# \#education **URL:** https://discuss.ai.google.dev/tag/education/306.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) --- ## [Which gemini api is most similar to the one the browser for free users?](https://discuss.ai.google.dev/t/which-gemini-api-is-most-similar-to-the-one-the-browser-for-free-users/121248)
**Author:** [@Diego\_E](https://discuss.ai.google.dev/u/Diego_E)\ **Replies:** 0\ **Last updated:** [February 4, 2026, 10:43am UTC](https://discuss.ai.google.dev/t/which-gemini-api-is-most-similar-to-the-one-the-browser-for-free-users/121248 "2026-02-04T10:43:46Z")
Doing research how well LLM find sources. --- ## [Optimizing seq2seq decoding script](https://discuss.ai.google.dev/t/optimizing-seq2seq-decoding-script/28299)
**Author:** [@acraev](https://discuss.ai.google.dev/u/acraev)\ **Replies:** 1\ **Last updated:** [July 25, 2025, 4:21am UTC](https://discuss.ai.google.dev/t/optimizing-seq2seq-decoding-script/28299 "2025-07-25T04:21:37Z")
Hello everyone, I am a beginner in Keras/TensorFlow. I am fitting a seq2seq Transformer model and I made my model based on Chollet’s book “Deep Learning with Python” where he shows seq2seq model on an example of machine… --- ## [A tutorial on logging best practices in TensorFlow?](https://discuss.ai.google.dev/t/a-tutorial-on-logging-best-practices-in-tensorflow/25278)
**Author:** [@Sayak\_Paul](https://discuss.ai.google.dev/u/Sayak_Paul)\ **Replies:** 1\ **Last updated:** [June 13, 2025, 6:45am UTC](https://discuss.ai.google.dev/t/a-tutorial-on-logging-best-practices-in-tensorflow/25278 "2025-06-13T06:45:24Z")
Since logging is important for ML (and any software system in general) I think it would be a good idea to have an introductory tutorial on this topic. This could be an opportunity to also introduce tf.get\_logger() to the… --- ## [AI-Powered Scientific Synthesis Platforms](https://discuss.ai.google.dev/t/ai-powered-scientific-synthesis-platforms/57945)
**Author:** [@Ioneuroscientist](https://discuss.ai.google.dev/u/Ioneuroscientist)\ **Replies:** 0\ **Last updated:** [December 29, 2024, 1:57pm UTC](https://discuss.ai.google.dev/t/ai-powered-scientific-synthesis-platforms/57945 "2024-12-29T13:57:29Z")
Continuing the discussion from Use Case: AI-Powered Scientific Information Synthesis Platform:Here’s a reformatted version of your statement, along with some additional context: Epistemologist | Osteopath | Ioneuroscien… --- ## [Utilizing XLA Optimization with Tensorflow Keras on GPU](https://discuss.ai.google.dev/t/utilizing-xla-optimization-with-tensorflow-keras-on-gpu/31285)
**Author:** [@Lu\_Bin\_Liu](https://discuss.ai.google.dev/u/Lu_Bin_Liu)\ **Replies:** 1\ **Last updated:** [October 25, 2024, 3:56pm UTC](https://discuss.ai.google.dev/t/utilizing-xla-optimization-with-tensorflow-keras-on-gpu/31285 "2024-10-25T15:56:40Z")
According to the documentation, using the XLA optimization on Tensorflow Keras involves adding the following line during model compilation: model.compile(optimizer=“adam”, jit\_compile=True) This works fine on CPU (bo… --- ## [How does MultiWorkerMirroredStrategy works?](https://discuss.ai.google.dev/t/how-does-multiworkermirroredstrategy-works/28056)
**Author:** [@wzz](https://discuss.ai.google.dev/u/wzz)\ **Replies:** 1\ **Last updated:** [September 11, 2024, 9:33am UTC](https://discuss.ai.google.dev/t/how-does-multiworkermirroredstrategy-works/28056 "2024-09-11T09:33:59Z")
We are training to run a distributed training on cluster with just CPUs. After reading the tutorials we choose to use tf.distribute.MultiWorkerMirroredStrategy. But there are something confusing us. It said that I need t… --- ## [Can I use tensorflow and other stuff to create a full informative blog post from start to finish?](https://discuss.ai.google.dev/t/can-i-use-tensorflow-and-other-stuff-to-create-a-full-informative-blog-post-from-start-to-finish/25666)
