我正在研究神经网络问题，将数据分类为 1 或 0。我使用二元交叉熵损失来执行此操作。损失很好，但是准确性非常低并且没有提高。我假设我在准确度计算中犯了错误。在每个纪元之后，我都会在对输出进行阈值处理后计算正确的预测，并将该数字除以数据集的总数。我在准确率计算中做错了什么吗？为什么不但没有改善，反而变得更糟？ 这是我的代码：
net = Model()
criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(net.parameters(), lr=0.1)
num_epochs = 100
for epoch in range(num_epochs):
for i, (inputs,labels) in enumerate (train_loader):
inputs = Variable(inputs.float())
labels = Variable(labels.float())
output = net(inputs)
optimizer.zero_grad()
loss = criterion(output, labels)
loss.backward()
optimizer.step()
#Accuracy
output = (output>0.5).float()
correct = (output == labels).float().sum()
print("Epoch {}/{}, Loss: {:.3f}, Accuracy: {:.3f}".format(epoch+1,num_epochs, loss.data[0], correct/x.shape[0]))
这是我得到的奇怪输出：
Epoch 1/100, Loss: 0.389, Accuracy: 0.035
Epoch 2/100, Loss: 0.370, Accuracy: 0.036
Epoch 3/100, Loss: 0.514, Accuracy: 0.030
Epoch 4/100, Loss: 0.539, Accuracy: 0.030
Epoch 5/100, Loss: 0.583, Accuracy: 0.029
Epoch 6/100, Loss: 0.439, Accuracy: 0.031
Epoch 7/100, Loss: 0.429, Accuracy: 0.034
Epoch 8/100, Loss: 0.408, Accuracy: 0.035
Epoch 9/100, Loss: 0.316, Accuracy: 0.035
Epoch 10/100, Loss: 0.436, Accuracy: 0.035
Epoch 11/100, Loss: 0.365, Accuracy: 0.034
Epoch 12/100, Loss: 0.485, Accuracy: 0.031
Epoch 13/100, Loss: 0.392, Accuracy: 0.033
Epoch 14/100, Loss: 0.494, Accuracy: 0.030
Epoch 15/100, Loss: 0.369, Accuracy: 0.035
Epoch 16/100, Loss: 0.495, Accuracy: 0.029
Epoch 17/100, Loss: 0.415, Accuracy: 0.034
Epoch 18/100, Loss: 0.410, Accuracy: 0.035
Epoch 19/100, Loss: 0.282, Accuracy: 0.038
Epoch 20/100, Loss: 0.499, Accuracy: 0.031
Epoch 21/100, Loss: 0.446, Accuracy: 0.030
Epoch 22/100, Loss: 0.585, Accuracy: 0.026
Epoch 23/100, Loss: 0.419, Accuracy: 0.035
Epoch 24/100, Loss: 0.492, Accuracy: 0.031
Epoch 25/100, Loss: 0.537, Accuracy: 0.031
Epoch 26/100, Loss: 0.439, Accuracy: 0.033
Epoch 27/100, Loss: 0.421, Accuracy: 0.035
Epoch 28/100, Loss: 0.532, Accuracy: 0.034
Epoch 29/100, Loss: 0.234, Accuracy: 0.038
Epoch 30/100, Loss: 0.492, Accuracy: 0.027
Epoch 31/100, Loss: 0.407, Accuracy: 0.035
Epoch 32/100, Loss: 0.305, Accuracy: 0.038
Epoch 33/100, Loss: 0.663, Accuracy: 0.025
Epoch 34/100, Loss: 0.588, Accuracy: 0.031
Epoch 35/100, Loss: 0.329, Accuracy: 0.035
Epoch 36/100, Loss: 0.474, Accuracy: 0.033
Epoch 37/100, Loss: 0.535, Accuracy: 0.031
Epoch 38/100, Loss: 0.406, Accuracy: 0.033
Epoch 39/100, Loss: 0.513, Accuracy: 0.030
Epoch 40/100, Loss: 0.593, Accuracy: 0.030
Epoch 41/100, Loss: 0.265, Accuracy: 0.036
Epoch 42/100, Loss: 0.576, Accuracy: 0.031
Epoch 43/100, Loss: 0.565, Accuracy: 0.027
