# \#faq

**URL:** https://discuss.flower.ai/tag/faq/17.md

[Latest](https://discuss.flower.ai/latest.md) · [Categories](https://discuss.flower.ai/categories.md) · [Tags](https://discuss.flower.ai/tags.md)

---

## [the problem on docker when using flower](https://discuss.flower.ai/t/the-problem-on-docker-when-using-flower/1143)

<div class="topic-metadata">

**Author:** [@nielinhai](https://discuss.flower.ai/u/nielinhai)\
**Replies:** 1\
**Last updated:** [December 2, 2025, 12:07pm UTC](https://discuss.flower.ai/t/the-problem-on-docker-when-using-flower/1143 "2025-12-02T12:07:29Z")

</div>

When I was following the process in the ‘Quickstart with Docker’ section on https://flower.ai/docs/framework/docker/tutorial-quickstart-docker.html, I encountered the following issue when running the command flwr run . l…

---

## [Feedback on Federated Learning Uni-seminar Project](https://discuss.flower.ai/t/feedback-on-federated-learning-uni-seminar-project/282)

<div class="topic-metadata">

**Author:** [@emrecanyerlikaya](https://discuss.flower.ai/u/emrecanyerlikaya)\
**Replies:** 1\
**Last updated:** [July 21, 2025, 11:35am UTC](https://discuss.flower.ai/t/feedback-on-federated-learning-uni-seminar-project/282 "2025-07-21T11:35:44Z")

</div>

Hi Flower community! We are currently working on a project where we forecast hourly energy consumption using “SmartMeter Energy Consumption Data” provided by London Datastore. (SmartMeter Energy Consumption Data in Lond…

---

## [Get defferent models for each participants](https://discuss.flower.ai/t/get-defferent-models-for-each-participants/794)

<div class="topic-metadata">

**Author:** [@shaoyuli](https://discuss.flower.ai/u/shaoyuli)\
**Replies:** 0\
**Last updated:** [March 11, 2025, 8:49am UTC](https://discuss.flower.ai/t/get-defferent-models-for-each-participants/794 "2025-03-11T08:49:07Z")

</div>

Hello guys. I am working on a project where each participant in FL wants to get a unique model after training. I currently have a preliminary idea like this paper’s Architecture Sharing part: only a portion of the model…

---

## [How to implement different aggregation method between layers?](https://discuss.flower.ai/t/how-to-implement-different-aggregation-method-between-layers/612)

<div class="topic-metadata">

**Author:** [@odymit](https://discuss.flower.ai/u/odymit)\
**Replies:** 0\
**Last updated:** [January 20, 2025, 8:09am UTC](https://discuss.flower.ai/t/how-to-implement-different-aggregation-method-between-layers/612 "2025-01-20T08:09:55Z")

</div>

Hi, everyone, I am a sutdent and working on federated learning communication efficiency. Currently, I am preparing to implement a three layer FL training using flower, as shown in the picture. For the edge layer to m…

---

## [Stateful/Persistent clients in simulation context](https://discuss.flower.ai/t/stateful-persistent-clients-in-simulation-context/251)

<div class="topic-metadata">

**Author:** [@micha](https://discuss.flower.ai/u/micha)\
**Replies:** 2\
**Last updated:** [September 26, 2024, 8:35am UTC](https://discuss.flower.ai/t/stateful-persistent-clients-in-simulation-context/251 "2024-09-26T08:35:49Z")

</div>

Hello everybody. I am trying to implement stateful clients together with the flwr.simulation.start\_simulation function. I have seen that in the Release Notes 1.7 it mentions the RecordSet data structure as a way of doin…

---

## [Customized Client and Dataset](https://discuss.flower.ai/t/customized-client-and-dataset/232)

<div class="topic-metadata">

**Author:** [@randomfl2312](https://discuss.flower.ai/u/randomfl2312)\
**Replies:** 2\
**Last updated:** [September 18, 2024, 9:38am UTC](https://discuss.flower.ai/t/customized-client-and-dataset/232 "2024-09-18T09:38:38Z")

</div>

Hello! I am very new to Flower framework. I want to know if we can implement k-anonymity on a few clients and local differential privacy on the others with different values of parameters using Flower. If yes, if someon…

