                            Thanks,
                                            Thomas

                                            S 1 Reply Last reply Reply Quote 0
                                            • First post
                                              Last post
                                            Powered by NodeBB | Contributors