Instantly share code, notes, and snippets.

Embed
What would you like to do?
PyTorch RNN training example
import torch
import torch.nn as nn
from torch.nn import functional as F
from torch.autograd import Variable
from torch import optim
import numpy as np
import math, random
# Generating a noisy multi-sin wave
def sine_2(X, signal_freq=60.):
return (np.sin(2 * np.pi * (X) / signal_freq) + np.sin(4 * np.pi * (X) / signal_freq)) / 2.0
def noisy(Y, noise_range=(-0.05, 0.05)):
noise = np.random.uniform(noise_range[0], noise_range[1], size=Y.shape)
return Y + noise
def sample(sample_size):
random_offset = random.randint(0, sample_size)
X = np.arange(sample_size)
Y = noisy(sine_2(X + random_offset))
return Y
# Define the model
class SimpleRNN(nn.Module):
def __init__(self, hidden_size):
super(SimpleRNN, self).__init__()
self.hidden_size = hidden_size
self.inp = nn.Linear(1, hidden_size)
self.rnn = nn.LSTM(hidden_size, hidden_size, 2, dropout=0.05)
self.out = nn.Linear(hidden_size, 1)
def step(self, input, hidden=None):
input = self.inp(input.view(1, -1)).unsqueeze(1)
output, hidden = self.rnn(input, hidden)
output = self.out(output.squeeze(1))
return output, hidden
def forward(self, inputs, hidden=None, force=True, steps=0):
if force or steps == 0: steps = len(inputs)
outputs = Variable(torch.zeros(steps, 1, 1))
for i in range(steps):
if force or i == 0:
input = inputs[i]
else:
input = output
output, hidden = self.step(input, hidden)
outputs[i] = output
return outputs, hidden
n_epochs = 100
n_iters = 50
hidden_size = 10
model = SimpleRNN(hidden_size)
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)
losses = np.zeros(n_epochs) # For plotting
for epoch in range(n_epochs):
for iter in range(n_iters):
_inputs = sample(50)
inputs = Variable(torch.from_numpy(_inputs[:-1]).float())
targets = Variable(torch.from_numpy(_inputs[1:]).float())
# Use teacher forcing 50% of the time
force = random.random() < 0.5
outputs, hidden = model(inputs, None, force)
optimizer.zero_grad()
loss = criterion(outputs, targets)
loss.backward()
optimizer.step()
losses[epoch] += loss.data[0]
if epoch > 0:
print(epoch, loss.data[0])
# Use some plotting library
# if epoch % 10 == 0:
# show_plot('inputs', _inputs, True)
# show_plot('outputs', outputs.data.view(-1), True)
# show_plot('losses', losses[:epoch] / n_iters)
# Generate a test
# outputs, hidden = model(inputs, False, 50)
# show_plot('generated', outputs.data.view(-1), True)
# Online training
hidden = None
while True:
inputs = get_latest_sample()
outputs, hidden = model(inputs, hidden)
optimizer.zero_grad()
loss = criterion(outputs, inputs)
loss.backward()
optimizer.step()
@marianophielipp

This comment has been minimized.

marianophielipp commented Aug 29, 2018

---> 75 loss = criterion(outputs, targets)
RuntimeError: input and target shapes do not match: input [49 x 1 x 1], target [49] at /Users/soumith/code/builder/wheel/pytorch-src/aten/src/THNN/generic/MSECriterion.c:12

@marianophielipp

This comment has been minimized.

marianophielipp commented Aug 29, 2018

loss = criterion(torch.squeeze(outputs), targets)
Pytorch version 0.4.1

@ishan00

This comment has been minimized.

ishan00 commented Oct 9, 2018

Shouldn't it be outputs, hidden = model.forward(inputs, None, force) instead of outputs, hidden = model(inputs, None, force) at line 72. Also line 99

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment