training
def get_pseudo_labels(dataset, model, threshold=0.65):
# This functions generates pseudo-labels of a dataset using given model.
# It returns an instance of DatasetFolder containing images whose prediction confidences exceed a given threshold.
# You are NOT allowed to use any models trained on external data for pseudo-labeling.
device = "cuda" if torch.cuda.is_available() else "cpu"
# Construct a data loader.
data_loader = DataLoader(dataset, batch_size=batch_size, shuffle=False)
# Make sure the model is in eval mode.
model.eval() #evaluation mode
# Define softmax function.
softmax = nn.Softmax(dim=-1) #对每一行进行softmax处理
# Iterate over the dataset by batches.
for batch in tqdm(data_loader):
img, _ = batch
# Forward the data
# Using torch.no_grad() accelerates the forward process.
with torch.no_grad():
logits = model(img.to(device))
# Obtain the probability distributions by applying softmax on logits.
probs = softmax(logits)
# ---------- TODO ----------
# Filter the data and construct a new dataset.
# # Turn off the eval mode.
model.train()
return dataset
# "cuda" only when GPUs are available.
device = "cuda" if torch.cuda.is_available() else "cpu"
# Initialize a model, and put it on the device specified.
model = Classifier().to(device)
model.device = device
# For the classification task, we use cross-entropy as the measurement of performance.
criterion = nn.CrossEntropyLoss()
# Initialize optimizer, you may fine-tune some hyperparameters such as learning rate on your own.
optimizer = torch.optim.Adam(model.parameters(), lr=0.0005, weight_decay=1e-5)
# The number of training epochs.
n_epochs = 80
# Whether to do semi-supervised learning.
do_semi = False
for epoch in range(n_epochs):
# ---------- TODO ----------
# In each epoch, relabel the unlabeled dataset for semi-supervised learning.
# Then you can combine the labeled dataset and pseudo-labeled dataset for the training.
if do_semi:
# Obtain pseudo-labels for unlabeled data using trained model.
pseudo_set = get_pseudo_labels(unlabeled_set, model)
# Construct a new dataset and a data loader for training.
# This is used in semi-supervised learning only.
concat_dataset = ConcatDataset([train_set, pseudo_set])
train_loader = DataLoader(concat_dataset, batch_size=batch_size, shuffle=True, num_workers=8, pin_memory=True)
# ---------- Training ----------
# Make sure the model is in train mode before training.
model.train()
# These are used to record information in training.
train_loss = []
train_accs = []
# Iterate the training set by batches.
for batch in tqdm(train_loader):
# A batch consists of image data and corresponding labels.
imgs, labels = batch
# Forward the data. (Make sure data and model are on the same device.)
logits = model(imgs.to(device))
# Calculate the cross-entropy loss.
# We don't need to apply softmax before computing cross-entropy as it is done automatically.
loss = criterion(logits, labels.to(device))
# Gradients stored in the parameters in the previous step should be cleared out first.
optimizer.zero_grad()
# Compute the gradients for parameters.
loss.backward()
# Clip the gradient norms for stable training.
grad_norm = nn.utils.clip_grad_norm_(model.parameters(), max_norm=10)
# Update the parameters with computed gradients.
optimizer.step()
# Compute the accuracy for current batch.
acc = (logits.argmax(dim=-1) == labels.to(device)).float().mean()
# Record the loss and accuracy.
train_loss.append(loss.item())
train_accs.append(acc)
# The average loss and accuracy of the training set is the average of the recorded values.
train_loss = sum(train_loss) / len(train_loss)
train_acc = sum(train_accs) / len(train_accs)
# Print the information.
print(f"[ Train | {epoch + 1:03d}/{n_epochs:03d} ] loss = {train_loss:.5f}, acc = {train_acc:.5f}")
# ---------- Validation ----------
# Make sure the model is in eval mode so that some modules like dropout are disabled and work normally.
model.eval()
# These are used to record information in validation.
valid_loss = []
valid_accs = []
# Iterate the validation set by batches.
for batch in tqdm(valid_loader):
# A batch consists of image data and corresponding labels.
imgs, labels = batch
# We don't need gradient in validation.
# Using torch.no_grad() accelerates the forward process.
with torch.no_grad():
logits = model(imgs.to(device))
# We can still compute the loss (but not the gradient).
loss = criterion(logits, labels.to(device))
# Compute the accuracy for current batch.
acc = (logits.argmax(dim=-1) == labels.to(device)).float().mean()
# Record the loss and accuracy.
valid_loss.append(loss.item())
valid_accs.append(acc)
# The average loss and accuracy for entire validation set is the average of the recorded values.
valid_loss = sum(valid_loss) / len(valid_loss)
valid_acc = sum(valid_accs) / len(valid_accs)
# Print the information.
print(f"[ Valid | {epoch + 1:03d}/{n_epochs:03d} ] loss = {valid_loss:.5f}, acc = {valid_acc:.5f}")
testing***
# Make sure the model is in eval mode.
# Some modules like Dropout or BatchNorm affect if the model is in training mode.
model.eval()
# Initialize a list to store the predictions.
predictions = []
# Iterate the testing set by batches.
for batch in tqdm(test_loader):
# A batch consists of image data and corresponding labels.
# But here the variable "labels" is useless since we do not have the ground-truth.
# If printing out the labels, you will find that it is always 0.
# This is because the wrapper (DatasetFolder) returns images and labels for each batch,
# so we have to create fake labels to make it work normally.
imgs, labels = batch
# We don't need gradient in testing, and we don't even have labels to compute loss.
# Using torch.no_grad() accelerates the forward process.
with torch.no_grad():
logits = model(imgs.to(device))
# Take the class with greatest logit as prediction and record it.
predictions.extend(logits.argmax(dim=-1).cpu().numpy().tolist())
98行
optimizer.step()
这个操作已经更新参数了，不知道你想问啥