Sign inSign in
ConceptAI & ML

Torch.no_grad

A context manager that disables gradient calculation to reduce memory usage during inference.
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Backpropagation2Gradient tracking1PyTorch1PyTorch autograd1

Lecturers

1
  • Andrej Karpathy

    Undergraduate

    • 3:05Building makemore Part 3: Activations, Gradients, Kaiming Init & BatchNorm

Connections

4

The lectures that define it or assume it, and the concepts next to it.

1 lecturer. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.