# \#tfjs **URL:** https://discuss.ai.google.dev/tag/tfjs/31.md [Latest](https://discuss.ai.google.dev/latest.md) · [Categories](https://discuss.ai.google.dev/categories.md) · [Tags](https://discuss.ai.google.dev/tags.md) --- ## [Can you control the behavior of an ML?](https://discuss.ai.google.dev/t/se-puede-dominar-el-comportamiento-de-un-ml/179830)
**Author:** [@Adrian\_Mendez\_millan](https://discuss.ai.google.dev/u/Adrian_Mendez_millan)\ **Replies:** 11\ **Last updated:** [October 1, 2026, 5:19pm UTC](https://discuss.ai.google.dev/t/se-puede-dominar-el-comportamiento-de-un-ml/179830 "2026-10-01T17:19:27Z")
Is it possible to control a language model's behavior? --- ## [AI Bias in tenserflow.js](https://discuss.ai.google.dev/t/ai-bias-in-tenserflow-js/79548)
**Author:** [@Peter\_Muller](https://discuss.ai.google.dev/u/Peter_Muller)\ **Replies:** 1\ **Last updated:** [December 16, 2025, 7:11am UTC](https://discuss.ai.google.dev/t/ai-bias-in-tenserflow-js/79548 "2025-12-16T07:11:49Z")
Hello, I am currently working on a project involving the classification of a judo competition. I have trained a tenerflow.js model to detect Ipon, Wazari and Yuko in live footage. I then implemented the model into a sim… --- ## [MobileNet Always Returns 'Safety Pin' as Classification Result](https://discuss.ai.google.dev/t/mobilenet-always-returns-safety-pin-as-classification-result/66753)
**Author:** [@cauany\_rodrigues](https://discuss.ai.google.dev/u/cauany_rodrigues)\ **Replies:** 1\ **Last updated:** [December 16, 2025, 4:52am UTC](https://discuss.ai.google.dev/t/mobilenet-always-returns-safety-pin-as-classification-result/66753 "2025-12-16T04:52:45Z")
I am developing a React Native application that uses TensorFlow’s MobileNet model for image classification. However, regardless of the image provided, the classification result always returns “safety pin” as the highest … --- ## [Inaccurate Classification in MobileNet – "Safety Pin" as Top Result](https://discuss.ai.google.dev/t/inaccurate-classification-in-mobilenet-safety-pin-as-top-result/66346)
**Author:** [@cauany\_rodrigues](https://discuss.ai.google.dev/u/cauany_rodrigues)\ **Replies:** 1\ **Last updated:** [December 16, 2025, 4:41am UTC](https://discuss.ai.google.dev/t/inaccurate-classification-in-mobilenet-safety-pin-as-top-result/66346 "2025-12-16T04:41:29Z")
Hello, community! I’m developing a React Native application that uses the TensorFlow.js MobileNet model to classify images taken with the camera or selected from the gallery. The app is working well, but I’m facing an i… --- ## [Model small enough for a Chrome extension](https://discuss.ai.google.dev/t/model-small-enough-for-a-chrome-extension/70921)
**Author:** [@Jean\_L](https://discuss.ai.google.dev/u/Jean_L)\ **Replies:** 1\ **Last updated:** [November 25, 2025, 4:56pm UTC](https://discuss.ai.google.dev/t/model-small-enough-for-a-chrome-extension/70921 "2025-11-25T16:56:01Z")
Hi, I am looking for a conversationnel model small enough like mobiletnet used in this project As I understand, mobiletnet is only for image recognition, right? I am trying to build a code syntax checker so I am look… --- ## [Seeking Collaborators for Open-Source Project using Node.js and TensorFlow.js](https://discuss.ai.google.dev/t/seeking-collaborators-for-open-source-project-using-node-js-and-tensorflow-js/34210)
