# \#addons
**URL:** https://discuss.ai.google.dev/tag/addons/263.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)
---
## [Mac M1 Chipset smart\_cond error](https://discuss.ai.google.dev/t/mac-m1-chipset-smart-cond-error/19406)
**Author:** [@Alper\_Bilgil](https://discuss.ai.google.dev/u/Alper_Bilgil)\
**Replies:** 1\
**Last updated:** [May 9, 2024, 7:19am UTC](https://discuss.ai.google.dev/t/mac-m1-chipset-smart-cond-error/19406 "2024-05-09T07:19:03Z")
Hi there, I am using RASA 2.0. I’ve downloaded code and made some modifications de to need. In my new Mac Pro M1 Chipset i couldn’t build via pyproject.toml. Then i made some modifications to pyproject.toml and i install…
---
## [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…
---
## [Next word prediction using tensflow Add ons](https://discuss.ai.google.dev/t/next-word-prediction-using-tensflow-add-ons/25034)
**Author:** [@AATMAJ\_JANARDANAN](https://discuss.ai.google.dev/u/AATMAJ_JANARDANAN)\
**Replies:** 1\
**Last updated:** [October 11, 2023, 12:30pm UTC](https://discuss.ai.google.dev/t/next-word-prediction-using-tensflow-add-ons/25034 "2023-10-11T12:30:46Z")
Hi team , anyone have tried doing next word prediction using the tensorflow addon, i tired but not getting proper output
---
## [SIG Addons Wind Down](https://discuss.ai.google.dev/t/sig-addons-wind-down/27832)
**Author:** [@seanpmorgan](https://discuss.ai.google.dev/u/seanpmorgan)\
**Replies:** 0\
**Last updated:** [February 10, 2023, 1:45am UTC](https://discuss.ai.google.dev/t/sig-addons-wind-down/27832 "2023-02-10T01:45:15Z")
Dear contributors and users of TensorFlow Addons, Over the course of 4 years, 200 contributors have built the TFA repository into a community owned and managed success. I’d like to take a moment to sincerely thank every…
---
## [TFA v0.19 released](https://discuss.ai.google.dev/t/tfa-v0-19-released/27968)
**Author:** [@Bhack](https://discuss.ai.google.dev/u/Bhack)\
**Replies:** 0\
**Last updated:** [December 10, 2022, 12:52pm UTC](https://discuss.ai.google.dev/t/tfa-v0-19-released/27968 "2022-12-10T12:52:15Z")
Hi everyone, TFA 0.19 built against TF2.11 has been released. https://github.com/tensorflow/addons/releases/tag/0.19.0
---
## [Viterbi decoder for top\_k best paths](https://discuss.ai.google.dev/t/viterbi-decoder-for-top-k-best-paths/28767)
**Author:** [@lucas\_alvarez\_lacasa](https://discuss.ai.google.dev/u/lucas_alvarez_lacasa)\
**Replies:** 3\
**Last updated:** [October 8, 2022, 1:46pm UTC](https://discuss.ai.google.dev/t/viterbi-decoder-for-top-k-best-paths/28767 "2022-10-08T13:46:29Z")
Hello team!. I was wondering if there’s a similar function to the viterbi\_decode but instead of returning the best path, it returns the top\_k best paths. I couldn’t find anything on the internet. Let me know. Best.
