PyTorch / Tensor, gradient, and module foundations

PyTorch β€” Tensor, gradient, and module foundations

CPU tensors, autograd modes, registered state, loss targets, data batches, and one controlled update.

6 lessons Β· No account required

What you will learn

  • CPU tensors, autograd modes, registered state, loss targets, data batches, and one controlled update.

  1. CPU tensors, dtypes, and shapes

    Construct a tensor with explicit ownership, numeric representation, and axis meaning before building a model.

    Start learning

  2. Autograd and gradient modes

    Trace which operations enter a backward graph and separate gradient accumulation from parameter updates.

    Start learning

  3. Modules, parameters, and buffers

    Use nn.Module registration to make trainable values, persistent state, and composition explicit.

    Start learning

  4. Losses, targets, and reductions

    Match a PyTorch loss input contract to target meaning, dimensions, dtype, and weighting.

    Start learning

  5. Datasets, loaders, and collation

    Define one sample and one batch explicitly while preserving identity, coverage, and split boundaries.

    Start learning

  6. A controlled training and evaluation step

    Make the order and state of one complete PyTorch update visible before building a larger training loop.

    Start learning
Back to course