**Author:** [@Math](https://discuss.ai.google.dev/u/Math)\ **Replies:** 0\ **Last updated:** [July 22, 2024, 6:18pm UTC](https://discuss.ai.google.dev/t/seeking-collaborators-for-open-source-project-using-node-js-and-tensorflow-js/34210 "2024-07-22T18:18:43Z")
I hope you’re all doing well! I’m currently working on a exciting open-source project that involve Node.js and TensorFlow.js, and I’m looking to extent the features on my code. Current Implementation: The API I’ve buil… --- ## [Make a payment app](https://discuss.ai.google.dev/t/make-a-payment-app/42551)
**Author:** [@Aju](https://discuss.ai.google.dev/u/Aju)\ **Replies:** 1\ **Last updated:** [July 10, 2025, 7:18am UTC](https://discuss.ai.google.dev/t/make-a-payment-app/42551 "2025-07-10T07:18:52Z")
// … (import statements, variable declarations) // Get payment details from the user input String cardNumber = … String expiryDate = … String cvv = … // Tokenize the payment details (using the chosen gateway’s SDK) … --- ## [What do you think about gemini taking over human workflows](https://discuss.ai.google.dev/t/what-do-you-think-about-gemini-taking-over-human-workflows/46971)
**Author:** [@Mary\_Anderson1](https://discuss.ai.google.dev/u/Mary_Anderson1)\ **Replies:** 1\ **Last updated:** [June 24, 2025, 10:15am UTC](https://discuss.ai.google.dev/t/what-do-you-think-about-gemini-taking-over-human-workflows/46971 "2025-06-24T10:15:15Z")
\*strong text\*\*I believe this Gemini API is going to change the world more productively --- ## [I am testing deleting a topic](https://discuss.ai.google.dev/t/i-am-testing-deleting-a-topic/29516)
**Author:** [@Sandy](https://discuss.ai.google.dev/u/Sandy)\ **Replies:** 1\ **Last updated:** [March 17, 2025, 9:44am UTC](https://discuss.ai.google.dev/t/i-am-testing-deleting-a-topic/29516 "2025-03-17T09:44:08Z")
There is example on Sentiment analysis using Tensorflow JS. \[TensorFlow.js Example: Sentiment Analysis\](https://TensorFlow.js Example: Sentiment Analysis) Alternate option. Convert any text classification model into … --- ## [Learning in loop, init tenserflow js](https://discuss.ai.google.dev/t/learning-in-loop-init-tenserflow-js/28396)
**Author:** [@gotostereo](https://discuss.ai.google.dev/u/gotostereo)\ **Replies:** 1\ **Last updated:** [March 17, 2025, 9:32am UTC](https://discuss.ai.google.dev/t/learning-in-loop-init-tenserflow-js/28396 "2025-03-17T09:32:53Z")
Hi! How possible create init function for tf, i use loop and when call onTrainEnd i need reset all in tf. Should this be done? or does it do it itself? --- ## [Update of @tensorflow-models/face-landmarks-detection from v0.0.3 to 1.0.2](https://discuss.ai.google.dev/t/update-of-tensorflow-models-face-landmarks-detection-from-v0-0-3-to-1-0-2/30952)
**Author:** [@Damian\_LLuch\_Castell](https://discuss.ai.google.dev/u/Damian_LLuch_Castell)\ **Replies:** 1\ **Last updated:** [March 17, 2025, 9:09am UTC](https://discuss.ai.google.dev/t/update-of-tensorflow-models-face-landmarks-detection-from-v0-0-3-to-1-0-2/30952 "2025-03-17T09:09:26Z")
Hi, I have a project running with the face-landmarks-detection-from model in version v0.0.3 and I have already done some of the work to upgrade it to version v1.0.2. The problem I have is how they calculate and use the … --- ## [Face Mesh Masks Not Loading in Firefox Despite Graphics Acceleration Being On](https://discuss.ai.google.dev/t/face-mesh-masks-not-loading-in-firefox-despite-graphics-acceleration-being-on/42168)
**Author:** [@Anuj\_Srivastav](https://discuss.ai.google.dev/u/Anuj_Srivastav)\ **Replies:** 1\ **Last updated:** [March 17, 2025, 7:34am UTC](https://discuss.ai.google.dev/t/face-mesh-masks-not-loading-in-firefox-despite-graphics-acceleration-being-on/42168 "2025-03-17T07:34:37Z")
attaching an error screenshot below --- ## [TensorflowJS Converter to WASM?](https://discuss.ai.google.dev/t/tensorflowjs-converter-to-wasm/30010)
