306 questions
- Bountied 0
- Unanswered
- Frequent
- Score
- Trending
- Week
- Month
- Unanswered (my tags)
-4
votes
0
answers
70
views
Converting TensorFlow.js mobilenet_v2_mid (nsfwjs) model to TFLite fails using tfjs-graph-converter [closed]
I'm trying to convert the TensorFlow.js mobilenet_v2_mid model used by nsfwjs to TensorFlow Lite.
Model source:
https://github.com/infinitered/nsfwjs/tree/master/models/mobilenet_v2_mid
What I’ve ...
0
votes
0
answers
60
views
Error when using Tflite Micro vs CMSIS-NN
I am designing a TfLite Micro project using CMSIS NN on PlatformIO.
Configuration in platformio.ini:
[env:portenta_h7_m7]
platform = ststm32
board = portenta_h7_m7
framework = arduino
...
0
votes
0
answers
63
views
AttributeError: module 'tensorflow' has no attribute 'saved_model' when importing gemma3 from ai_edge_torch in Google Colab
I'm trying to use Google's ai-edge-torch library to work with the Gemma 3 model in a Google Colab environment. However, I encounter the following error during import:
import torch
from ai_edge_torch....
0
votes
2
answers
187
views
Why does TFLite INT8 quantization decompose BatchMatMul (from Einsum) into many FullyConnected layers?
I’m debugging a model conversion using onnx2tf and post-training quantization issue involving Einsum, BatchMatMul, and FullyConnected layers across different model formats.
Pipeline:
ONNX → TF ...
-1
votes
0
answers
126
views
XNNPACK on raspberry pi5 [closed]
How can I enable XNNPACK on a Raspberry Pi 5 for an INT8 TensorFlow Lite model?
I have a quantized INT8 TensorFlow Lite model that I want to run efficiently on my Raspberry Pi 5.
I’ve read that ...
0
votes
0
answers
54
views
Run Custom Tflite Model in Flutter | Didn't find op for builtin opcode 'CAST' version '5'
import 'dart:developer';
import 'package:plant_decease/core/constants/app_strings.dart';
import 'package:tflite_flutter/tflite_flutter.dart';
class ModelHelper {
Interpreter? _interpreter;
List&...
2
votes
1
answer
212
views
Convert custom YOLOX model (.pth) to tflite model and quantize model
I have trained YOLOX using this repo on a custom dataset with 8 classes. The final output is a .pth file which I need to convert to a quantized .tflite format but I am completely stuck.
What I tried ...
1
vote
1
answer
131
views
Package libffi-dev has no installation candidate on Raspberry pi-os bookworm 12
Some context, I am using a raspberry pi 5 running pi-os bookworm 12. I have a coral ai usb accelerator, and I am trying to run a tflite model on it. Due to pycoral only supporting versions 3.6 to 3.9, ...
0
votes
0
answers
18
views
Inverting back resized and Grayscaled TensorBuffer
I have a bg removal model that takes in 512x512 RGB image and outputs a 512x512 Grayscale.
How can i resize it back to original Widths and Heights, and invert this creepy Grayscale back to RGB?
...
0
votes
0
answers
143
views
How to load tflite files in a bare ios react native project during dev and production
I'm running bare react 0.75 (not expo) and am trying to load in my tflite files using react-native-fast-tflite but it doesn't seem to be working. I tried adding the files to my asset folder as ...
0
votes
1
answer
300
views
INT8 quantization of tflite model from ONNX
I have my ONNX model file and I want to convert it into tflite model with INT8 quantization. Using onnx2tf library I was able to convert the model into tflite float32 and float16.
onnx2tf -i model....
0
votes
1
answer
69
views
Flutter TFLite Model Predictions Wrong Despite Matching Python Preprocessing (Works in Python)
I'm struggling with a Flutter + TFLite integration.
I have a trained TFLite model (EMNIST-like for handwritten letters), and it works perfectly when I test it in Python — but in Flutter, the ...
1
vote
0
answers
134
views
Why is a dimension-adding problem occuring during the conversion from my onnx to tflite model?
I am kinda new to model training and machine learning in general, so sorry in advance if my question mind seem weird.
Last week I managed to train a model with PyTorch and got an .pth file.
To use ...
1
vote
0
answers
96
views
how to convert a QAT quantization aware trained tensorflow graph into tflite model?
I have am quantizing a neural network using QAT and I want to convert it into tflite.
Quantization nodes get added to the skeleton graph and we get a new graph.
I am able to load the trained QAT ...
0
votes
0
answers
121
views
tflite-runtime ValueError: Didn't find op for builtin opcode 'FULLY_CONNECTED' version '12'. An older version of this builtin might be supported
I have trained and quantised my models on tensorflow==2.19.0 instead of a previous version and now am facing troubles in using the quantised models for inference on my Raspberry Pi (Raspbian GNU/Linux ...