dtorch

Description

This package is the main module of this project for machine learning. It is basicly a replica of pytorch. It offer the possibility to create tensor, have them store elements for gradient calcul and create ML models.

Important

This project is currently in progress. It’s undergoing majors changes and is subject to changements

Modules

Here’s the list of the available modules:

• dtorch.jtensors
  • JTensors
    • JTensors.grad
    • JTensors.require_grads
    • JTensors.ndims
    • JTensors.shape
    • JTensors.dtype
    • JTensors.T
    • JTensors.itemsize
    • JTensors.size
    • JTensors.stride
    • JTensors.backward()
    • JTensors.numpy()
    • JTensors.transpose()
    • JTensors.reshape()
    • JTensors.max()
    • JTensors.sum()
    • JTensors.rearrange()
    • JTensors.shuffle()
    • JTensors.norm()
    • JTensors.detach()
    • JTensors.clone()
    • JTensors.unsqueeze()
    • JTensors.squeeze()
• dtorch.nn
  • Description
  • Layers
    • Module
      • Module.save()
      • Module.load()
      • Module.parameters()
      • Module.eval()
      • Module.train()
    • Linear
      • Linear.__init__()
    • Sequential
      • Sequential.__init__()
    • Softmax
    • Sigmoid
    • ReLU
    • Tanh
    • Dropout
      • Dropout.__init__()
    • RNN
      • RNN.__init__()
    • Conv1d
      • Conv1d.__init__()
    • Conv2d
• dtorch.functionnal
  • Description
  • Functions
    • transpose()
    • split()
    • norm()
    • sqrt()
    • logsumexp()
    • sigmoid()
    • from_list()
    • to_list()
    • as_strided()
    • conv1d()
    • conv2d()
    • dropout()
    • softmax()
    • max()
    • exp()
    • log()
    • matmul()
    • sum()
    • squeeze()
    • unsqueeze()
    • reshape()
    • arange()
    • tensor()
    • random()
    • ones()
    • zeros()
    • xavier()
    • zeros_like()
    • uniform_()
• dtorch.einops
  • Description
  • Functions
    • rearrange()
• dtorch.optim
  • Description
  • Optimizers
    • Optimizer
      • Optimizer.zero_grad()
      • Optimizer.step()
    • SGD
      • SGD.__init__()
    • Adam
      • Adam.__init__()
• dtorch.loss
  • Description
  • Loss
    • MSELoss
    • BCELoss