**Author:** [@Jeremy\_Ellis](https://discuss.ai.google.dev/u/Jeremy_Ellis)\ **Replies:** 1\ **Last updated:** [March 16, 2025, 9:37am UTC](https://discuss.ai.google.dev/t/tensorflowjs-converter-to-wasm/30010 "2025-03-16T09:37:37Z")
Is anyone able to export tensorflowJS\_converter to WASM with a very simple example webpage? I will do any major testing. I don’t need it to convert every possible model and layer, just a few of the basics. I realize thi… --- ## [(HELP)Tensorflow React Native Expo for Offline Use](https://discuss.ai.google.dev/t/help-tensorflow-react-native-expo-for-offline-use/50000)
**Author:** [@AxlRich](https://discuss.ai.google.dev/u/AxlRich)\ **Replies:** 1\ **Last updated:** [March 11, 2025, 10:02am UTC](https://discuss.ai.google.dev/t/help-tensorflow-react-native-expo-for-offline-use/50000 "2025-03-11T10:02:45Z")
Is there any way I can integrate tensorflow into my react native expo bare workflow to make it work offline? cause Im having a hard time trying to solve but still haven’t done any progress til now since I saved the model… --- ## [Proofread text using Tensorflow.js](https://discuss.ai.google.dev/t/proofread-text-using-tensorflow-js/67618)
**Author:** [@Pixy\_Dixy](https://discuss.ai.google.dev/u/Pixy_Dixy)\ **Replies:** 0\ **Last updated:** [February 21, 2025, 1:30pm UTC](https://discuss.ai.google.dev/t/proofread-text-using-tensorflow-js/67618 "2025-02-21T13:30:30Z")
Hello I want a Nodejs app that reads and learns a prepared text using Tensorflow.js, and then when a sentence is given to it, it guesses the necessary corrections in the given sentence based on the prepared text and ret… --- ## [React Native Architecture Update](https://discuss.ai.google.dev/t/react-native-architecture-update/67373)
**Author:** [@Sanjaiyan\_Parthipan](https://discuss.ai.google.dev/u/Sanjaiyan_Parthipan)\ **Replies:** 0\ **Last updated:** [February 20, 2025, 3:03pm UTC](https://discuss.ai.google.dev/t/react-native-architecture-update/67373 "2025-02-20T15:03:38Z")
PR Update: I’ve updated the project for the latest React Native architecture. See details in the PR. --- ## [While using the model in frontend(nextjs) i am getting this error when i try to load the model:-\>ValueError: An InputLayer should be passed either a batchInputShape or an inputShape](https://discuss.ai.google.dev/t/while-using-the-model-in-frontend-nextjs-i-am-getting-this-error-when-i-try-to-load-the-model-valueerror-an-inputlayer-should-be-passed-either-a-batchinputshape-or-an-inputshape/65622)
**Author:** [@Aich007](https://discuss.ai.google.dev/u/Aich007)\ **Replies:** 3\ **Last updated:** [February 14, 2025, 8:48am UTC](https://discuss.ai.google.dev/t/while-using-the-model-in-frontend-nextjs-i-am-getting-this-error-when-i-try-to-load-the-model-valueerror-an-inputlayer-should-be-passed-either-a-batchinputshape-or-an-inputshape/65622 "2025-02-14T08:48:49Z")
:small\_blue\_diamond: Title: “ValueError: An InputLayer should be passed either a batchInputShape or an inputShape” - TensorFlow Model Issue :small\_blue\_diamond: Description: I’m working on training a TensorFlow model fo… --- ## [Tfjs-node + webgl backend](https://discuss.ai.google.dev/t/tfjs-node-webgl-backend/17113)
**Author:** [@scott](https://discuss.ai.google.dev/u/scott)\ **Replies:** 1\ **Last updated:** [February 13, 2025, 9:19am UTC](https://discuss.ai.google.dev/t/tfjs-node-webgl-backend/17113 "2025-02-13T09:19:56Z")
Hi all, In my project, I bundle some code as a client-side library which imports the webgl backend (i.e. import @tensorflow/tfjs-backend-webgl;). Separately, I have some unit tests (using Jest) which import the node ba… --- ## [LSTM in tensorflow.js game - what am I doing wrong?](https://discuss.ai.google.dev/t/lstm-in-tensorflow-js-game-what-am-i-doing-wrong/29542)
