Skip to main content
Stack Overflow for Teams is now Stack Internal: See how we’re powering the human intelligence layer of enterprise AI. Read more >
1,572 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
1 vote
0 answers
67 views

I’m trying to convert my TensorFlow SavedModel into a TensorFlow.js format using tensorflowjs_converter. tensorflowjs_converter --input_format=tf_saved_model --output_format=tfjs_graph_model --...
A A's user avatar
  • 19
0 votes
1 answer
39 views

I made a custom layer in TensorFlow.js that consists of sublayers but not weights of its own. Here is a simplified example import * as tf from "@tensorflow/tfjs"; import { LayerArgs } from &...
rkuang25's user avatar
  • 141
0 votes
0 answers
59 views

Please comment how to enable Metal with tfjs-node on MacOS +Metal isn't ready with tensorflow (c++) on the server side. bun ./verify-backend.js const tf = require('@tensorflow/tfjs-node'); async ...
madeinQuant's user avatar
  • 1,823
1 vote
1 answer
53 views

I'm trying to quantize a tfjs model to float16 from the standard float32. This is how I loaded my .keras model and converted it to tfjs. This part works. keras_input_file_path = '/content/cnn_model....
program1232123's user avatar
  • 119
0 votes
0 answers
54 views

I'm currently trying to load a tensorflow js model in a React app: const modelPromise = tf.loadLayersModel('/assets/models/tfjs_model/model.json') However, whenever I use the model I receive the ...
hac739048's user avatar
  • 13
0 votes
0 answers
44 views

I read the documentation of tensorflow-js and various tutorials and used the "cameraWithTensors" from the tfjs library like shown below: const TensorCamera = cameraWithTensors(Camera); ...
Samir's user avatar
  • 1
2 votes
2 answers
57 views

i was building a simple demo that would load a model that i have converted a JSON and binary using tensorfjs. The model is utilizing the following architecture model = Sequential([ Flatten(...
amm4r's user avatar
  • 36
1 vote
0 answers
27 views

I implemented a definition layer and model using TensorFlowJS, and encountered a problem during training. The code is as follows. Can anyone help solve this problem? Thank you very much I implemented ...
xinghuode's user avatar
  • 11
0 votes
0 answers
23 views

I am following this tutorial creating a Tensorflow.js object detection system. The full code is also available here. The App.js code: // Import dependencies import React, { useRef, useState, useEffect ...
Monty Swanson's user avatar
  • 795
0 votes
0 answers
73 views

I have deployed a deep learning model on node-red. Originally a keras file that was later converted to a model.json format with its .bin shard files. Using node-red-contrib-tf-model i deployed this ...
user30221169's user avatar
  • 1
-1 votes
1 answer
49 views

I have exported my VertexAI model to TFJS as "edge", which results in: dict.txt group1_shard1of2.bin group1_shard2of2.bin model.json Now, I send an image from my client to the Node/Express ...
Phil Lucks's user avatar
  • 4,152
1 vote
1 answer
82 views

I'm building a Variational auto encoder (VAE) with tfjs. For now I'm only exploring with the fashionMNIST dataset and a simple model as follows: input layer (28*28*1) flatten intermediate_1 (dense 50 ...
Moc Cam's user avatar
  • 13
0 votes
0 answers
10 views

Using tensor flow.js for deploy model... Model get [1,63] I can't fix problem "const predictedClass = prediction.argMax(1).dataSync();" async function predictGesture(coordinates) { if (!...
LEbEdEV's user avatar
  • 7
0 votes
0 answers
84 views

I'm running Windows10. For my project I have to use Python 3.10 with tensorflow-directml, torchvision and other deep learning tools. The following is a link to one of the many guides about this topic: ...
Chemicalfox's user avatar
  • 1
1 vote
0 answers
66 views

I'm using YOLOv8 for real-time hand detection in a web app. The model works well in Python, but after converting it to TensorFlow.js, detection struggles when the hand is too close to the webcam—...
Vtos's user avatar
  • 11
-1 votes
1 answer
50 views

I am working on an Angular 15 application where I apply a background blur effect to a video stream using CanvasRenderingContext2D and MediaPipeSelfieSegmentation (from bodySegmentation) for real-time ...
subash shakya's user avatar
  • 1
1 vote
0 answers
74 views

