training_accuracy = []
### Training of the model
for e in range(nb_epochs + 1):
for b in range(0, train_input.size(0), mini_batch_size):
##Forward propagation
output = model.forward(train_input.narrow(0, b, mini_batch_size).t())
#Calculate loss
loss = criterion.forward(
output,
train_target_hot.narrow(0, b, mini_batch_size).t())
# put to zero weights and bias
model.zero_grad()
##Backpropagation
#Calculate grad of loss
loss_grad = criterion.backward()
#Grad of the model
model.backward(loss_grad)
#Update parameters
model.grad_step(lr=lr)
if e % print_step == 0:
print(f'Epoc : {e}, Loss: {loss}')
#Save loss in vector
loss_at_print.append(float(loss))
pytorch_training_accuracy = []
### Training of the framework_model
for e in range(nb_epochs+1):
for b in range(0, train_input.size(0), mini_batch_size):
#Train the mini deep learning framework
##Forward propagation
framework_output = framework_model.forward(train_input.narrow(0, b, mini_batch_size).t())
#Calculate loss
framework_loss = framework_criterion.forward(framework_output,train_target_hot.narrow(0,b,mini_batch_size).t())
# put to zero weights and bias
framework_model.zero_grad()
##Backpropagation
#Calculate grad of loss
loss_grad = framework_criterion.backward()
#Grad of the framework_model
framework_model.backward(loss_grad)
#Update parameters
framework_model.grad_step(lr=lr)
#Train the model using pytorch NN
pytorch_output = pytorch_model(train_input.narrow(0, b, mini_batch_size))
pytorch_loss = pytorch_criterion(pytorch_output, train_target_hot.narrow(0, b, mini_batch_size))
pytorch_model.zero_grad()