**Author:** [@Christian\_1](https://discuss.ai.google.dev/u/Christian_1)\ **Replies:** 1\ **Last updated:** [February 13, 2025, 7:01am UTC](https://discuss.ai.google.dev/t/lstm-in-tensorflow-js-game-what-am-i-doing-wrong/29542 "2025-02-13T07:01:28Z")
Hi everyone, I’m very new to neural networks and just trying to figure out the right approach for my project and why my current code is not working as planned. I apologize in advance for my stupid questions. I am tryin… --- ## [@tensorflow-models/body-segmentation & @tensorflow-models/body-segmentation](https://discuss.ai.google.dev/t/tensorflow-models-body-segmentation-tensorflow-models-body-segmentation/23753)
**Author:** [@chaimae\_seghir](https://discuss.ai.google.dev/u/chaimae_seghir)\ **Replies:** 1\ **Last updated:** [February 5, 2025, 5:42am UTC](https://discuss.ai.google.dev/t/tensorflow-models-body-segmentation-tensorflow-models-body-segmentation/23753 "2025-02-05T05:42:56Z")
please I’m trying to follow this article Body Segmentation with MediaPipe and TensorFlow.js — The TensorFlow Blog But i have a problem with body-segmentation installation ! i juste can’t, so in my app i can’t found bod… --- ## [Official #MadeWithTFJS Show & Tell inspiration thread](https://discuss.ai.google.dev/t/official-madewithtfjs-show-tell-inspiration-thread/30761)
**Author:** [@Jason](https://discuss.ai.google.dev/u/Jason)\ **Replies:** 22\ **Last updated:** [January 27, 2025, 6:07pm UTC](https://discuss.ai.google.dev/t/official-madewithtfjs-show-tell-inspiration-thread/30761 "2025-01-27T18:07:42Z")
Once per quarter we meet with several members from the TensorFlow.js community to learn more about what amazing projects they have created. This thread is the one stop place to see the latest interviews to get inspiratio… --- ## [Video classification with MoViNet in web browser?](https://discuss.ai.google.dev/t/video-classification-with-movinet-in-web-browser/16256)
**Author:** [@TsuNa](https://discuss.ai.google.dev/u/TsuNa)\ **Replies:** 2\ **Last updated:** [January 24, 2025, 5:03am UTC](https://discuss.ai.google.dev/t/video-classification-with-movinet-in-web-browser/16256 "2025-01-24T05:03:19Z")
Hey there ! I’m here to get some advice about a video classification problem, but with a constraint : I’ve to do this in a web browser. Here is the context : I’ve to create an app to identify a composed move (with 3 di… --- ## [Tensorflow JS Inference error](https://discuss.ai.google.dev/t/tensorflow-js-inference-error/9432)
**Author:** [@gabbygab1233](https://discuss.ai.google.dev/u/gabbygab1233)\ **Replies:** 9\ **Last updated:** [January 12, 2025, 4:58am UTC](https://discuss.ai.google.dev/t/tensorflow-js-inference-error/9432 "2025-01-12T04:58:14Z")
I’m having a problem deploying my model on the browser. --- ## [Rendering pose detection keypoints over the camera in react native](https://discuss.ai.google.dev/t/rendering-pose-detection-keypoints-over-the-camera-in-react-native/29068)
**Author:** [@harshbhatt7585](https://discuss.ai.google.dev/u/harshbhatt7585)\ **Replies:** 1\ **Last updated:** [December 16, 2024, 12:25pm UTC](https://discuss.ai.google.dev/t/rendering-pose-detection-keypoints-over-the-camera-in-react-native/29068 "2024-12-16T12:25:32Z")
I am working on a project and using TensorflowJs in react native using tfjs-react-native library, I am perfectly able to detect the pose detection model using Movenet, but how can I render these keypoints over the camera… --- ## [Using TensorFlow to handle (respond to) websocket connections](https://discuss.ai.google.dev/t/using-tensorflow-to-handle-respond-to-websocket-connections/24098)
