pytorch loading model not same softmax probabilities - python-3.x

Question

I cannot reproduce the same results after loading a model using pytorch.
I am training a model 'net' and in the same file, after training (kfold) then the model is saved and also tested in 1 specific testing file:
class model(nn.Module):
def __init__(self,size_net):
print('Initialize net with size: ',size_net)
self.T = size_net
# Layer 1
self.conv1 = nn.Conv2d(1, 16, (1,16), padding = 0)
self.batchnorm1 = nn.BatchNorm2d(16, False)
# Layer 2
self.padding1 = nn.ZeroPad2d((16, 17, 0, 1))
self.conv2 = nn.Conv2d(1, 4, (2, 32))
self.batchnorm2 = nn.BatchNorm2d(4, False)
self.pooling2 = nn.MaxPool2d(2, 4)
# Layer 3
self.padding2 = nn.ZeroPad2d((2, 1, 4, 3))
self.conv3 = nn.Conv2d(4, 4, (8, 4))
self.batchnorm3 = nn.BatchNorm2d(4, False)
self.pooling3 = nn.MaxPool2d((2, 4))
# FC Layer
# NOTE: This dimension will depend on the number of timestamps per sample in your data.
# I have 120 timepoints.
self.fc1 = nn.Linear(int(self.T/2), 2)
def forward(self, x):
# Layer 1
x = F.elu(self.conv1(x))
x = self.batchnorm1(x)
x = F.dropout(x, 0.25)
x = x.permute(0, 3, 1, 2)
#print "layer 1"
# Layer 2
x = self.padding1(x)
x = F.elu(self.conv2(x))
x = self.batchnorm2(x)
x = F.dropout(x, 0.25)
x = self.pooling2(x)
#print "layer 2"
# Layer 3
x = self.padding2(x)
x = F.elu(self.conv3(x))
x = self.batchnorm3(x)
x = F.dropout(x, 0.25)
x = self.pooling3(x)
#print "layer 3"
# FC Layer
#print ('view:',x.shape)
x = x.view(-1, int(self.T/2))
#x = torch.sigmoid(self.fc1(x))
x= torch.softmax(self.fc1(x),1)
#print "layer 4"
return x
#now call the model and train
net = model(SIZE_NET)
....
eval.train_Kfold_validation(n_epochs=25)
## save models state
"""
net = EEGNet(SIZE_NET)
save_path = './eeg_net_{}.pt'.format(date.today().strftime("%Y%m%d"))
torch.save(net.state_dict(), save_path)
'''
TEST
'''
testfile = '1_testonline_1_20190202-163051.csv'
kun_1 = np.genfromtxt( '../'+ testfile, delimiter=',').astype('float32')[:-1, :]
kun_1 = kun_1[:, :SIZE_NET]
X, y = prep.list_2darrays_to_3d([kun_1], -1)
print(X.shape)
array_dstack = np.array(X)
array_dstack_reshaped = np.reshape(array_dstack,(1, 1, SIZE_NET, 16))
inputs = Variable(torch.from_numpy(array_dstack_reshaped))
pred = net(inputs)
print('prob: '+str(pred)) #Converted to probabilities
For example for this file I got: pred=tensor([[0.5912, 0.4088]], grad_fn=)
When instead I load the saved model in a new script and I attempt inference again on the same testfile:
prep= Data_prep()
fileName = '1_testonline_1_20190202-163051.csv'
kun_1 = np.genfromtxt(file_dir+fileName, delimiter=',').astype('float32')[:-1,:]
kun_1 = kun_1[:,:SIZE_NET]
X , y = prep.list_2darrays_to_3d([kun_1],[-1])
# Load pre-trained model
net = model(SIZE_NET)
load_path = file_dir+'/model_colors/model_20190205.pt'
net.load_state_dict(torch.load(load_path))
net.eval()
array_dstack = np.array(X)
print(X.shape)
# (#samples, 1, #timepoints, #channels)
array_dstack_reshaped = np.reshape(array_dstack,(1, 1, SIZE_NET, 16))
inputs = Variable(torch.from_numpy(array_dstack_reshaped))
pred = net(inputs)
print(pred)
When I run the test script the prob values are different and even worse NOT stable: running multiple times give different predictions... Any help appreciated

Answer 1

As #Jatentaki pointed out the solution is to ALWAYS fix the seed in all scripts that need to use the model in pytorch
torch.manual_seed(0)