emnist | Classify EMNIST Digits using Convolutional Neural Networks | Machine Learning library

I am trying to do learning rate decay challange of Building Your Own Federated Learning Algorithm tutorial. I have used the following code

At the very end the "Building Your Own Federated Learning Algorithm" tutorial it is stated ,after training our model for 15 rounds, we shall expect a sparse_categorical_accuracy around 0.25, but running the tutorial in colab as is gives a result between 0.09 and 0.11 based on my runs. Yet simply changing the tf and tff versions to 2.3.x and 0.17, respectively, gives a result around 0.25, just like we expected!

To replicate run the said tutorial as is, it should use tf 2.5 and tff 0.19. After that run the same tutorial by simply changing

I want to create a malicious dataset for CIFAR-100 to test a Federated Learning Attack similar to this malicious dataset for EMNIST:

I'm making a CNN and I've got this error that the matrices don't align and i understand the error but i don't know how to fix it. Here is the code:

TensorFlow Datasets was a convent tool to utilize the datasets from the internet. However, I got confused about how to feed it into the Input layer in tensor flow Keras API. The dataset used was the tensorflow dataset's emnist.

Here's what was known:

Point 1: Instead of the store the dataset into the memory, tensorflow database, warp around the tensorflow data module, preprocess the dataset on the hard drive, and use a pipeline(a class instance like object?) to feed the data into the python function. It does so with a load function.

Issue 1 "as_supervised": However, there were two "different" load methods with or without "as_supervised" being on,

I am working on a project with Tensorflow federated. I have managed to use the libraries provided by TensorFlow Federated Learning simulations in order to load, train, and test some datasets.

For example, i load the emnist dataset

I am testing some algorithms in TensorFlow Federated (TFF). In this regard, I would like to test and compare them on the same federated dataset with different "levels" of data heterogeneity, i.e. non-IIDness.

Hence, I would like to know whether there is any way to control and tune the "level" of non-IIDness in a specific federated dataset, in an automatic or semi-automatic fashion, e.g. by means of TFF APIs or just traditional TF API (maybe inside the Dataset utils).

To be more practical: for instance, the EMNIST federated dataset provided by TFF has 3383 clients with each one of them having their handwritten characters. However, these local dataset seems to be quite balanced in terms of number of local examples and in terms of represented classes (all classes are, more or less, represented locally). If I would like to have a federated dataset (e.g., starting by the TFF's EMNIST one) that is:

• Patologically non-IID, for example having clients that hold only one class out of N classes (always referring to a classification task). Is this the purpose of tff.simulation.datasets.build_single_label_dataset documentation here. If so, how should I use it from a federated dataset such as the ones already provided by TFF?;
• Unbalanced in terms of the amount of local examples (e.g., one client has 10 examples, another one has 100 examples);
• Both the possibilities;

how should I proceed inside the TFF framework to prepare a federated dataset with those characteristics?

Should I do all the stuff by hand? Or do some of you have some advices to automate this process?

An additional question: in this paper "Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification", by Hsu et al., they exploit the Dirichlet distribution to synthesize a population of non-identical clients, and they use a concentration parameter to control the identicalness among clients. This seems an wasy-to-tune way to produce datasets with different levels of heterogeneity. Any advice about how to implement this strategy (or a similar one) inside the TFF framework, or just in TensorFlow (Python) considering a simple dataset such as the EMNIST, would be very useful too.

Thank you a lot.

I just downloaded the TensorFlow repository from github (https://github.com/tensorflow/tensorflow (v.2.3.1)). I included it in my C++ project. After I make my Makefile I got the error:

The problem is the change of the dataset from one type to another during different points of the execution stack. For example, if I add a new dataset class with more member properties of interest (which inherits from one of the classes in ops.data.dataset_ops like UnaryDataset), the result is at later execution point (client_update function), the dataset is converted to _VaraintDataset Type and hence any added attributes are lost. So the question is how to retain the member attributes of the newly defined dataset class over the course of execution. Below is the emnist example where the type changes from ParallelMapDataset to _VariantDataset.

In the function client_dataset of training_utils.py line 194, I modified it to show the type of the dataset as follows