finish chapter 6
This commit is contained in:
11
06_training pipeline.md
Normal file
11
06_training pipeline.md
Normal file
@@ -0,0 +1,11 @@
|
||||
# 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)
|
||||
Reference in New Issue
Block a user