If we combine one trainable parameters with a non-trainable parameter, is the original trainable param trainable?

Question

I have two nets and I combine their parameters in some fancy way using only pytorch operations. I store the result in a third net which has its parameters set to non-trainable . Then I proceed and pass data through this new net. The new net is just a placeholder for:

placeholder_net.W = Op( not_trainable_net.W, trainable_net.W )

Then I pass data:

output = placeholder_net(input)

I am concerned that since the parameters of the placeholder net are set to non-trainable that it won't actually train the variable that it should train. Will this happen? Or what is the result when you combine a trainable param with and non-trainable param (and then set that where the param is not trainable)?

---

Current solution:

del net3.conv0.weight
net3.conv0.weight = net.conv0.weight + net2.conv0.weight

---

import torch
from torch import nn
import torch.optim as optim

import torchvision
import torchvision.transforms as transforms

from collections import OrderedDict

import copy

def dont_train(net):
    '''
    set training parameters to false.
    '''
    for param in net.parameters():
        param.requires_grad = False
    return net

def get_cifar10():
    transform = transforms.Compose(
        [transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
    trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,shuffle=True, num_workers=2)
    classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')
    return trainloader,classes



def combine_nets(net_train, net_no_train, net_place_holder):
        '''
            Combine nets in a way train net is trainable
        '''
        params_train = net_train.named_parameters()
        dict_params_place_holder = dict(net_place_holder.named_parameters())
        dict_params_no_train = dict(net_no_train.named_parameters())
        for name, param_train in params_train:
            if name in dict_params_place_holder:
                layer_name, param_name = name.split('.')
                param_no_train = dict_params_no_train[name]
                ## get place holder layer
                layer_place_holder = getattr(net_place_holder, layer_name)
                delattr(layer_place_holder, param_name)
                ## get new param
                W_new = param_train + param_no_train  # notice addition is just chosen for the sake of an example
                ## store param in placehoder net
                setattr(layer_place_holder, param_name, W_new)
        return net_place_holder

def combining_nets_lead_to_error():
    '''
    Intention is to only train the net with trainable params.
    Placeholder rnet is a dummy net, it doesn't actually do anything except hold the combination of params and its the
    net that does the forward pass on the data.
    '''
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    ''' create three musketeers '''
    net_train = nn.Sequential(OrderedDict([
          ('conv1', nn.Conv2d(1,20,5)),
          ('relu1', nn.ReLU()),
          ('conv2', nn.Conv2d(20,64,5)),
          ('relu2', nn.ReLU())
        ])).to(device)
    net_no_train = copy.deepcopy(net_train).to(device)
    net_place_holder = copy.deepcopy(net_train).to(device)
    ''' prepare train, hyperparams '''
    trainloader,classes = get_cifar10()
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net_train.parameters(), lr=0.001, momentum=0.9)
    ''' train '''
    net_train.train()
    net_no_train.eval()
    net_place_holder.eval()
    for epoch in range(2):  # loop over the dataset multiple times
        running_loss = 0.0
        for i, (inputs, labels) in enumerate(trainloader, 0):
            optimizer.zero_grad() # zero the parameter gradients
            inputs, labels = inputs.to(device), labels.to(device)
            # combine nets
            net_place_holder = combine_nets(net_train,net_no_train,net_place_holder)
            #
            outputs = net_place_holder(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            # print statistics
            running_loss += loss.item()
            if i % 2000 == 1999:  # print every 2000 mini-batches
                print('[%d, %5d] loss: %.3f' %
                      (epoch + 1, i + 1, running_loss / 2000))
                running_loss = 0.0
    ''' DONE '''
    print('Done \a')

if __name__ == '__main__':
    combining_nets_lead_to_error()

Answer 1

I'm not sure if this is what you want to know.

But when I understand you correct - you want to know if the results of operations with non-trainable and trainable variables are still trainable ?

If so, this is indeed the case, here is an example:

>>> trainable = torch.ones(1, requires_grad=True)
>>> non_trainable = torch.ones(1, requires_grad=False)
>>> result = trainable + non_trainable
>>> result.requires_grad
True

Maybe you might also find torch.set_grad_enabled useful, with some examples given here (PyTorch Migration Guide for version 0.4.0 ):

https://pytorch.org/2018/04/22/0_4_0-migration-guide.html

Answer 2

First, do not use eval() mode for any network. Set requires_grad flag to false to make the parameters non-trainable for only the second network and train the placeholder network.