**Author:** [@Zubayer\_Hossain](https://discuss.ai.google.dev/u/Zubayer_Hossain)\ **Replies:** 1\ **Last updated:** [July 29, 2024, 10:11am UTC](https://discuss.ai.google.dev/t/can-i-use-tensorflow-and-other-stuff-to-create-a-full-informative-blog-post-from-start-to-finish/25666 "2024-07-29T10:11:47Z")
I don’t care how long it takes to train my machine. I just want to know if it is possible to do that. I know people who do this, but I don’t know how they do it because they don’t spill a word about it. If it is possible… --- ## [Predict method with transformer encoder decoder](https://discuss.ai.google.dev/t/predict-method-with-transformer-encoder-decoder/30512)
**Author:** [@acraev](https://discuss.ai.google.dev/u/acraev)\ **Replies:** 1\ **Last updated:** [July 9, 2024, 6:58am UTC](https://discuss.ai.google.dev/t/predict-method-with-transformer-encoder-decoder/30512 "2024-07-09T06:58:24Z")
I have fitted a model using a fairly standard transformer encoder-decoder architecture using keras\_nlp layers. When instantiating the model, I provide input as (\[input, target\], offset\_target). So, target is just a sequ… --- ## [Recognition of educational emotions](https://discuss.ai.google.dev/t/recognition-of-educational-emotions/29248)
**Author:** [@Pviegas](https://discuss.ai.google.dev/u/Pviegas)\ **Replies:** 10\ **Last updated:** [June 11, 2024, 5:17pm UTC](https://discuss.ai.google.dev/t/recognition-of-educational-emotions/29248 "2024-06-11T17:17:23Z")
Hi everyone, I’m new to the forum, I don’t know if I posted in the right place. I am a Ph.D. student in web science, and my thesis is on the recognition of educational emotions. My current project is a serious game, wh… --- ## [Post-training quantization. Where to learn more?](https://discuss.ai.google.dev/t/post-training-quantization-where-to-learn-more/32134)
**Author:** [@aqaaqa](https://discuss.ai.google.dev/u/aqaaqa)\ **Replies:** 3\ **Last updated:** [June 5, 2024, 11:41am UTC](https://discuss.ai.google.dev/t/post-training-quantization-where-to-learn-more/32134 "2024-06-05T11:41:44Z")
Hi I am using post-training quantization to create 8-bit quantized tensorflow models. The documentation is simple to follow and I achieve results that I am happy with. I want to learn more about post-training quantizat… --- ## [What contributor documentation improvements do you suggest?](https://discuss.ai.google.dev/t/what-contributor-documentation-improvements-do-you-suggest/24805)
**Author:** [@thea](https://discuss.ai.google.dev/u/thea)\ **Replies:** 5\ **Last updated:** [May 29, 2024, 5:46am UTC](https://discuss.ai.google.dev/t/what-contributor-documentation-improvements-do-you-suggest/24805 "2024-05-29T05:46:38Z")
The TensorFlow team is doing a pass on the contributor documentation we have on tensorflow/tensorflow, tensorflow/community, and the website. Based on your experience in contributing to TensorFlow, are there any docs th… --- ## [Monitor your ML jobs on mobile phones📱](https://discuss.ai.google.dev/t/monitor-your-ml-jobs-on-mobile-phones/29943)
**Author:** [@rishit\_dagli](https://discuss.ai.google.dev/u/rishit_dagli)\ **Replies:** 1\ **Last updated:** [May 9, 2024, 9:05am UTC](https://discuss.ai.google.dev/t/monitor-your-ml-jobs-on-mobile-phones/29943 "2024-05-09T09:05:01Z")
What if you could monitor your Machine Learning jobs on Google Colab or Kaggle or pretty much anywhere in real-time on your mobile phones📱. You can now monitor your ML jobs even while taking a walk🚶with \<5 lines of code … --- ## [Google Coral-Micro board](https://discuss.ai.google.dev/t/google-coral-micro-board/30581)