**Author:** [@Arcypojeb](https://discuss.ai.google.dev/u/Arcypojeb)\ **Replies:** 1\ **Last updated:** [December 16, 2024, 9:56am UTC](https://discuss.ai.google.dev/t/using-tensorflow-to-handle-respond-to-websocket-connections/24098 "2024-12-16T09:56:00Z")
Hello! Let me begin by saying that I’m a complete noob when it comes to coding, however thanks to the wonders of AI copilots avaliable in VSC I managed to construct such monstrocity \ **Author:** [@serg1992nk](https://discuss.ai.google.dev/u/serg1992nk)\ **Replies:** 1\ **Last updated:** [December 16, 2024, 7:01am UTC](https://discuss.ai.google.dev/t/chatbot-without-using-an-intent-dictionary-maybe/31529 "2024-12-16T07:01:05Z") Hello! I have seen many examples of creating a chat bot based on classification. There is an array of intents, where inside there is a tag, a question and an answer. And the neural network tries to predict which tag is t… --- ## [Open-Source Pose Estimation Movement Analysis for mobile & web applications](https://discuss.ai.google.dev/t/open-source-pose-estimation-movement-analysis-for-mobile-web-applications/53814)
**Author:** [@Fabrice\_Sepret](https://discuss.ai.google.dev/u/Fabrice_Sepret)\ **Replies:** 0\ **Last updated:** [December 11, 2024, 8:41am UTC](https://discuss.ai.google.dev/t/open-source-pose-estimation-movement-analysis-for-mobile-web-applications/53814 "2024-12-11T08:41:56Z")
Hello TensorFlow Community, I’m reaching out to discuss an exciting potential open-source project in pose estimation and movement analysis. Project Context With PoseTracker API, we’ve developed a streamlined approach b… --- ## [Tensorflow.js image](https://discuss.ai.google.dev/t/tensorflow-js-image/31314)
**Author:** [@hanim\_sofia](https://discuss.ai.google.dev/u/hanim_sofia)\ **Replies:** 1\ **Last updated:** [December 5, 2024, 9:54am UTC](https://discuss.ai.google.dev/t/tensorflow-js-image/31314 "2024-12-05T09:54:24Z")
I have followed the documentation of tensorflow.js in codelab. But I received this error Error: pixels passed to tf.browser.fromPixels() can not be null How to solve it? --- ## [Dynamic optimizer](https://discuss.ai.google.dev/t/dynamic-optimizer/29733)
**Author:** [@gotostereo](https://discuss.ai.google.dev/u/gotostereo)\ **Replies:** 1\ **Last updated:** [December 5, 2024, 9:35am UTC](https://discuss.ai.google.dev/t/dynamic-optimizer/29733 "2024-12-05T09:35:06Z")
Hi! I use tf js, and i have a question example let optimizer = tf.train.adam(0.1, 0.99, 0.999) this.model = tf.sequential(); this.model.add( tf.layers.dense({ inputShape: \[units\], units: units, … --- ## [Face landmark detection has staticImageMode option that seems to do nothing](https://discuss.ai.google.dev/t/face-landmark-detection-has-staticimagemode-option-that-seems-to-do-nothing/27920)
**Author:** [@Ken\_Kahn](https://discuss.ai.google.dev/u/Ken_Kahn)\ **Replies:** 1\ **Last updated:** [December 5, 2024, 9:18am UTC](https://discuss.ai.google.dev/t/face-landmark-detection-has-staticimagemode-option-that-seems-to-do-nothing/27920 "2024-12-05T09:18:10Z")
tfjs-models/face-landmarks-detection/src/tfjs at master · tensorflow/tfjs-models · GitHub states: staticImageMode: Optional. Defaults to false. If set to true, face detection will run on every input image, otherwise if… [Next page](https://discuss.ai.google.dev/tag/tfjs/31.md?match_all_tags=true&page=1&tags%5B%5D=tfjs)