Trying to convert a simple CNN using tfjs. The model gets converted, however it does not get loaded in properly. Error: 'An InputLayer should be passed either a batchInputShape or an inputShape.' tf....
program1232123's user avatar
  • 119
1 vote
0 answers
147 views

pyannote/segmentation-3.0 suggests to use pyannote/speaker-diarization-3.0 since it has better embedding model for diarization. I am trying to use this in client-side JS. It seems like I am supposed ...
Student's user avatar
  • 53
0 votes
0 answers
18 views

Followed this guide to create a tensorflow.js neural network https://medium.com/@GeorgePerry/finding-intent-to-buy-from-instagram-comments-with-tensorflow-js-3f764c132be7 It works prefectly until I ...
ollfa's user avatar
  • 31
2 votes
0 answers
22 views

I am having a problem with the gaussian blur of tensorflow.js. Tried to apply the gaussian blur to a video but the best I can do is get the colors inverted. The 5 by 5 matrix kernel I have seems to ...
reallybigbuger's user avatar
  • 21
1 vote
1 answer
129 views

I'm trying to change the background behind the detected body segment, but I can't get it to work. Even though I'm modifying the background(...) function, it keeps defaulting to white. Can anyone ...
user27884943's user avatar
  • 11
1 vote
0 answers
138 views

heres my code for generating and training the model https://github.com/JaylenLuc/Terrestrial-based-ML-cloud-classification/blob/main/cloud.ipynb I specified the input shape in the VGG16 model yet ...
Riku's user avatar
  • 90
1 vote
1 answer
136 views

I was following the TFJS WebML YT Course from Jason Mayes and following along to the TFJS Converter video, here's my notebook: Google Colab Notebook Basically it is an exact replica from the video and ...
Dhanwanth Parameswar's user avatar
  • 25
0 votes
1 answer
55 views

I'm facing an error when calling a pre-trained keras model in javascript for a simple web app on Heroku. https://digit-predictor-6ba58c0cd85a.herokuapp.com Unhandled Promise Rejection: Error: ...
KrC's user avatar
  • 1
1 vote
0 answers
222 views

I have the following React Native App.js File where I'm trying to print nextImageTensor received, but the flow is not going inside loop(). As a matter of fact loop is not even getting called App.js ...
skaul05's user avatar
  • 2,384
1 vote
1 answer
79 views

Thanks for taking the time to read my problem 👍 System information OS Platform and Distribution : Windows 10 TensorFlow.js installed from (npm or script link): npm TensorFlow.js version (use command ...
Titos Arthur's user avatar
  • 11
2 votes
2 answers
186 views

I have saved a TFJS model to a document in cloud firestore, if I run this code straight from the browser: const jsonObject = JSON.parse(TFModeljson); loadedModel = await tf.loadLayersModel(tf.io....
chrispsv's user avatar
  • 455
1 vote
0 answers
98 views

I want to performance a face detection + face recognition in a React Native App offline, so I need to do my inference directly on mobile. I see that are many ways to do that, such as with Tensorflow....
mentejoao's user avatar
  • 23
0 votes
0 answers
250 views

I want to use my deep learning CNN algorithm in a web application and I converted my tensorflow model, emotion_model.h5 to a tensorflow.js model using this command in the terminal ...
snoopy_doo's user avatar
  • 11
0 votes
0 answers
367 views

I have a keras machine learning model titled "melanoma_binary_classifer.keras", and I am trying to convert it to tf.js layer format, and load it into tensorflow.js. I am doing this by ...
Chris's user avatar
  • 43
1 vote
0 answers
75 views

I am trying to create a multi-head attention using tensorflowjs. When trying to train the model, an error kept popping up that the gradient shape was inconsistent with the input shape. reproducable ...
MrGeniusProgrammer's user avatar
  • 11
0 votes
0 answers
40 views

I am having difficulties in converting a model saved by tfjs-react-native to a Keras or TF_Saved_Model format using tensorflowjs_converter. My intention is to use federated learning to train a global ...
daniellaios's user avatar
  • 1
1 vote
0 answers
125 views

