Questions tagged [teachable-machine]

Teachable Machine is a web-based tool developed and maintained by Google that makes creating machine learning models fast, easy, and accessible to everyone. Use this tag for questions for a specific problem you face when using Teachable Machine to create your models to recognize images, sounds, and poses without writing any machine learning code.

Teachable Machine is a web-based tool developed and maintained by Google that makes creating machine learning models fast, easy, and accessible to everyone. One can train a computer to recognize images, sounds, and poses without writing any machine learning code. Then that model can be leveraged in other projects, sites or apps.

Please see Techable Machine - Homepage for more details.

24 questions
7
votes
2 answers

No module named 'tensorflow.compat'

I'm trying to use the code from the Teachable Machine website: from keras.models import load_model from PIL import Image, ImageOps import numpy as np # Load the model model = load_model('keras_model.h5') # Create the array of the right shape to…
laviRZ
  • 316
  • 1
  • 3
  • 11
1
vote
0 answers

App crashes while running tflite model on image

I was trying to run a tflite model I created from teachable machine on an image using I picked using image_picker, I'm using (flutter_tflite)[https://pub.dev/packages/flutter_tflite] package. app keeps crashes whenever I try to run model on…
Shanu
  • 311
  • 2
  • 16
1
vote
1 answer

selenium giving me NoSuchElementException when it's clear that it exists

I'm trying to upload pictures in google teachable machine using selenium in python, cuz there's too many for me to do it manually. I keep getting NoSuchElementException when it's clear that it exists. Errors used to happen at …
조승주
  • 13
  • 2
0
votes
1 answer

Teachablemachine model working with 100% accuracy on website, but very low accuracy with python

I am creating a car-interior classifier, and I use teachable machine to generate a keras.h5 model, which I can use with python. Whilst on the teachablemachine website, there is a preview window that uses your webcam to classify images, and I help up…
0
votes
0 answers

How to run pose estimation inference with an IP cam (ESP32-CAM) instead of webcam with Teachable Machine in HTML?

I am trying to replace the default webcam funtion in the teachable machine default pose detection code to detect from the camera feed of an IP camera. I cant find any documentation or similar projects to what i'm trying to achieve //…
0
votes
1 answer

Load Teachable Machine Model in HTML and JavaScript Code

I created a teachable machine audio project and uploaded it and used url in html code that is also provided by teachable machine and when I run in the browser it is working. But now I want to use downloaded model instead of uploaded url: what I…
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

How to add bbox on a teachable machine model (Quail Eggs)?

I have downloaded the Keras model and I can run it on Python. The problem is I have no idea how to put bbox on it. from keras.models import load_model # TensorFlow is required for Keras to work import cv2 # Install opencv-python import numpy as…
0
votes
0 answers

Making an object detection model in OpenCv python with tensorflow classification model (frozen graph)

I am a beginner in computer vision and machine learning. I want to make an object detection program in OpenCv python with a TensorFlow classification model. This model is generated from teachable machine and exported as saved model. It has only the…
0
votes
0 answers

how to predict using html video tag instead of webcam in tensorflow.js

please help, i have rtsp video embbed to html using vlc plugin, the rtsp video setup in html video tag. the question is in teachable machine, the given code is predict the model using webcam, how can i predict it using rtsp in html video tag instead…
phpers
  • 1
  • 2
0
votes
1 answer

Why function model.predict() doesn't free RAM memory?

Function model.predict() doesn't free it's memory. Every literation of loop it takes more and more RAM.Im trying that on Ubuntu 22.04 with Conda env. Keras model is created via teachablemachine from google. Thanks! Here is my code: import keras #…
0
votes
0 answers

Saving random shapes to create picture of what I'm saying

I would like to save the generated symbols so that it creates a picture. I used teachable machine sound to classify the certain symbols as sound. Also it generates almost 140 symbols for example triangles or circles per voice input - how can I…
Jojorts
  • 1
  • 1
0
votes
1 answer

How can I solve React Native Tensorflow error?

This is my App.js: //expo & react import * as React from 'react'; import { Dimensions, StyleSheet, View } from 'react-native'; import { Camera, CameraType } from 'expo-camera'; //tensorflow import * as tf from '@tensorflow/tfjs'; import { …
0
votes
0 answers

Teachable machine 20 or more classes

Im new in Machine learning, It is possoble to create 20 or more classes in teachable machine?I experienced problem when i convert it in quantized model tflite , but when i convert 5 classes there is no error
RVC
  • 19
  • 1
0
votes
0 answers

"blocked by CORS policy" error, Take input locally rather than webcam in teachable machine code

From the teachable machine export, I copied javascript code and it takes its input from the webcam to give produced results. I want to provide an input image from my device but facing an issue as my code is not giving any output. This is my…
1
2