Epoch 44/100, Loss: 0.576, Accuracy: 0.030
Epoch 45/100, Loss: 0.396, Accuracy: 0.035
Epoch 46/100, Loss: 0.423, Accuracy: 0.034
Epoch 47/100, Loss: 0.489, Accuracy: 0.033
Epoch 48/100, Loss: 0.591, Accuracy: 0.029
Epoch 49/100, Loss: 0.415, Accuracy: 0.034
Epoch 50/100, Loss: 0.291, Accuracy: 0.039
Epoch 51/100, Loss: 0.395, Accuracy: 0.033
Epoch 52/100, Loss: 0.540, Accuracy: 0.026
Epoch 53/100, Loss: 0.436, Accuracy: 0.033
Epoch 54/100, Loss: 0.346, Accuracy: 0.036
Epoch 55/100, Loss: 0.519, Accuracy: 0.029
Epoch 56/100, Loss: 0.456, Accuracy: 0.031
Epoch 57/100, Loss: 0.425, Accuracy: 0.035
Epoch 58/100, Loss: 0.311, Accuracy: 0.039
Epoch 59/100, Loss: 0.406, Accuracy: 0.034
Epoch 60/100, Loss: 0.360, Accuracy: 0.035
Epoch 61/100, Loss: 0.476, Accuracy: 0.030
Epoch 62/100, Loss: 0.404, Accuracy: 0.034
Epoch 63/100, Loss: 0.382, Accuracy: 0.036
Epoch 64/100, Loss: 0.538, Accuracy: 0.031
Epoch 65/100, Loss: 0.392, Accuracy: 0.034
Epoch 66/100, Loss: 0.434, Accuracy: 0.033
Epoch 67/100, Loss: 0.479, Accuracy: 0.031
Epoch 68/100, Loss: 0.494, Accuracy: 0.031
Epoch 69/100, Loss: 0.415, Accuracy: 0.034
Epoch 70/100, Loss: 0.390, Accuracy: 0.036
Epoch 71/100, Loss: 0.330, Accuracy: 0.038
Epoch 72/100, Loss: 0.449, Accuracy: 0.030
Epoch 73/100, Loss: 0.315, Accuracy: 0.039
Epoch 74/100, Loss: 0.450, Accuracy: 0.031
Epoch 75/100, Loss: 0.562, Accuracy: 0.030
Epoch 76/100, Loss: 0.447, Accuracy: 0.031
Epoch 77/100, Loss: 0.408, Accuracy: 0.038
Epoch 78/100, Loss: 0.359, Accuracy: 0.034
Epoch 79/100, Loss: 0.372, Accuracy: 0.035
Epoch 80/100, Loss: 0.452, Accuracy: 0.034
Epoch 81/100, Loss: 0.360, Accuracy: 0.035
Epoch 82/100, Loss: 0.453, Accuracy: 0.031
Epoch 83/100, Loss: 0.578, Accuracy: 0.030
Epoch 84/100, Loss: 0.537, Accuracy: 0.030
Epoch 85/100, Loss: 0.483, Accuracy: 0.035
Epoch 86/100, Loss: 0.343, Accuracy: 0.036
Epoch 87/100, Loss: 0.439, Accuracy: 0.034
Epoch 88/100, Loss: 0.686, Accuracy: 0.023
Epoch 89/100, Loss: 0.265, Accuracy: 0.039
Epoch 90/100, Loss: 0.369, Accuracy: 0.035
Epoch 91/100, Loss: 0.521, Accuracy: 0.027
Epoch 92/100, Loss: 0.662, Accuracy: 0.027
Epoch 93/100, Loss: 0.581, Accuracy: 0.029
Epoch 94/100, Loss: 0.322, Accuracy: 0.034
Epoch 95/100, Loss: 0.375, Accuracy: 0.035
Epoch 96/100, Loss: 0.575, Accuracy: 0.031
Epoch 97/100, Loss: 0.489, Accuracy: 0.030
Epoch 98/100, Loss: 0.435, Accuracy: 0.033
Epoch 99/100, Loss: 0.440, Accuracy: 0.031
Epoch 100/100, Loss: 0.444, Accuracy: 0.033
更好的方法是在优化步骤之后立即计算正确
for epoch in range(num_epochs):
correct = 0
for i, (inputs,labels) in enumerate (train_loader):
...
output = net(inputs)
...