Chrome's Topics API's internal tool chrome://topics-internals/ has a Classifier that can list which categories a domain/app belongs to, as determined by an offline file (which is shipped with Chrome) ...
LWC's user avatar
  • 1,235
0 votes
2 answers
922 views

When I tried to convert a .h5 model by using this command in the terminal tensorflowjs_converter --input_format keras model.h5 ./folder I got an output that says "ValueError: Expected Keras ...
Alex's user avatar
  • 23
0 votes
0 answers
163 views

I want to use part of the Time Series Library, namely TimesNet on Tensorflow.js. How can I do this? This requires knowledge of PyTorch, Python and mathematics. Source code https://github.com/thuml/...
yiv1's user avatar
  • 1
2 votes
2 answers
166 views

I am learning tensorflow.js and this is perhaps the first full program I am trying to write. However I feel something is wrong. My model is not able to predict right Weather and always predicting '...
sribasu's user avatar
  • 660
1 vote
0 answers
57 views

I am trying to convert my .pb file (Frozen model format) to TensorFlow.js graph model format. I followed the instructions in the tfjs_converter documentation. So the command that I am running on my ...
Berk Ali Çam's user avatar
  • 11
0 votes
1 answer
208 views

I have simple react app which has three buttons one to start the camera feed, one to capture an image and displays it and one to detect face(s) in that image and add a box around the face with the ...
cdt123's user avatar
  • 71
3 votes
4 answers
4k views

I saved a CNN model using tfjs. But when I tried to load the model in js I got the following error tfjs Uncaught (in promise) Error: An InputLayer should be passed either a `batchInputShape` or an `...
Selim Bamri's user avatar
  • 33
0 votes
1 answer
118 views

im follwing the transfer learning course of tensorflowjs on youtube. Im trying to make a model recognize some picture i upload. The problem is when i close window or reload, the model is load from ...
ooolakaka's user avatar
  • 1
0 votes
1 answer
703 views

I'm trying to classify maize leaf diseases using a react native cli offline. l used teachable machine to train a simple machine learning model for 4 classes and have downloaded the tensorflow.js ...
Tkay's user avatar
  • 11
0 votes
1 answer
111 views

I want to use the model I trained with tensorflow, but I'm getting errors. Please help me const tf = require("@tensorflow/tfjs"); const path = require("path") const MODEL_PATH = &...
Candar TOZAN's user avatar
  • 1
1 vote
0 answers
290 views

I'm having problems to export a simple tensorflow model to a tensorflowjs model, currently I have read the official documentation about recomendations and found the next: ERROR OUTPUT failed to ...
Layer's user avatar
  • 336
0 votes
1 answer
76 views

On the press of a button, I would like to convert the current video frame from the webcam to an array or tfjs tensor. I am unable to find a way to: Get the array Crop and resize the array to the ...
personion's user avatar
  • 13
0 votes
0 answers
73 views

I have an error when I try to predict with an LSTM model in React with TensorFlow.js. The purpose of the React project is to translate sign language and I use media pipe holistic to detect key points ...
Bastian Castillo's user avatar
  • 3
0 votes
0 answers
155 views

I'm trying to package @tensorflow/tfjs-node in an electron project. Everything works properly when I run electron locally, but when I try to package it using electron-forge I get an error An unhandled ...
Braden Roseborough's user avatar
  • 98
1 vote
1 answer
673 views

I am working on getting a local server set up that can serve pages that will have access to tensorflow.js and the webGPU backend. I have run into an issue where if I serve my files on localhost (127.0....
Occam's user avatar
  • 573
2 votes
0 answers
73 views

How do I train a Tensorflow model using Adam optimizer that decays learning rate during the trining with Tensorflow.JS! (not python) I cannot find that the library provides an exponential decay ...
Oleg K's user avatar
  • 5,328
0 votes
1 answer
22 views

I have a JS app which is internally using the TensorFlow.js to run inference on two models. The first model is a GraphModel that consists of 126 nodes. And the second is a LayersModel that consists of ...
Milan's user avatar
  • 1,010
0 votes
1 answer
82 views

I have a trained classification model in tfjs-node that exports a model.json and weights.bin file. When I execute it from the Terminal it works just fine and returns correct prediction probabilities ...
nxtwrld's user avatar
  • 2,062

1
2 3 4 5
…
32