from mxnet import init, np, npx
from mxnet.gluon import nn
npx.set_np()A neural network is a tree of parameters — the weight matrices and bias vectors gradient descent updates. Training is one thing you do with them; this deck covers the others.
A nested module is just a tree. Each module is a node; each parameter is a leaf:
net (Sequential)
├─ 0: Linear ├─ weight (8, 4)
│ └─ bias (8,)
├─ 1: ReLU (no params)
└─ 2: Linear ├─ weight (1, 8)
└─ bias (1,)
Two access patterns:
net[2].weight — direct.Frameworks give you both, plus serialization built on the same traversal.
Index into a Sequential like a list; each layer exposes its parameters as attributes:
Two parameters per Linear layer — weight matrix and bias vector. The output object is a Parameter (PyTorch) or similar wrapper that carries the tensor + gradient + extra metadata.
.data (PyTorch) unwraps the parameter to a plain tensor for inspection:
For everything-at-once, use named_parameters(). It walks the whole tree and yields (name, param) pairs at the leaves — names use dotted paths through the nesting:
This is the iterator optim.SGD(net.parameters(), …) consumes. It’s also what gets pickled when you save a checkpoint with state_dict(). Walk-tree-once, use many ways.
Reuse the same module instance at multiple positions in your architecture, and the framework treats them as one parameter set — same memory, gradients accumulate across uses.
Common cases:
net = nn.Sequential()
# We need to give the shared layer a name so that we can refer to its
# parameters
shared = nn.Dense(8, activation='relu')
shared_clone = nn.Dense(8, activation='relu')
shared_clone.share_parameters(shared.collect_params())
net.add(nn.Dense(8, activation='relu'),
shared,
shared_clone,
nn.Dense(10))
net.initialize()
X = np.random.uniform(size=(2, 20))
net(X)
# Check whether the parameters are the same
print(net[1].weight.data()[0] == net[2].weight.data()[0])
net[1].weight.data()[0, 0] = 100
# Make sure that they are actually the same object rather than just having the
# same value
print(net[1].weight.data()[0] == net[2].weight.data()[0])Modify net[2].weight and net[4].weight reflects the same change — they are the same tensor, not just equal.
net[i].weight, .bias, .grad.named_parameters() / state_dict() walks the whole tree.