---

## [FL basics question: labelling for local model training in FL](https://discuss.flower.ai/t/fl-basics-question-labelling-for-local-model-training-in-fl/177)

<div class="topic-metadata">

**Author:** [@marcoesposito890](https://discuss.flower.ai/u/marcoesposito890)\
**Replies:** 4\
**Last updated:** [March 22, 2024, 2:16pm UTC](https://discuss.flower.ai/t/fl-basics-question-labelling-for-local-model-training-in-fl/177 "2024-03-22T14:16:53Z")

</div>

Hello, I am just starting now with studying FL and something is very unclear to me regarding labels. From what I understand of FL, the idea is to train models on devices so that only model weights are shared with a cent…

---

## [Where can I find example projects of Flower in action?](https://discuss.flower.ai/t/where-can-i-find-example-projects-of-flower-in-action/77)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [March 5, 2024, 4:10pm UTC](https://discuss.flower.ai/t/where-can-i-find-example-projects-of-flower-in-action/77 "2024-03-05T16:10:08Z")

</div>

A frequently asked question we get is: Where can I find example projects of Flower in action? :mag: :thinking:

---

## [Does Flower support XGBoost training? What’s the bagging strategy based on?](https://discuss.flower.ai/t/does-flower-support-xgboost-training-what-s-the-bagging-strategy-based-on/78)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [March 1, 2024, 2:46pm UTC](https://discuss.flower.ai/t/does-flower-support-xgboost-training-what-s-the-bagging-strategy-based-on/78 "2024-03-01T14:46:26Z")

</div>

Frequently asked questions we get are: Does Flower support XGBoost training? What’s the bagging strategy based on?

---

## [Why don't I see evaluate results in my output?](https://discuss.flower.ai/t/why-dont-i-see-evaluate-results-in-my-output/105)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [March 1, 2024, 11:13am UTC](https://discuss.flower.ai/t/why-dont-i-see-evaluate-results-in-my-output/105 "2024-03-01T11:13:31Z")

</div>

This question was migrated from Github Discussions. Original Question: When following the quick start Tensorflow example, I noticed that in the example terminal it showed the evaluate function being called and printing…

---

## [How do I generate a confusion matrix for each client at the end of each round?](https://discuss.flower.ai/t/how-do-i-generate-a-confusion-matrix-for-each-client-at-the-end-of-each-round/113)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 0\
**Last updated:** [February 29, 2024, 3:59pm UTC](https://discuss.flower.ai/t/how-do-i-generate-a-confusion-matrix-for-each-client-at-the-end-of-each-round/113 "2024-02-29T15:59:16Z")

</div>

This question was migrated from the Slack channel #questions. Original Question: Hello everyone. I am using FLOWER to develop a federated model on tabular datasets. It is a multiclassification problem, and I am using …

---

## [How do I write a custom client selection protocol?](https://discuss.flower.ai/t/how-do-i-write-a-custom-client-selection-protocol/74)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [March 1, 2024, 9:33am UTC](https://discuss.flower.ai/t/how-do-i-write-a-custom-client-selection-protocol/74 "2024-03-01T09:33:04Z")

</div>

A frequently asked question we get is: How do I write a custom client selection protocol? :thinking:

---

## [Does Flower support Federated Learning on iOS devices?](https://discuss.flower.ai/t/does-flower-support-federated-learning-on-ios-devices/115)

<div class="topic-metadata">

**Author:** [@danielnata](https://discuss.flower.ai/u/danielnata)\
**Replies:** 0\
**Last updated:** [March 1, 2024, 9:26am UTC](https://discuss.flower.ai/t/does-flower-support-federated-learning-on-ios-devices/115 "2024-03-01T09:26:33Z")

</div>

Yes it does. We provide an iOS SDK written in Swift to easily use Flower in iOS devices, please take a look our documentation for more information. Additionally we provide a code example for iOS with CoreML, check it out…

---

## [How do I plot the metrics from the strategy](https://discuss.flower.ai/t/how-do-i-plot-the-metrics-from-the-strategy/72)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [March 1, 2024, 9:02am UTC](https://discuss.flower.ai/t/how-do-i-plot-the-metrics-from-the-strategy/72 "2024-03-01T09:02:46Z")

