I'm building Flutter application that the user can upload image (clothes, shoes, etc..) and the app will display similar products as the captured one. so i learned a few about how to build a custom model with Tensorflow to implement it with the google ml kit into flutter app, but i don't know how to build the model to show similar, what i do is image classification that it will simply tells what image for which class belongs!
Example for what i need https://developers.google.com/ml-kit/case-studies/adidas but not in live camera.
any help with that?
Related
I'm using google ml kit with the object detection and tracking api, what I need that when the user capture an image my app will display similar products as the captured on, my question is should I train a model with Tensorflow or whatever to do that or I will not need for a custom model to track the similar products ?
I have a Flutter mobile app, using custom Mobilenet object detection model but I want to try using TensorFlow Lite Model Maker.
However I saw we can only use EfficientDet in order to do object detection on the Colab.
So my question is, has anyone ever used EfficientDet_Lite on Flutter ?
Thanks for your help.
I want to make an app which uses Blazepose model (instead of COCO model) which returns 33 body landmark locations. It is created by Mediapipe. Link to download this tflite model is https://github.com/google/mediapipe/blob/master/mediapipe/modules/pose_detection/pose_detection.tflite. I want to use this model on live camera feed in a flutter app. any suggestions will be appreciated.
I have trained a model which takes a pointcloud as input and outputs the bounding boxes on Images on google colab.
Now, I want to build a flutter app where the inputs(pointcloud) will be uploaded and gets the output image as result.
I have explored the use of tflite,but it doesn't support some of the tensorflow operations.
I can think of two solutions.
1)I wish I could connect my flutter app to google colab,run the cells and save the output to my drive from where I could return it to my flutter app. Is this possible? If so,how can I do it?
Using Google Cloud Platform. There are wide range of tools available in GCP and I have no idea which one to use. Can I know the possible and easy to implement ways?
Kindly share your thoughts on How I need to proceed.
What are the basic steps would be to deploy keras model on mobile devices using Flutter? What should I consider here? A quick guideline would be very much appreciated. Thanks.
You have to convert your model to tensorflow lite (provided all the operations in your model are supported in tflite).
The below link gives a complete demo on how an object detection model can be ported to mobile device via flutter. In place of the object detection model , you can use your custom model.
be wary of the input type, and the output type when you convert to tf lite.
https://blog.francium.tech/real-time-object-detection-on-mobile-with-flutter-tensorflow-lite-and-yolo-android-part-a0042c9b62c6