Questions tagged [tflite]
269 questions
0
votes
0 answers
Using NnApiDelegate in TFLite 2.11.0 returns same embeddings for all images. It works fine for 2.6.0
In my android app I'm using Facenet model to recognize faces.
I have added NnApiDelegate to the interpreterOptions.
My app has been working with TFLite version 2.6.0. When I upgraded the TFLite version to 2.10.0 or 2.11.0, I see that the model…
Shubham Agarwal
- 95
- 6
0
votes
0 answers
TFLite could not broadcast input array from shape (96,96) into shape (96,96,1)
I have built a tensorflow lite model using 3 sets of 96x96px grayscale jpgs using Google's Teachable Machine, then exported the model in tflite format. When I attempt to run a prediction on a new 96x96px grayscale image I get the error:
ValueError:…
UltrasoundJelly
- 1,845
- 2
- 18
- 32
0
votes
0 answers
Problems with micro mutable resolver
Can someone help with understanding how micromutableops resolver is used in Arduino instead of Allopsresolver?
I am trying it to reduce my sketch size and i obtained the ops in my model using Netron but i cant quite get past The model…
KasuleTrevor
- 1
- 1
0
votes
0 answers
Converting keras to .tflite - unreal classifying results
I’m working on a university project aiming to create an image classifier app on Android. Apart from using Tflite Model Maker, I wanted to try Keras as well - Sequential model, converted to .tflite afterwards. I get strange classification results…
monter
- 1
0
votes
0 answers
trying to install "tflite-model-maker" in jupyter but got conflict with optax and jaxlib error
I did these steps to install tflite-model-maker:
conda create --name myenv
conda activate myenv
pip install tensorflow
pip install tflite-model-maker
keep facing this issue:
ERROR: Cannot install flax because these package versions have conflicting…
Raven
- 1
- 1
0
votes
1 answer
Flutter TFLite model keeps outputting the same result
I am building a CNN classification model using tensorflow and python. The model has an input shape of [1, 50, 7] consisting the first column of timestamp, and sensor values for the rest of the columns. The output value is either 0 or 1 to specify…
Cubelated
- 47
- 8
0
votes
0 answers
tflite-model-maker infinite install
at this page
https://colab.research.google.com/github/khanhlvg/tflite_raspberry_pi/blob/main/object_detection/Train_custom_model_tutorial.ipynb#scrollTo=35BJmtVpAP_n
when i run these commands:
!pip install -q tflite-model-maker
!pip install -q…
0
votes
0 answers
YOLO exported TFLite model not compatible with GPU delegate in Flutter app
I exported YOLOv8 (using ultralytics package) model to TFLite format and I'm trying to use it in my Flutter app. I'm using tflite_flutter package to do so and there is no issue with running it without GPU delegate, but when adding GPU delegates it…
Kamil Zieliński
- 1
- 1
0
votes
0 answers
linking a cmake project against pre-built libtensorflow-lite static lib?
I tried the example cmake project listed here, or something very similar to it.
This seems to imply that in order to build my application, which would link against a libtensorflow-lite.a, the libtensorflow-lite target needs to be built first.
Ok, so…
C M
- 11
- 2
0
votes
0 answers
Tflite object detection model crashes android application
I want to create an object detection application but as with custom object detection model but the tensorflow example object detection app crashes if i use my trained model.
link to the trained model https://github.com/SPEAR22/tfliteodmodel.git
Did…
0
votes
0 answers
Getting this error while trying to run flutter app, tried different things but nothing works so far
So I am trying to run my app on the vscode and I keep getting the following error:
A problem occurred evaluating project ':tflite'.
Could not find method compile() for arguments [org.tensorflow:tensorflow-lite:+] on object of type…
Shahbaz1
- 11
- 1
0
votes
0 answers
RangeError (index): Invalid value: Not in inclusive range 0..10: 11
I'm building an app that integrated a deep learning model, this is the example input and output:
input = [[30, 143, 1, 1, 0, 0, 1]]
output = [[0.2993126 0.63993865 0.06074876]]
this is my code in flutter, and I don't know why it keeps showing…
Wendy
- 1
0
votes
0 answers
AttributeError: module 'keras.api._v2.keras.mixed_precision' has no attribute 'experimental' : TFLite models on Android using TensorFlow and Python
I am facing a persistent issue with using TensorFlow 2.8.4 and Python 3.8.16 to train my TFLite models. So far, I have been able to successfully train my models and obtain my TFLite models. However, when I try to use them on Android, I receive the…
GUEYE
- 1
- 3
0
votes
0 answers
I am converting YOLOV7 .pt to tflite and stumble upon this problem
I'm trying to convert YOLOV7 model to mobile using this command line onnx-tf convert -i yolov7.onnx -o /yolov7/ and I'm getting an error message that I'm struggling to understand. The error message is:
ValueError: Dimensions must be equal, but are…
0
votes
0 answers
How to improve quantized TFLite model test accuracy as it decreases after quantization?
I have trained a custom CNN model for doing image classification upon two classes (Class A and B). I have used an image pre-processing method for edge detection before training. The code is given below:
def img_process(img):
img_gray =…