</div>

A frequently asked question we get is: How do I plot the metrics from the strategy (e.g., the loss/accuracy over rounds)? :thinking:

---

## [Does Flower support differential privacy?](https://discuss.flower.ai/t/does-flower-support-differential-privacy/93)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [February 29, 2024, 5:19pm UTC](https://discuss.flower.ai/t/does-flower-support-differential-privacy/93 "2024-02-29T17:19:30Z")

</div>

A frequently asked question we get is: Does Flower support differential privacy? :lock:

---

## [How do I save the global model after training?](https://discuss.flower.ai/t/how-do-i-save-the-global-model-after-training/71)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [February 28, 2024, 10:27pm UTC](https://discuss.flower.ai/t/how-do-i-save-the-global-model-after-training/71 "2024-02-28T22:27:56Z")

</div>

A frequently asked question we get is: How do I save the global model after training? :thinking::question:

---

## [How do I start from a pre-trained model](https://discuss.flower.ai/t/how-do-i-start-from-a-pre-trained-model/73)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [February 28, 2024, 9:49pm UTC](https://discuss.flower.ai/t/how-do-i-start-from-a-pre-trained-model/73 "2024-02-28T21:49:36Z")

</div>

A frequently asked question we get is: How do I start from a pre-trained model? :thinking:

---

## [How do I run Flower using Docker?](https://discuss.flower.ai/t/how-do-i-run-flower-using-docker/79)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 1\
**Last updated:** [February 26, 2024, 10:29am UTC](https://discuss.flower.ai/t/how-do-i-run-flower-using-docker/79 "2024-02-26T10:29:46Z")

</div>

A frequently asked question we get is: How do I run Flower using Docker? :whale:

---

## [Does Flower support Federated Learning on Android devices?](https://discuss.flower.ai/t/does-flower-support-federated-learning-on-android-devices/51)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 0\
**Last updated:** [February 20, 2024, 2:53pm UTC](https://discuss.flower.ai/t/does-flower-support-federated-learning-on-android-devices/51 "2024-02-20T14:53:33Z")

</div>

Yes, it does. We provide an Android SDK to easily use Flower in Android devices, please take a look at our documentation for more information. Additionally, we also provide blog post and following code example for both J…

---

## [Can I combine Federated Learning with Blockchain?](https://discuss.flower.ai/t/can-i-combine-federated-learning-with-blockchain/52)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 0\
**Last updated:** [February 20, 2024, 2:54pm UTC](https://discuss.flower.ai/t/can-i-combine-federated-learning-with-blockchain/52 "2024-02-20T14:54:59Z")

</div>

Yes, of course. A list of available examples using Flower within a blockchain environment is available here: Flower meets Nevermined GitHub Repository Flower meets Nevermined YouTube video Flower meets KOSMoS Flower me…

---

## [How can I run Federated Learning on a Raspberry Pi?](https://discuss.flower.ai/t/how-can-i-run-federated-learning-on-a-raspberry-pi/50)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 0\
**Last updated:** [February 20, 2024, 2:51pm UTC](https://discuss.flower.ai/t/how-can-i-run-federated-learning-on-a-raspberry-pi/50 "2024-02-20T14:51:59Z")

</div>

Find the blog post about federated learning on embedded devices here and the corresponding GitHub code example.

---

## [Can Flower run on Juptyter Notebooks / Google Colab?](https://discuss.flower.ai/t/can-flower-run-on-juptyter-notebooks-google-colab/47)

<div class="topic-metadata">

**Author:** [@flower](https://discuss.flower.ai/u/flower)\
**Replies:** 0\
**Last updated:** [February 20, 2024, 2:38pm UTC](https://discuss.flower.ai/t/can-flower-run-on-juptyter-notebooks-google-colab/47 "2024-02-20T14:38:17Z")

</div>

Yes, it can! Flower even comes with a few under-the-hood optimizations to make it work even better on Colab. Here’s a quickstart example: Flower simulation PyTorch Flower simulation TensorFlow/Keras
