Data pipeline: From files to tensors
Training a neural network one example at a time is slow and inefficient. We combine data into batches. To keep this process from bottlenecking the GPU, PyTorch uses multithreaded loading. While the GPU computes gradients for one batch, the CPU is already preparing and slicing the next.
Content is available with subscription.
Get full access to all courses on the platform for one year with a single payment.
▼
Unlike other platforms that charge per course, here you get everything for one price, and after one year of use there will be no automatic charge for the following year.