I have a simple toy NN with Pytorch. I am setting all the seeds I can find in the docs as well as numpy random.
If I run the code below from top to bottom, the results appear to be reproducible.
BUT, if I run Block 1 only once and then each time repeatedly run block 2, the result changes (sometimes dramatically). I am unsure why this happens since the network is being re-initialized and optimizer reset each time. Something with the inputs and target?
I am using version 0.4.0
BLOCK #1**************************************
from __future__ import division
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import torch
import torch.utils.data as utils_data
from torch.autograd import Variable
from torch import optim, nn
from torch.utils.data import Dataset
import torch.nn.functional as F
from torch.nn.init import xavier_uniform_, xavier_normal_,uniform_
torch.manual_seed(123)
import random
random.seed(123)
from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split
%matplotlib inline
cuda=True #set to true uses GPU
if cuda:
torch.cuda.manual_seed(123)
#load boston data from scikit
boston = load_boston()
x=boston.data
y=boston.target
y=y.reshape(y.shape[0],1)
#train and test
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.3, random_state=123, shuffle=False)
#change to tensors
x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)
#create dataset and use data loader
training_samples = utils_data.TensorDataset(x_train, y_train)
data_loader_trn = utils_data.DataLoader(training_samples, batch_size=64,drop_last=False)
#change to tensors
x_test = torch.from_numpy(x_test)
y_test = torch.from_numpy(y_test)
#create dataset and use data loader
testing_samples = utils_data.TensorDataset(x_test, y_test)
data_loader_test = utils_data.DataLoader(testing_samples, batch_size=64,drop_last=False)
#simple model
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
#all the layers
self.fc1 = nn.Linear(x.shape[1], 20)
xavier_uniform_(self.fc1.weight.data) #this is how you can change the weight init
self.drop = nn.Dropout(p=0.5)
self.fc2 = nn.Linear(20, 1)
def forward(self, x):
x = F.relu(self.fc1(x))
x= self.drop(x)
x = self.fc2(x)
return x
****BLOCK #2******************************************
net=Net()
if cuda:
net.cuda()
# create a stochastic gradient descent optimizer
optimizer = optim.Adam(net.parameters())
# create a loss function (mse)
loss = nn.MSELoss(size_average=False)
# run the main training loop
epochs =20
hold_loss=[]
for epoch in range(epochs):
cum_loss=0.
cum_records_epoch =0
for batch_idx, (data, target) in enumerate(data_loader_trn):
tr_x, tr_y = data.float(), target.float()
if cuda:
tr_x, tr_y = tr_x.cuda(), tr_y.cuda()
# Reset gradient
optimizer.zero_grad()
# Forward pass
fx = net(tr_x)
output = loss(fx, tr_y) #loss for this batch
cum_loss += output.item() #accumulate the loss
# Backward
output.backward()
# Update parameters based on backprop
optimizer.step()
cum_records_epoch +=len(tr_x)
if batch_idx % 1 == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, cum_records_epoch, len(data_loader_trn.dataset),
100. * (batch_idx+1) / len(data_loader_trn), output.item()))
print('Epoch average loss: {:.6f}'.format(cum_loss/cum_records_epoch))
hold_loss.append(cum_loss/cum_records_epoch)
#training loss
plt.plot(np.array(hold_loss))
plt.show()