optimizer.step()
correct += (output == labels).float().sum()
accuracy = 100 * correct / len(trainset)
# trainset, not train_loader
# probably x in your case
print("Accuracy = {}".format(accuracy))
xcorrect/x.shape[0]correct/output.shape[0]只需阅读这个答案：
https://stackoverflow.com/a/63271002/1601580
我认为最简单的答案是来自 cifar10 教程：
total = 0
with torch.no_grad():
net.eval()
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))
所以：
acc = (true == pred).sum().item()
如果您有计数器，请不要忘记最终除以数据集或类似值的大小。
我用过：
N = data.size(0) # since usually it's size (batch_size, D1, D2, ...)
correct += (1/N) * correct
自包含代码：
# testing accuracy function
# https://discuss.pytorch.org/t/calculating-accuracy-of-the-current-minibatch/4308/11
# https://stackoverflow.com/questions/51503851/calculate-the-accuracy-every-epoch-in-pytorch
import torch
import torch.nn as nn
D = 1
true = torch.tensor([0,1,0,1,1]).reshape(5,1)
print(f'true.size() = {true.size()}')
batch_size = true.size(0)
print(f'batch_size = {batch_size}')
x = torch.randn(batch_size,D)
print(f'x = {x}')
print(f'x.size() = {x.size()}')
mdl = nn.Linear(D,1)
logit = mdl(x)
_, pred = torch.max(logit.data, 1)
print(f'logit = {logit}')
print(f'pred = {pred}')
print(f'true = {true}')
acc = (true == pred).sum().item()
print(f'acc = {acc}')
另外，我发现这段代码是很好的参考：
def calc_accuracy(mdl, X, Y):
# reduce/collapse the classification dimension according to max op
# resulting in most likely label
max_vals, max_indices = mdl(X).max(1)
# assumes the first dimension is batch size
n = max_indices.size(0) # index 0 for extracting the # of elements
# calulate acc (note .item() to do float division)
acc = (max_indices == Y).sum().item() / n
return acc
解释
pred = mdl(x).max(1)最主要的是，您必须减少/折叠分类原始值/logit 具有最大值的维度，然后使用
.indices1[batch_size,D_classification][batch_size,C,H,W]一维原始数据的综合示例如下：
import torch
import torch.nn as nn
# data dimension [batch-size, D]
D, Dout = 1, 5
batch_size = 16
x = torch.randn(batch_size, D)
y = torch.randint(low=0,high=Dout,size=(batch_size,))
mdl = nn.Linear(D, Dout)
logits = mdl(x)
print(f'y.size() = {y.size()}')
# removes the 1th dimension with a max, which is the classification layer
# which means it returns the most likely label. Also, note you need to choose .indices since you want to return the
# position of where the most likely label is (not it's raw logit value)
pred = logits.max(1).indices
print(pred)
print('--- preds vs truth ---')
print(f'predictions = {pred}')
print(f'y = {y}')
acc = (pred == y).sum().item() / pred.size(0)
print(acc)
输出：
y.size() = torch.Size([16])
tensor([3, 1, 1, 3, 4, 1, 4, 3, 1, 1, 4, 4, 4, 4, 3, 1])
--- preds vs truth ---
predictions = tensor([3, 1, 1, 3, 4, 1, 4, 3, 1, 1, 4, 4, 4, 4, 3, 1])
y = tensor([3, 3, 3, 0, 3, 4, 0, 1, 1, 2, 1, 4, 4, 2, 0, 0])
0.25
参考：
这是我的解决方案：
def evaluate(model, validation_loader, use_cuda=True):
model.eval()
with torch.no_grad():
acc = .0
for i, data in enumerate(validation_loader):
X = data[0]
y = data[1]
if use_cuda:
X = X.cuda()
y = y.cuda()
predicted = model(X)
acc+=(predicted.round() == y).sum()/float(predicted.shape[0])
model.train()
return (acc/(i+1)).detach().item()
注 1： 在验证时将模型设置为 eval 模式，然后返回到 train 模式。
注2：我不确定是否需要禁用
autogradcorrect = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))
让我们看看基础知识：
Accuracy = Total Correct Observations / Total Observations
在您的代码中，当您计算准确性时，您将一个时期内的总正确观测值除以不正确的总观测值
correct/x.shape[0]
相反，您应该将其除以每个时期的观察数量，即批量大小。假设你的批量大小=batch_size
Solution 1. Accuracy = correct/batch_size
Solution 2. Accuracy = correct/len(labels)
Solution 3. Accuracy = correct/len(input)
理想情况下，在每个时期，批量大小、输入长度（行数）和标签长度应该相同。
在这里检查这些定义：
def train(model, train_loader):
model.train()
