# By Justin Johnson https://github.com/jcjohnson/pytorch-examples/blob/master/nn/dynamic_net.py
import random
import torch
from torch.autograd import Variable
"""
To showcase the power of PyTorch dynamic graphs, we will implement a very strange
model: a fully-connected ReLU network that on each forward pass randomly chooses
a number between 1 and 4 and has that many hidden layers, reusing the same
weights multiple times to compute the innermost hidden layers.
"""
class DynamicNet(torch.nn.Module):
def __init__(self, D_in, H, D_out):
"""
In the constructor we construct three nn.Linear instances that we will use
in the forward pass.
"""
super(DynamicNet, self).__init__()
self.input_linear = torch.nn.Linear(D_in, H)
self.middle_linear = torch.nn.Linear(H, H)
self.output_linear = torch.nn.Linear(H, D_out)
def forward(self, x, verbose = False):
"""
For the forward pass of the model, we randomly choose either 0, 1, 2, or 3
and reuse the middle_linear Module that many times to compute hidden layer
representations.
Since each forward pass builds a dynamic computation graph, we can use normal
Python control-flow operators like loops or conditional statements when
defining the forward pass of the model.
Here we also see that it is perfectly safe to reuse the same Module many
times when defining a computational graph. This is a big improvement from Lua
Torch, where each Module could be used only once.
"""
h_relu = self.input_linear(x).clamp(min=0)
n_layers = random.randint(0, 3)
if verbose:
print("The number of layers for this run is", n_layers)
# print(h_relu)
for _ in range(n_layers):
h_relu = self.middle_linear(h_relu).clamp(min=0)
if verbose:
pass
# print(h_relu)
y_pred = self.output_linear(h_relu)
return y_pred
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 10, 1
# Create random Tensors to hold inputs and outputs, and wrap them in Variables
x = Variable(torch.randn(N, D_in))
y = Variable(torch.randn(N, D_out), requires_grad=False)
# Construct our model by instantiating the class defined above
model = DynamicNet(D_in, H, D_out)
# Construct our loss function and an Optimizer. Training this strange model with
# vanilla stochastic gradient descent is tough, so we use momentum
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4, momentum=0.9)
for t in range(500):
# Forward pass: Compute predicted y by passing x to the model
y_pred = model(x)
# Compute and print loss
loss = criterion(y_pred, y)
print(t, loss.data[0])
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()
model(x)[1:5]
model(x)[1:5] # another run
model(x)[1:5]
Looks consistent! Let's now try to see what's happening inside
model(x, verbose = True)[1:5]
model(x, verbose = True)[1:5]
model(x, verbose = True)[1:5]
model(x, verbose = True)[1:5]
model(x, verbose = True)[1:5]
So what's the target?
y[1:5]