**Author:** [@Jeremy\_Ellis](https://discuss.ai.google.dev/u/Jeremy_Ellis)\ **Replies:** 2\ **Last updated:** [March 27, 2024, 9:34pm UTC](https://discuss.ai.google.dev/t/google-coral-micro-board/30581 "2024-03-27T21:34:11Z")
Anyone in this forum have the Google CoralMicro board? It says pre-order but Mouse has several. However it seems to have a few issues especially using the Arduino IDE even with Linux and when using tFlite-micro. Any… --- ## [What's the opinion about keras from google research team?](https://discuss.ai.google.dev/t/whats-the-opinion-about-keras-from-google-research-team/28236)
**Author:** [@Simon\_Alerdic](https://discuss.ai.google.dev/u/Simon_Alerdic)\ **Replies:** 1\ **Last updated:** [March 11, 2024, 11:10am UTC](https://discuss.ai.google.dev/t/whats-the-opinion-about-keras-from-google-research-team/28236 "2024-03-11T11:10:05Z")
One of my co-workers asked this question but I’ve no clue to answer. It is assumed that after tensroflow 2 (keras), the research space might change in terms of API. But gradually, Jax becomes popular and to research sci… --- ## [Is TensorFlow a good ML software for a mechanical engineer for PhD research?](https://discuss.ai.google.dev/t/is-tensorflow-a-good-ml-software-for-a-mechanical-engineer-for-phd-research/29688)
**Author:** [@ankithadam](https://discuss.ai.google.dev/u/ankithadam)\ **Replies:** 1\ **Last updated:** [March 6, 2024, 4:45pm UTC](https://discuss.ai.google.dev/t/is-tensorflow-a-good-ml-software-for-a-mechanical-engineer-for-phd-research/29688 "2024-03-06T16:45:02Z")
I come from India, and I know the learning curve is really high for machine learning. but is TensorFlow a good software where I can invest my time and energy to learn so that I can do my Ph.D. project and contribute some… --- ## [\[Research 🎉\] LaMDA - a family of Transformer-based language models specialized for dialog (by Google Research)](https://discuss.ai.google.dev/t/research-lamda-a-family-of-transformer-based-language-models-specialized-for-dialog-by-google-research/29435)
**Author:** [@8bitmp3](https://discuss.ai.google.dev/u/8bitmp3)\ **Replies:** 2\ **Last updated:** [February 12, 2024, 6:18am UTC](https://discuss.ai.google.dev/t/research-lamda-a-family-of-transformer-based-language-models-specialized-for-dialog-by-google-research/29435 "2024-02-12T06:18:10Z")
arXiv: LaMDA: Language Models for Dialog Applications We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 13… --- ## [Object detection with TensorFlow 2 Object detection API](https://discuss.ai.google.dev/t/object-detection-with-tensorflow-2-object-detection-api/32543)
**Author:** [@MWITIDERRICK](https://discuss.ai.google.dev/u/MWITIDERRICK)\ **Replies:** 6\ **Last updated:** [February 9, 2024, 7:03am UTC](https://discuss.ai.google.dev/t/object-detection-with-tensorflow-2-object-detection-api/32543 "2024-02-09T07:03:38Z")
How to perform object detection with a custom dataset using TensorFlow 2 Object Detection API. You will also learn how to prepare custom datasets for object detection and image segmentation. --- ## [Passing in multiple losses in tape.gradient](https://discuss.ai.google.dev/t/passing-in-multiple-losses-in-tape-gradient/32673)
**Author:** [@Lu\_Bin\_Liu](https://discuss.ai.google.dev/u/Lu_Bin_Liu)\ **Replies:** 1\ **Last updated:** [February 6, 2024, 3:27am UTC](https://discuss.ai.google.dev/t/passing-in-multiple-losses-in-tape-gradient/32673 "2024-02-06T03:27:18Z")
In the code below, there’s a line tape.gradient(\[reg\_loss, cat\_loss\], model.trainable\_variables). For trainable weights that affects both reg\_loss and cat\_loss, are the gradients for those weights just averaged or summe… --- ## [Need help for comparing TensorFlow guide with MATLAB tutorial for time series forecasting](https://discuss.ai.google.dev/t/need-help-for-comparing-tensorflow-guide-with-matlab-tutorial-for-time-series-forecasting/28634)
