Stack Overflow
Stack Overflow

Questions tagged [tflite]

269 questions
0
votes
0 answers

Passing an array of arrays to a input tensor

I'm working into breaking an image(540x360) to 60x60 matrix referred by cv::Mat imga in my code, then normalizing in cv::Mat imga_normalized and finally passing each 60x60 normalized to a std::vector arrayimganorm, which has 54 elements…
mentejoao
  • 1
  • 1
  • 3
0
votes
0 answers

tf.lite is faster than tflite_runtime.interpreter for tflite quantized model

I have a tflite qunatized model (int8), The model running with import tensorflow as tf interpreter = tf.lite.Interpreter(model_path=model_path, experimental_delegates=[]) is 40x faster than: import…
Jasseur Hadded
  • 55
  • 7
0
votes
0 answers

* What went wrong: Execution failed for task ':app:processDebugMainManifest'. > Manifest merger failed with multiple errors, see logs

FAILURE: Build failed with an exception. What went wrong: Execution failed for task ':app:processDebugMainManifest'. Manifest merger failed with multiple errors, see logs Try: Run with --stacktrace option to get the stack trace. Run with…
mina
  • 1
0
votes
0 answers

Tflite flutter not working, Axis 2 is not in range (-(D+1), D), where D is the number of dimensions of input tensor (shape=[1, 10])

I'm developing a object detection app by using tflite_flutter, tflite_flutter_helper and a pretrained ssdMobilenet model. I followed same steps that are given in the documentation but still the error encountered. keep getting this…
Ninad7N
  • 544
  • 4
  • 13
0
votes
1 answer

Understanding the output shape of mediapipes tflite models for pose detection

I'm trying to use one of mediapipes pretrained tflite models to perform a pose landmark detection in android (java), which offers me information about 33 landmarks of a human body. I know there are different ways for example using ML Kit, but for…
EinePriseCode
  • 1
  • 2
0
votes
0 answers

Tensorflow lite model maker for react native

I am building a mobile app for scanning receipts from images. I collected enough datasets for the app and app is also almost completed. I tried with some tflite models which are free open sourced online but in my case of scanning receipts, it…
Kyle Moore
  • 77
  • 4
0
votes
0 answers

I have some problems running the tflite(MoveNet singlepose lightning model) on the flutter

I am not good at English, so I used a translator and a dictionary. Please understand if there is an awkward sentence, and if you don't understand what I'm saying, please let me know. I git cloned the code from…
AdHoc
  • 1
  • 3
0
votes
0 answers

Unhandled Exception: PlatformException(Failed to run model, Interpreter busy,

why im getting this error, im trying to run a object detection app in flutter while running im getting this error in run time, and the object text also not appear [ERROR:flutter/runtime/dart_vm_initializer.cc(41)] Unhandled Exception:…
20C079 Shakeel Akthar
  • 1
0
votes
0 answers

How to use .tflite and .txt files in android studio for EMG signal classification?

I have .tflite and .txt files for my trained model of EMG signals. How should I proceed for developing an app to android studio? The examples which I getting over the internet are mostly for image classifier app, can anyone suggest me for 2D…
Doli Hazarika
  • 1
  • 1
0
votes
0 answers

TFlite model slow/no inference

I am trying to get an opencv pipeline working on a REV control hub for FTC with tensorflow. I have a trained TFLite model and I am processing it and retrieving the confidences. It works well on an android device as an android app, but it doesn't…
Magic Wizard
  • 1
0
votes
0 answers

My custom tflite image classifier perfoms well in python but when I launch it in Android studio it doesn't work at all

We were doing a course project and faced this issue. The idea is simple, three categories: cats, dogs, and cars, the app should classify the photo in one of these. There are lots of tutorials how to implement an already taught net like ImageNet but…
kolqueqo
  • 1
0
votes
1 answer

How do I to save a stateful TFLite model where shape of state depends on input?

I'm trying to do something fairly simple in tensorflow-lite, but I'm not sure it's possible. I want to define a stateful graph where the shape of the state variable is defined when model is LOADED, not when it's saved. As a simple example - lets say…
Peter
  • 12,274
  • 9
  • 71
  • 86
0
votes
0 answers

TFGPT2LMHeadModel to TFLite changes the input and output shape

The TFGPT2LMHeadModel convertion to TFlite renders unexpected input and output shape as oppoed to the pre trained model gpt2-64.tflite , how can we fix the same ? !wget https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-64.tflite import numpy…
kolibyte
  • 1
  • 2
0
votes
1 answer

Tensorflow.js - merge segmentation mask with original image

I am trying to run this model: https://tfhub.dev/google/lite-model/seefood/segmenter/mobile_food_segmenter_V1/1 and display a segmentation mask merged with the original image. However the result is a completely black image. I expected a greyscale…
Hugh Pearse
  • 699
  • 1
  • 7
  • 18
0
votes
0 answers

Image transformation in tflite with variable input and outputsize

I trained a fully convolutional network to transform an image into another image of the same resolution. i was able to convert it into a .tflite model and load it in my android app. I create an interpreter and can set the inputsize by…
spam junk
  • 71
  • 1
  • 2
  • 9
1 2 3
…
17 18