Files
pytorch_learn/06_training pipeline.md
Joseph Hopfmüller 3ce77417fe finish chapter 6
2022-10-17 13:04:51 +02:00

11 lines
303 B
Markdown

# Training Pipeline
a training pipeline generally consists of 3 steps:
1. Design model (input, output size, forward pass (layers))
2. Construct loss and optimizer
3. Training loop
- forward pass: compute prediction
- backward pass: gradient computation
- update parameters
(iterate step 3)