Welcome to dtorch’s documentation!

---

Description

DTorch is a package made by a student at Epitech to improve his understanding of pytorch and better his knowledge of ia.

It is built on top of numpy which is a scientific framework for math between matrices.

This project run on cpu but still have decent computation time making it usable for model building, optimization and saving/loading. The tensors created can work with numpy but remember that the gradients will not be calculated if the operation are not in the range of control of the library. Therefore, a usage of the packages methods on the tensors if preferable. Cuda support may appear in the future and similarly for the mkldnn library that seems to be excellent when working on CPU.

Tip

A direct advantage of using dtorch is it’s lightness. The package is currently close to 14 Ko and is fast to load in any project while the use of torch often lead to a slow start.

Content

• dtorch
  • Description
  • 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
• dtorchtree
  • Description
  • Modules
    • dtorchtree.models
      • Description
      • Models
        • DecisionTree
          • DecisionTree.__init__()
          • DecisionTree.fit()
          • DecisionTree.predict()
          • DecisionTree.save()
          • DecisionTree.load()
      • Pretrained Models
        • IrisDecisionTree
          • IrisDecisionTree.__init__()
          • IrisDecisionTree.predict()
    • dtorchtree.datasets
      • Description
      • Datasets
        • IrisDataset
          • IrisDataset.__init__()
          • IrisDataset.data
• dtorchvision
  • Description
  • Modules
    • dtorchvision.models
      • Description
      • Models
        • AutoEncoder
          • AutoEncoder.__init__()
      • Pretrained Models
        • MNISTAutoEncoder_128_32
          • MNISTAutoEncoder_128_32.__init__()
    • dtorchvision.datasets
      • Description
      • Datasets
        • MNISTDataset
          • MNISTDataset.__init__()
          • MNISTDataset.data
          • MNISTDataset.train_data()
          • MNISTDataset.test_data()
• dtorchtext