def train():
"""
Performs training and evaluation of ConvNet model.
TODO:
Implement training and evaluation of ConvNet model. Evaluate your model on the whole test set each eval_freq iterations.
"""
### DO NOT CHANGE SEEDS!
# Set the random seeds for reproducibility
np.random.seed(42)
# ## Prepare all functions
# # Get number of units in each hidden layer specified in the string such as 100,100
# if FLAGS.dnn_hidden_units:
# dnn_hidden_units = FLAGS.dnn_hidden_units.split(",")
# dnn_hidden_units = [int(dnn_hidden_unit_) for dnn_hidden_unit_ in dnn_hidden_units]
# else:
# dnn_hidden_units = []
# Set path to data
data_dir = FLAGS.data_dir
data = cifar10_utils.get_cifar10(data_dir)
# Prepare the test set
input_dims_test = data['test'].images.shape
height = input_dims_test[2]
width = input_dims_test[3]
channels = input_dims_test[1]
# num_images_test = input_dims_test[0]
# image_dims_ravel = height * width * channels
X_test = data["test"].images
Y_test = data["test"].labels
# Make acceptable input for test
# X_test = X_test.reshape((num_images_test, image_dims_ravel))
# make usable by pytorch
X_test = torch.tensor(X_test, requires_grad=False).type(dtype).to(device)
Y_test = torch.tensor(Y_test, requires_grad=False).type(dtype).to(device)
# Determine the channels
n_channels = channels
model = ConvNet(n_channels=n_channels, n_classes=10)
model.cuda()
accuracy_train_log = list()
accuracy_test_log = list()
loss_train_log = list()
loss_test_log = list()
# FLAGS hold command line arguments
batch_size = FLAGS.batch_size
numb_iterations = FLAGS.max_steps
learning_rate = FLAGS.learning_rate
evaluation_freq = FLAGS.eval_freq
logging.info(f"learning rate: %2d " % learning_rate)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
# X_train = data['train'].images.reshape((data['train'].images.shape[0],
# image_dims_ravel))
X_train = data['train'].images
Y_train = data['train'].labels
X_train = torch.tensor(X_train, requires_grad=False).type(dtype).to(device)
Y_train = torch.tensor(Y_train, requires_grad=False).type(dtype).to(device)
targs_train = Y_train.argmax(dim=1)
# running_loss = loss_current.detach().item()
for step in range(numb_iterations):
X_batch, Y_batch = data['train'].next_batch(batch_size)
# X_batch = X_batch.reshape((batch_size, image_dims_ravel))
# Convert to tensors which are handled by the device
X_batch = torch.from_numpy(X_batch).type(dtype).to(device)
Y_batch = torch.from_numpy(Y_batch).type(dtype).to(device)
# why do we need this again?
optimizer.zero_grad()
targs = Y_batch.argmax(dim=1)
outputs = model.forward(X_batch)
loss_current = criterion(outputs, targs)
loss_current.backward()
optimizer.step()
running_loss = loss_current.detach().item()
if step % evaluation_freq == 0:
list_acc = list()
list_loss = list()
for i in range(0, 70):
selection = random.sample(range(1, 5000), 64)
targs_train = Y_train[selection].argmax(dim=1)
outputs_train = model(X_train[selection])
loss_current_train = criterion(outputs_train, targs_train).detach().item()
acc_current_train = accuracy(outputs_train, Y_train[selection])
list_loss.append(loss_current_train)
list_acc.append(acc_current_train)
loss_train_log.append(np.mean(list_loss))
accuracy_train_log.append(np.mean(list_acc))
logging.info(f"train performance: loss = %4f, accuracy = %4f ", loss_train_log[-1], accuracy_train_log[-1])
# loss_train_log.append(running_loss)
# accuracy_train_log.append(accuracy(outputs, Y_batch))
# logging.info(f"train performance: loss = %4f, accuracy = %4f ", loss_train_log[-1], accuracy_train_log[-1])
# Get performance on the test set
# targs_test = Y_test.argmax(dim=1)
# outputs_test = model(X_test)
# test_loss_current = criterion(outputs_test, targs_test).detach().item()
list_acc = list()
list_loss= list()
for i in range(0, 15):
selection = random.sample(range(1, 1000), 64)
targs_test = Y_test[selection].argmax(dim=1)
outputs_test = model(X_test[selection])
loss_current_test = criterion(outputs_test, targs_test).detach().item()
acc_current_test = accuracy(outputs_test, Y_test[selection])
list_loss.append(loss_current_test)
list_acc.append(acc_current_test)
loss_test_log.append(np.mean(list_loss))
accuracy_test_log.append(np.mean(list_acc))
logging.info(f"test performance: loss = %4f , accuracy = %4f\n", loss_test_log[-1], accuracy_test_log[-1])
