Train on numpy arrays

Hello everyone,
I wanna say that I am a total beginner to the entire topic of NN.
I am trying to train a CNN on classifying numpy arrays into one of two categories.

So the first question is if a CNN is even the right approach or if I should use something else.

I have one 3D numpy array (third component is time) and one that contains the labels (either True or False).

What I do with them is currently:

  tensor_training_data = torch.Tensor(training_data)
  tensor_training_label = torch.Tensor(training_label)
  training_dataset = TensorDataset(tensor_training_data, tensor_training_label)

Second question: Is this the right way to handle the data?

Third question: Is there some tutorial for handling data that are not images? All I saw always utilizes images and therefore 3 channels. My understanding of this topic is at the moment not good enough to figure out how to proceed.

To clarify: I don’t want anyone to do the work for me, I just need someone pointing me in the right direction.