Це відео не доступне.
Перепрошуємо.
How to train an object detection model - ML on Raspberry Pi with MediaPipe
Вставка
- Опубліковано 18 сер 2024
- Learn how to create your own object detection model that you can deploy to your Raspberry Pi device. Paul Ruiz, a Senior Developer Advocate, shares a high level approach to training a model so that you can prototype your ideas.
Resources:
Getting started with object detection→ goo.gle/41pWKCv
MediaPipe → goo.gle/3u7sbos
Object detection model customization guide → goo.gle/3stlY5N
Hyperparameters → goo.gle/3QxZR6k
Demo → goo.gle/3SvLKAS
Label Studio→ goo.gle/476VqXg
Watch more ML on Raspberry Pi with MediaPipe → goo.gle/479YC3B
Subscribe to Google for Developers → goo.gle/develo...
#ML #MediaPipe
Resources:
Getting started with object detection→ goo.gle/41pWKCv
MediaPipe → goo.gle/3u7sbos
Object detection model customization guide → goo.gle/3stlY5N
Hyperparameters → goo.gle/3QxZR6k
Demo → goo.gle/3SvLKAS
Label Studio→ goo.gle/476VqXg
Hello Google Dev Team! This new way of training with Mediapipe is excellent, especially for deploying on Raspberry Pi 4. I have trained a custom network to identify industrial vehicles within a factory, and it works ✅. I would like to improve the processing speed because sometimes it is a bit slow. I would like to know if you can do a video explaining how to train a network for a tflite model to use Coral AI on Raspberry pi for improve a speed, and do the corresponding deploy 😁. I thank you very much, congrats! Excellent work.
Thanks for the great video. The tips on how to fiddle with Label Studio's labels.json file output (make sure you have 0 be a background class, etc.) were extremely helpful. (FWIW, my current project is a Pi + a battery-powered water gun. It's meant to detect and deter squirrels trying to eat oranges on our orange tree.)
I think a great addition to the series would be some intro tips on how to adjust hyperparameters to potentially improve accuracy. Please consider putting it on the to-do list!
Good call! I need to learn more about that myself, but it's definitely something I'll look into :)
Hi Paul, thanks for your clear instructions. I was able to create a simple model, deployed to Pi and ran it successfully. I also managed to compile it to a Edgetpu model using Kang’s colab by down grade to tensorflow 2.13.0. It did compiled. Unfortunately, it failed to run on Pi for some runtime errors. Would you please provide instructions on how to compile it with mediapipe support. Thanks!
Hello, your video is really useful, thank you. There is one point I don't understand.
I see that you created a label for the background. Are there background images in your dataset and have you labeled them? Or do we just need to create it as a label and automatically the unlabeled area in any image becomes the background?
Any unlabeled area takes on that label :) It's a generic catch-all
at 12:39, there are some other commands "qat_hparams = object_detector..QATHParams(..." that never got executed in this tutorial? What's that about?
Thanks for this awesome guide too! That was very helpful. I'm working on a calibration fixture, and ideally I would like to import this custom model into OpenCV.
Quantization! Basically reducing the model size, but that gets more into the data science side of things. It's worth running, but I didn't want to make the video even longer by getting into it :)
I have trained a model now. Can I add new photos and categories for training based on this model? If so, will previously trained parts be retrained?
Nope unfortunately once you start that training process it'll remove the images it currently knows and replace them with whatever the entire set is that you're using for the new training.
can i use it after in my react app ?
So I'm not the most familiar with react, but it supports JavaScript libraries yeah? If so, we do have a JavaScript version available :)
i get error No module named 'keras.src.engine' , how to fix this
wow amezing
is there any alternative for label studio? i don't have ubuntu devices
It can run on Windows
I ran this on a Mac, and as someone else mentioned it'll also run on Windows :) I specifically went for that one because it's broadly available.
when importing from mediapipe_model_maker import object_detector I get error ModuleNotFoundError: No module named 'keras.src.engine'
me, too, do you got any solution?
same issue. Did you find a way around?
@@hmdate-2910 modify the `!pip install mediapipe-model-maker` to `!pip install 'keras
yes,it because this model don't support for Windows .you should build your objects in linux.
@@xinglinc is this solve your problem ?