**Author:** [@Muhammad\_Robith](https://discuss.ai.google.dev/u/Muhammad_Robith)\ **Replies:** 1\ **Last updated:** [January 30, 2024, 10:11am UTC](https://discuss.ai.google.dev/t/need-help-for-comparing-tensorflow-guide-with-matlab-tutorial-for-time-series-forecasting/28634 "2024-01-30T10:11:13Z")
Hello! I have 2 questions regarding TensorFlow guide on time series forecasting It is stated on the guide that the “window” shape of data should be (batch, time, features). Since fit, evaluate and predict methods of t… --- ## [TensorFlow Lite C API - Problem with input and output dimensions](https://discuss.ai.google.dev/t/tensorflow-lite-c-api-problem-with-input-and-output-dimensions/32113)
**Author:** [@Laurick](https://discuss.ai.google.dev/u/Laurick)\ **Replies:** 2\ **Last updated:** [January 28, 2024, 10:46pm UTC](https://discuss.ai.google.dev/t/tensorflow-lite-c-api-problem-with-input-and-output-dimensions/32113 "2024-01-28T22:46:02Z")
Hello, I am working on a neural network built with tensorflow. The format is .tflite. the model input dimensions are \[1,30,1\] / the ouput ones are \[1,30\]. I am aiming to feed a float input\[30\] in the model, and retrie… --- ## [How TensorFlow Works?](https://discuss.ai.google.dev/t/how-tensorflow-works/29445)
**Author:** [@ashutosh1919](https://discuss.ai.google.dev/u/ashutosh1919)\ **Replies:** 1\ **Last updated:** [January 2, 2024, 7:24pm UTC](https://discuss.ai.google.dev/t/how-tensorflow-works/29445 "2024-01-02T19:24:51Z")
Here is my attempt to curate a content which explains how TensorFlow works internally. I have spent good amount of time (2 months) curating content, structuring it, creating visuals and animations for this one. I hope … --- ## [Generating Embeddings from Nested Sequences](https://discuss.ai.google.dev/t/generating-embeddings-from-nested-sequences/31733)
**Author:** [@Bharathi\_A](https://discuss.ai.google.dev/u/Bharathi_A)\ **Replies:** 1\ **Last updated:** [December 29, 2023, 7:07am UTC](https://discuss.ai.google.dev/t/generating-embeddings-from-nested-sequences/31733 "2023-12-29T07:07:24Z")
Data : Lists of ordered sequences, some of which may contain nested sequences.(As in the example below) I have input sequences that contain not just single elements, but also lists. Eg : i1 = \[2, 5, 10, \[1, 7 ,9 , 20\],… --- ## [Question about input\_dim and mask\_zero in embedding layers](https://discuss.ai.google.dev/t/question-about-input-dim-and-mask-zero-in-embedding-layers/32468)
**Author:** [@Lu\_Bin\_Liu](https://discuss.ai.google.dev/u/Lu_Bin_Liu)\ **Replies:** 1\ **Last updated:** [December 29, 2023, 6:58am UTC](https://discuss.ai.google.dev/t/question-about-input-dim-and-mask-zero-in-embedding-layers/32468 "2023-12-29T06:58:55Z")
From the documentation on tf.keras.layers.Embedding: input\_dim: Integer. Size of the vocabulary, i.e. maximum integer index + 1. mask\_zero: Boolean, whether or not the input value 0 is a special “padding” value th… --- ## [A TensorFlow Model Garden contributor report](https://discuss.ai.google.dev/t/a-tensorflow-model-garden-contributor-report/30888)
**Author:** [@Bhack](https://discuss.ai.google.dev/u/Bhack)\ **Replies:** 1\ **Last updated:** [December 6, 2023, 6:56pm UTC](https://discuss.ai.google.dev/t/a-tensorflow-model-garden-contributor-report/30888 "2023-12-06T18:56:15Z")
I hope you can find this detailed report useful: An Experience Report on Machine Learning Reproducibility: Guidance for Practitioners and TensorFlow Model Garden Contributors --- ## [General question from a beginner](https://discuss.ai.google.dev/t/general-question-from-a-beginner/29548)
