olliepugh/parkr

A lightweight basic neural networks library in Python

Hey! 👋

What do I make?

I make things that typically don't have much of a purpose but are pretty fun to play/interact with! Interact is a key word for the projects I make, I love making things that people from all over the world can interact with from the comfort of their own home!

• 🚗 Want to drive an RC car but don't have one, You don't need one...

• 🎃 Wanted to make your own VR Horror Game but don't know how to do any game design? You can make and control the game all from your web browser... I got you

• 🎄 Why not even decorate my Christmas Tree for me?

All of these projects get put onto my YouTube Channel in a entertainment/comedy (My mum thinks they're funny?) style.

But Why?

Growing up I was always under the impression computers/engineering is boring, and now I fully beleive that engineering and programming is as boring as you make it, so make sure you make it fun! So I post these projects/videos in the hope it can change the minds of people to get involved and try it out themselves!

parkr's Issues

Investigate random installs in requirements.txt

Not sure why things such as

Pillow
matplotlib

are in the requirements.txt

Fatal error on more than one output node

Fatal error when trying to train with more than one output node.

(env) C:\Users\olive\OneDrive\Programming\Python\Parkr>py main.py
Traceback (most recent call last):
  File "C:\Users\olive\OneDrive\Programming\Python\Parkr\main.py", line 16, in <module>
    my_network.train(epochs, (training_data, expected_data))
  File "C:\Users\olive\OneDrive\Programming\Python\Parkr\src\parkr\network.py", line 180, in train
    row_weight_change, row_bias_change = self.__generate_changes(activated_forward_pass, expected_batches[batch_count][i], step_size, prev_changes=(prev_weight_change, prev_bias_change), **kwargs)  # generate the changes required        
  File "C:\Users\olive\OneDrive\Programming\Python\Parkr\src\parkr\network.py", line 251, in __generate_changes
    delta = np.dot((expected-activated_result[i]), derived)
  File "<__array_function__ internals>", line 5, in dot
ValueError: shapes (1,2) and (1,2) not aligned: 2 (dim 1) != 1 (dim 0)

Fatal bug when trying to export training results

When trying to export training without providing validation data a fatal error occurs.

Line 277 in train.export_file.write("f{training_loss}, {validation_loss}\n")
UnboundLocalError: local variable 'validation_loss' referenced before assignment