If this doesn't work, you can try the following approach which I prefer.

Instead of using multiple networks, you can use a single network and use a non-trainable layer as a parallel connection after every trainable layer before non-linearity.

For example look at this image:

Set requires_grad flag to false to make the parameters non-trainable. Do not use eval() and train the network.

Combining outputs of the layers before non-linearity is important. Initialize the parameters of the parallel layer and choose the post-operation such that it gives the same result as when you combine the parameters.

Answer 3

Original answer below, here I address the added code you've uploaded.

in your combine_nets functions you needlessly try to remove and set the attribute, when you can simply copy your required value like this:

def combine_nets(net_train, net_no_train, net_place_holder):
    '''
        Combine nets in a way train net is trainable
    '''
    params_train = net_no_train.named_parameters()
    dict_params_place_holder = dict(net_place_holder.named_parameters())
    dict_params_no_train = dict(net_train.named_parameters())
    for name, param_train in params_train:
        if name in dict_params_place_holder:
            param_no_train = dict_params_no_train[name]
            W_new = param_train + param_no_train 
            dict_params_no_train[name].data.copy_(W_new.data)
    return net_place_holder

Due to other errors in the code you've supplied I couldn't make it run without further changes so I attach below an updated version of the code I've given you earlier:

import torch
from torch import nn
from torch.autograd import Variable
import torch.optim as optim


# toy feed-forward net
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.fc1 = nn.Linear(10, 5)
        self.fc2 = nn.Linear(5, 5)
        self.fc3 = nn.Linear(5, 1)

    def forward(self, x):
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        return x

def combine_nets(net_train, net_no_train, net_place_holder):
    '''
        Combine nets in a way train net is trainable
    '''
    params_train = net_no_train.named_parameters()
    dict_params_place_holder = dict(net_place_holder.named_parameters())
    dict_params_no_train = dict(net_train.named_parameters())
    for name, param_train in params_train:
        if name in dict_params_place_holder:
            param_no_train = dict_params_no_train[name]
            W_new = param_train + param_no_train
            dict_params_no_train[name].data.copy_(W_new.data)
return net_place_holder


# define random data
random_input1 = Variable(torch.randn(10,))
random_target1 = Variable(torch.randn(1,))
random_input2 = Variable(torch.rand(10,))
random_target2 = Variable(torch.rand(1,))
random_input3 = Variable(torch.randn(10,))
random_target3 = Variable(torch.randn(1,))

# define net
net1 = Net()
net_place_holder = Net()
net2 = Net()

# train the net1
criterion = nn.MSELoss()
optimizer = optim.SGD(net1.parameters(), lr=0.1)
for i in range(100):
    net1.zero_grad()
    output = net1(random_input1)
    loss = criterion(output, random_target1)
    loss.backward()
    optimizer.step()

# train the net2
criterion = nn.MSELoss()
optimizer = optim.SGD(net2.parameters(), lr=0.1)
for i in range(100):
    net2.zero_grad()
    output = net2(random_input2)
    loss = criterion(output, random_target2)
    loss.backward()
    optimizer.step()

# train the net2
criterion = nn.MSELoss()
optimizer = optim.SGD(net_place_holder.parameters(), lr=0.1)
for i in range(100):
    net_place_holder.zero_grad()
    output = net_place_holder(random_input3)
    loss = criterion(output, random_target3)
    loss.backward()
    optimizer.step()

print('#'*50)
print('Weights before combining')
print('')
print('net1 fc2 weight after train:')
print(net1.fc3.weight)
print('net2 fc2 weight after train:')
print(net2.fc3.weight)

combine_nets(net1, net2, net_place_holder)

print('#'*50)
print('')
print('Weights after combining')
print('net1 fc2 weight after train:')
print(net1.fc3.weight)
print('net2 fc2 weight after train:')
print(net2.fc3.weight)


# train the net
criterion = nn.MSELoss()
optimizer1 = optim.SGD(net1.parameters(), lr=0.1)
for i in range(100):
    net1.zero_grad()
    net2.zero_grad()
    output1 = net1(random_input3)
    output2 = net2(random_input3)
    loss1 = criterion(output1, random_target3)
    loss2 = criterion(output2, random_target3)
    loss = loss1 + loss2
    loss.backward()
    optimizer1.step()

print('#'*50)
print('Weights after further training')
print('')
print('net1 fc2 weight after freeze:')
print(net1.fc3.weight)
print('net2 fc2 weight after freeze:')
print(net2.fc3.weight)