**Author:** [@Raphael\_Henri](https://discuss.ai.google.dev/u/Raphael_Henri)\ **Replies:** 1\ **Last updated:** [November 29, 2023, 5:08pm UTC](https://discuss.ai.google.dev/t/general-question-from-a-beginner/29548 "2023-11-29T17:08:10Z")
Hi everyone, I am a complete beginner in machine learning and I have a general question. Let’s say I have a 1D function with 300 points and I would like to extract 2 specifics points of this function. So my neural netw… --- ## [Try out ConvNeXt in Keras!](https://discuss.ai.google.dev/t/try-out-convnext-in-keras/28235)
**Author:** [@Sayak\_Paul](https://discuss.ai.google.dev/u/Sayak_Paul)\ **Replies:** 26\ **Last updated:** [November 8, 2023, 4:09am UTC](https://discuss.ai.google.dev/t/try-out-convnext-in-keras/28235 "2023-11-08T04:09:26Z")
Hi folks, I hope you are doing well. I wanted to tell y’all about the new ConvNeXt models \[1\] I have been converting for the past few days. Finally, they are available on TF-Hub \[2\]. The collection contains a total of 3… --- ## [Tutorial on Cyclical LR](https://discuss.ai.google.dev/t/tutorial-on-cyclical-lr/31943)
**Author:** [@Sayak\_Paul](https://discuss.ai.google.dev/u/Sayak_Paul)\ **Replies:** 0\ **Last updated:** [June 17, 2021, 4:02am UTC](https://discuss.ai.google.dev/t/tutorial-on-cyclical-lr/31943 "2021-06-17T04:02:38Z")
It’s been a while TensorFlow Addons released an easy-to-use wrapper for Cyclical Learning Rates. Today, we are pleased to release its accompanying tutorial guide: Usage is straightforward: steps\_per\_epoch = len(x\_tra… --- ## [Object Detection - Tutorial Example using Model Garden](https://discuss.ai.google.dev/t/object-detection-tutorial-example-using-model-garden/30533)
**Author:** [@pradeepkuppala](https://discuss.ai.google.dev/u/pradeepkuppala)\ **Replies:** 20\ **Last updated:** [October 24, 2023, 9:25pm UTC](https://discuss.ai.google.dev/t/object-detection-tutorial-example-using-model-garden/30533 "2023-10-24T21:25:27Z")
Want to know more about how Image Classification works with Model Garden, This tutorial fine-tunes a RetinaNet with ResNet-50 as backbone model from the TensorFlow Model Garden package (tensorflow-models) to detect three… --- ## [Installing cuda gpu 2.7.0 on windows anaconda](https://discuss.ai.google.dev/t/installing-cuda-gpu-2-7-0-on-windows-anaconda/29576)
**Author:** [@Ashok\_Bhowmick](https://discuss.ai.google.dev/u/Ashok_Bhowmick)\ **Replies:** 1\ **Last updated:** [September 4, 2023, 9:20am UTC](https://discuss.ai.google.dev/t/installing-cuda-gpu-2-7-0-on-windows-anaconda/29576 "2023-09-04T09:20:36Z")
Just giving heads up if this video might be of any help in installing the latest version for windows 10 anaconda users, which anaconda is yet to provide! --- ## [Tf.gradients() vs tf.gradientTape.gradient() in graph mode](https://discuss.ai.google.dev/t/tf-gradients-vs-tf-gradienttape-gradient-in-graph-mode/32098)
**Author:** [@Mihir\_Khambete](https://discuss.ai.google.dev/u/Mihir_Khambete)\ **Replies:** 1\ **Last updated:** [September 22, 2023, 5:15am UTC](https://discuss.ai.google.dev/t/tf-gradients-vs-tf-gradienttape-gradient-in-graph-mode/32098 "2023-09-22T05:15:26Z")
Hello, I had a question regarding the behavior of tf.gradients() as opposed tf.gradientTape.gradient() in graph mode. Given a differentiable function y = f(x), where x and y are each single tensorflow tensors, is there… [Next page](https://discuss.ai.google.dev/tag/education/306.md?match_all_tags=true&page=1&tags%5B%5D=education)