NeuralNetwork | Simple Back Propagation Neural Network

I need some help for a project I am working on for a data science course. In this project I classy the digits of the MNIST datasets in three ways:

1. using the dissimilarity matrices induced by the distances 1,2 and infinity
2. using a BallTree
3. using a neural network.

The first two parts are done, but I getting an error for the neural network code that I can't solve. This is the code.

I am trying to process the data obtained from YOLO v5, which is an array of 4 values (posX, posY, SizX, Sizy) per object detected. Now, I know several detections are related, and I want a neural network to find this relation. For every array input, it should return as output a 2x4 matrix, or, flattened, an array of size 8. I am training 4017 samples using Keras Sequential model:

I recently coded a neural network based on this online book and Sebastian Lague's brief series on neural networks on youtube. I coded it as faithfully to the original as possible but it didn't end up working. I am trying to solve a simple XOR problem with it but it always seems to give me random but similar values. I even tried copying and pasting the author's code, without changing anything, but it still didn't work.

I am trying to implement the code from a Pytorch beginner's tutorial. But I have written the code for loading the saved model in another Python file. The FashionClassify file contains the code exactly as its in the tutorial.

Below is the code:

While training a NeuralNetwork model, I am getting the below error:

I built a basic chatbot using PyTorch, and in the training code, I moved both the neural network as well as the training data to the gpu. However, when I run the program, it uses up to 2GB of my ram. There is a little gpu memory that is used, but not that much. When i run the same program, but this time on the cpu, it takes only about 900mb of my ram. Can anyone tell me why is is happening? i have attached my code, as well as a couple of screenshots. Sorry if the answer is pretty obvious, I'm new to deep learning.

My code:

I'm working on a project which is stored locally inside a folder called NeuralNetwork.

I have a .py file inside a folder load_data named load_data.py. Inside that .py file is a class names LoadData. I would like to import that class inside a file test_load_data.py stored in NeuralNetwork/tests/test_load_data/unit_tests/test_load_data.py

I tried to do it in the following way

I'm having some trouble following a guide at: https://www.geeksforgeeks.org/ml-neural-network-implementation-in-c-from-scratch/ I have installed the eigen library with vcpkg and it seems to be working because it gives no error.

Code:

I use Boost to serialize a NeuralNetwork object with code like this