---
## [TFA 0.17 Released](https://discuss.ai.google.dev/t/tfa-0-17-released/27431)
**Author:** [@seanpmorgan](https://discuss.ai.google.dev/u/seanpmorgan)\
**Replies:** 0\
**Last updated:** [May 21, 2022, 3:56pm UTC](https://discuss.ai.google.dev/t/tfa-0-17-released/27431 "2022-05-21T15:56:46Z")
Hi everyone, TFA 0.17 built against TF2.9 has been released. This is our first wheel that is manylinux2014 compatible instead of manylinux2010:
---
## [TFA BeamSearchDecoder Clarification Request](https://discuss.ai.google.dev/t/tfa-beamsearchdecoder-clarification-request/30690)
**Author:** [@Ethen\_Kaufmann](https://discuss.ai.google.dev/u/Ethen_Kaufmann)\
**Replies:** 2\
**Last updated:** [May 9, 2022, 3:12am UTC](https://discuss.ai.google.dev/t/tfa-beamsearchdecoder-clarification-request/30690 "2022-05-09T03:12:23Z")
Hi, If the question seems to dumb, it is because I am new to TensorFlow. I was implementing a toy endocer-decoder problem using TensorFlow 2’s TFA seq2seq implementation. The API was clearly understandable until I wan…
---
## [TFA 0.16 Released](https://discuss.ai.google.dev/t/tfa-0-16-released/21699)
**Author:** [@Bhack](https://discuss.ai.google.dev/u/Bhack)\
**Replies:** 0\
**Last updated:** [February 15, 2022, 6:58pm UTC](https://discuss.ai.google.dev/t/tfa-0-16-released/21699 "2022-02-15T18:58:22Z")
Hi everyone, TFA 0.16 built against TF2.8, CUDA11.2 and cuDNN 8.1.0 has been released:
---
## [Use of the MaxUnPooling2D](https://discuss.ai.google.dev/t/use-of-the-maxunpooling2d/30587)
**Author:** [@Ami\_na](https://discuss.ai.google.dev/u/Ami_na)\
**Replies:** 2\
**Last updated:** [February 15, 2022, 4:19am UTC](https://discuss.ai.google.dev/t/use-of-the-maxunpooling2d/30587 "2022-02-15T04:19:02Z")
i want use MaxUnPooling2D in an autoencoder like this code input\_img = Input(shape=(nr\_col, nr\_rows, 1)) ec\_conv1 = Conv2D(N\[0\], (3,3), activation=‘relu’, padding=‘same’)(input\_img) ec\_ouput = MaxPooling2D((2, 2), pad…
---
## [How to implement and use a Linear Chain CRF in TensorFlow?](https://discuss.ai.google.dev/t/how-to-implement-and-use-a-linear-chain-crf-in-tensorflow/24247)
**Author:** [@rocketstar31](https://discuss.ai.google.dev/u/rocketstar31)\
**Replies:** 12\
**Last updated:** [January 4, 2022, 11:08pm UTC](https://discuss.ai.google.dev/t/how-to-implement-and-use-a-linear-chain-crf-in-tensorflow/24247 "2022-01-04T23:08:00Z")
Hi, I’m currently working on my first machine learning project - using neural networks to try and syllabify words using the Moby Hyphenator II dataset. I am treating this as a multi-label classification problem in which…
---
## [Does the CRFModelWrapper in the TFA support the serialization for the continuous training?](https://discuss.ai.google.dev/t/does-the-crfmodelwrapper-in-the-tfa-support-the-serialization-for-the-continuous-training/31291)
**Author:** [@dada\_Lai](https://discuss.ai.google.dev/u/dada_Lai)\
**Replies:** 9\
**Last updated:** [December 4, 2021, 9:13pm UTC](https://discuss.ai.google.dev/t/does-the-crfmodelwrapper-in-the-tfa-support-the-serialization-for-the-continuous-training/31291 "2021-12-04T21:13:49Z")
Hi everyone, I am using the CRFModelWrapper method following the tutorial as addons/layers\_crf.ipynb at add\_crf\_tutorial · howl-anderson/addons · GitHub to implement a Bi-LSTM -CRF neural-network for a multi-classes NER…
---
## [TFA 0.14 released](https://discuss.ai.google.dev/t/tfa-0-14-released/24856)
**Author:** [@Bhack](https://discuss.ai.google.dev/u/Bhack)\
**Replies:** 0\
**Last updated:** [August 31, 2021, 9:31pm UTC](https://discuss.ai.google.dev/t/tfa-0-14-released/24856 "2021-08-31T21:31:26Z")
Hi everyone, TFA 0.14 built against TF2.6, CUDA11.2 and cuDNN 8.1.0 has been released:
---
## [An example of Compose?](https://discuss.ai.google.dev/t/an-example-of-compose/31313)
**Author:** [@Sayak\_Paul](https://discuss.ai.google.dev/u/Sayak_Paul)\
**Replies:** 10\
**Last updated:** [June 7, 2021, 12:29pm UTC](https://discuss.ai.google.dev/t/an-example-of-compose/31313 "2021-06-07T12:29:01Z")
@Bhack could you provide a minimal example of tfa.image.compose\_transforms()?