All Questions
471 questions
0
votes
2
answers
59
views
Saving and Loading Images for Tensorflow Lite
Planning on using Tensorflow Lite for image classification.
To test the model, using Fashion-MNIST database to create the model following a Tensorflow basic example from their website. Created and ...
- 361
0
votes
1
answer
39
views
How can I save a TFLite model with a fixed input shape after using interpreter.resize_input_tensor?
I am trying to run inference using the TFLite model of multipose-lightning-tflite-float16 distributed by movenet.
https://www.kaggle.com/models/google/movenet/tfLite
However, this model cannot be used ...
0
votes
0
answers
26
views
Should I run tf-lite models on front-end or back-end on a Flutter app
I am building an app that uses a tf-lite model called MoveNet which recognizes 17 body key points, as well as my own tf-lite model on top of that (lets call it PoseClassifier) to classify poses based ...
0
votes
0
answers
101
views
Why is my 8-bit quantized model slower than my 16-bit model?
I've quantized my neural network tensorflow model to both 8-bit and 16-bit precision to improve performance, expecting the 8-bit version to be faster due to reduced memory and computational ...
0
votes
0
answers
72
views
Issue with "IndexError: _Map_base::at" when convert a tensorflow model to tensorflow lite
I want to test the performance of the quantized tensorflow model .First, I need to quantize the model using tensorflow lite,and got the .tflite model.
When I converter a tensorflow model .h5 to ....
- 11
1
vote
0
answers
80
views
Problem loading TensorFlow Lite model into Android application
Problem loading TensorFlow Lite model into Android application.
I used many repositories as an example of an application with a .tflite format model (specifically for the segmentation task), they all ...
- 11
0
votes
2
answers
80
views
BytesRequired number of elements overflowed when Tensorflow Lite inferencing
I was trying to convert rtmpose body2d onnx file to tensorflow lite format from here https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose#body-2d
I was succesfully converting to saved model ...
- 147
2
votes
0
answers
184
views
Kernel crashes everytime when trying to convert tensorflow model into tflite model
I'm using jupyter notebook in vscode and running a virtual enviroment with python 3.10.12.
The python script is as follow:
import math
import numpy as np
import tensorflow as tf
from tensorflow.keras ...
- 21
2
votes
2
answers
513
views
The TFLite model does not load in android studio
I am building and training a neural network model on tensorflow version 2.17.0-nightly. After that I convert it to a tflite model.
But when I try to load the model I get the following message:
Didn't ...
- 23
-1
votes
1
answer
130
views
Got trouble during on building Mediapipe Example "hand_tracking_cpu"
I'm doing project with Mediapipe, and i successed install and built "hello_wolrd". But, I got trouble during on building "hand_tracking_cpu" like this:
참고: 포함 파일: external/...
0
votes
0
answers
43
views
TypeError: only size-1 arrays can be converted to Python scalars (tflite model)
I try to run an tflite-model but always get this error:
Traceback (most recent call last):
File "label_image.py", line 133, in
print('{:08.6f}: {}'.format(float(results[i]), labels[i]))
...
- 1
0
votes
1
answer
230
views
Changing the name of the input layer of a pre-trained model in TensorFlow Transfer Learning
I am trying to change the input layer's name of a Pre-trained TensorFlow model imported from Keras
I am able to add the output layer name but I keep failing in adding input model name. Is it even ...
- 503
0
votes
1
answer
329
views
How to export tflite model maker model_spec for offline usage?
I'm using a tflite model maker efficientdet_lite3 model for object detection.
The basic set up goes like this:
import numpy as np
import os
from tflite_model_maker.config import ExportFormat, ...
- 1
1
vote
1
answer
486
views
ImportError: cannot import name 'object_detector' from 'mediapipe_model_maker' during initial import
I am trying to follow this tutorial here to train a tensorflow lite object detection model using mediapipe.
I set up the environment as described here using Anaconda.
I am using Pycharm on Windows and ...
- 170
0
votes
1
answer
520
views
Proper way of exporting TF models to TFLite to work with different input sizes
I am exporting my tensorflow model to TFLite. I want to be able to run the TFLite model on mobile device GPU with different input shapes.
For that, I was using the following code:
# tf model class
...
- 31