torch训练和推理的模板
作者：互联网
def train(epoch):
model.train()
train_loss = 0
for data, label in train_loader:
data, label = data.cuda(), label.cuda() # 将数据放入显卡
optimizer.zero_grad()
output = model(data)
loss = criterion(output, label)
loss.backward()
optimizer.step()
train_loss += loss.item()*data.size(0) # loss需要取item()得到数字，才能相加
train_loss = train_loss/len(train_loader.dataset)
print('Epoch: {} \tTraining Loss: {:.6f}'.format(epoch, train_loss))
def val(epoch):
model.eval()
val_loss = 0
gt_labels = []
pred_labels = []
with torch.no_grad():
for data, label in test_loader:
data, label = data.cuda(), label.cuda()
output = model(data)
preds = torch.argmax(output, 1)
gt_labels.append(label.cpu().data.numpy()) # 将GPU中的tensor转化为numpy.array
pred_labels.append(preds.cpu().data.numpy())
loss = criterion(output, label)
val_loss += loss.item()*data.size(0)
val_loss = val_loss/len(test_loader.dataset)
gt_labels, pred_labels = np.concatenate(gt_labels), np.concatenate(pred_labels)
acc = np.sum(gt_labels==pred_labels)/len(pred_labels)
print('Epoch: {} \tValidation Loss: {:.6f}, Accuracy: {:6f}'.format(epoch, val_loss, acc))
标签：loss,torch,val,data,labels,label,train,推理,模板 来源： https://www.cnblogs.com/gagaein/p/16435856.html