# TODO: implement early stopping ?
path = "./convnet_results_pytorch/"
date_time = datetime.now().replace(second=0, microsecond=0).strftime(format="%Y-%m-%d-%H-%M")
np.save(os.path.join(path, date_time + "accuracy_test"), accuracy_test_log)
np.save(os.path.join(path, date_time + "loss_test"), loss_test_log)
np.save(os.path.join(path, date_time + "loss_train"), loss_train_log)
np.save(os.path.join(path, date_time + "accuracy_train"), accuracy_train_log)
def train():
"""
Performs training and evaluation of ConvNet model.
TODO:
Implement training and evaluation of ConvNet model. Evaluate your model on the whole test set each eval_freq iterations.
"""
# set cuda
cuda = False
### DO NOT CHANGE SEEDS!
# Set the random seeds for reproducibility
np.random.seed(42)
# import the test data
cifar10 = cifar10_utils.get_cifar10(FLAGS.data_dir)
loss_function = torch.nn.CrossEntropyLoss()
neuralnet = ConvNet(3, 10)
if cuda:
neuralnet.cuda() # run on GPU
sgd_back = torch.optim.Adam(neuralnet.parameters(), lr=FLAGS.learning_rate)
#lists with losses and accuracies
train_losses = []
train_accs = []
test_losses = []
test_accs = []
graph_x = []
# for i in range(50):
for i in range(FLAGS.max_steps):
neuralnet.train()
x, y = cifar10['train'].next_batch(FLAGS.batch_size)
if cuda:
x = torch.from_numpy(x).cuda()
y = torch.from_numpy(y).cuda()
else:
x = torch.from_numpy(x)
y = torch.from_numpy(y)
# predict on the train data and calculate the gradients
out = neuralnet.forward(x) #output after the softmax
train_loss = loss_function(out, y.argmax(dim=1))
sgd_back.zero_grad()
train_loss.backward()
sgd_back.step()
# save the losses for every eval_freqth loop
if i % FLAGS.eval_freq == 0 or i == (FLAGS.max_steps - 1):
# if i % 1 == 0 or i == (FLAGS.max_steps - 1):
neuralnet.eval()
with torch.no_grad():
test_x, test_y = cifar10['test'].next_batch(1000)
if cuda:
torch.cuda.empty_cache()
test_x = torch.from_numpy(test_x).cuda()
test_y = torch.from_numpy(test_y).cuda()
else:
test_x = torch.from_numpy(test_x)
test_y = torch.from_numpy(test_y)
train_out = neuralnet.forward(x) # output after the softmax
test_out = neuralnet.forward(test_x)
if cuda:
torch.cuda.empty_cache()
train_loss = loss_function(train_out, y.argmax(dim=1))
test_loss = loss_function(test_out, test_y.argmax(dim=1))
train_acc = accuracy(out, y)
test_acc = accuracy(test_out, test_y)
train_losses.append(train_loss)
train_accs.append(train_acc)
test_losses.append(test_loss)
test_accs.append(test_acc)
graph_x.append(i)
print("iteration:", i)
print("Test accuracy:", test_accs[-1])
print("Test loss:", test_losses[-1])
plt.figure()
plt.subplot(1, 2, 1)
plt.plot(graph_x, train_losses, label="train loss")
plt.plot(graph_x, test_losses, label="test loss")
plt.title('Losses')
plt.legend()
plt.subplot(1, 2, 2)
plt.plot(graph_x, train_accs, label="train acc")
plt.plot(graph_x, test_accs, label="test acc")
plt.title('Accuracies')
plt.legend()
print("Final test accuracy:", test_accs[-1])
print("Final test loss:", test_losses[-1])
plt.savefig("conv_acc_and_loss.png")
with open('conv_acc_and_loss.txt', 'w') as f:
f.write("test_losses \n")
f.write(str(test_losses) + "\n \n")
f.write("test accs \n")
f.write(str(test_accs))