train_acc, correct_train, train_loss, target_count = 0, 0, 0, 0
for i, (input, target) in enumerate(train_loader):
target = target.cuda()
input_var = Variable(input)
target_var = Variable(target)
optimizer.zero_grad()
output = model(input_var)
loss = criterion(output, target_var)
loss.backward()
optimizer.step()
# accuracy
_, predicted = torch.max(output.data, 1)
target_count += target_var.size(0)
correct_train += (target_var == predicted).sum().item()
train_acc = (100 * correct_train) / target_count
return train_acc, train_loss / target_count
def validate(model, val_loader):
model.eval()
val_acc, correct_val, val_loss, target_count = 0, 0, 0, 0
for i, (input, target) in enumerate(val_loader):
target = target.cuda()
input_var = Variable(input, volatile=True)
target_var = Variable(target, volatile=True)
output = model(input_var)
loss = criterion(output, target_var)
val_loss += loss.item()
# accuracy
_, predicted = torch.max(output.data, 1)
target_count += target_var.size(0)
correct_val += (target_var == predicted).sum().item()
val_acc = 100 * correct_val / target_count
return (val_acc * 100) / target_count, val_loss / target_count
for epoch in range(0, n_epoch):
train_acc, train_loss = train(model, train_loader)
val_loss = validate(model, val_loader)
print("Epoch {0}: train_acc {1} \t train_loss {2} \t val_acc {3} \t val_loss {4}".format(epoch, train_acc, train_loss, val_acc, val_loss))
一根衬管即可获得准确性
acc == (true == mdl(x).max(1).item() / true.size(0)
假设第 0 维是批量大小，第 1 维保存分类标签的 logits/原始值。
更多详情：
def calc_error(mdl: torch.nn.Module, X: torch.Tensor, Y):
# acc == (true != mdl(x).max(1).item() / true.size(0)
train_acc = calc_accuracy(mdl, X, Y)
train_err = 1.0 - train_acc
return train_err
def calc_accuracy(mdl: torch.nn.Module, X: torch.Tensor, Y: torch.Tensor) -> float:
"""
Get the accuracy with respect to the most likely label
:param mdl:
:param X:
:param Y:
:return:
"""
# get the scores for each class (or logits)
y_logits = mdl(X) # unnormalized probs
# return the values & indices with the largest value in the dimension where the scores for each class is
# get the scores with largest values & their corresponding idx (so the class that is most likely)
max_scores, max_idx_class = mdl(X).max(dim=1) # [B, n_classes] -> [B], # get values & indices with the max vals in the dim with scores for each class/label
# usually 0th coordinate is batch size
n = X.size(0)
assert( n == max_idx_class.size(0))
# calulate acc (note .item() to do float division)
acc = (max_idx_class == Y).sum().item() / n
return acc
只需阅读这个答案：
以下是以自包含代码为例的分步说明：
#%%
# refs:
# https://stackoverflow.com/questions/51503851/calculate-the-accuracy-every-epoch-in-pytorch
# https://discuss.pytorch.org/t/how-to-calculate-accuracy-in-pytorch/80476/5
# https://discuss.pytorch.org/t/how-does-one-get-the-predicted-classification-label-from-a-pytorch-model/91649
# how to get the class prediction
batch_size = 4
n_classes = 2
y_logits = torch.randn(batch_size, n_classes) # usually the scores
print('scores (logits) for each class for each example in batch (how likely a class is unnormalized)')
print(y_logits)
print('the max over entire tensor (not usually what we want)')
print(y_logits.max())
print('the max over the n_classes dim. For each example in batch returns: '
'1) the highest score for each class (most likely class)\n, and '
'2) the idx (=class) with that highest score')
print(y_logits.max(1))
print('-- calculate accuracy --')
# computing accuracy in pytorch
"""
random.choice(a, size=None, replace=True, p=None)
Generates a random sample from a given 1-D array
for pytorch random choice https://stackoverflow.com/questions/59461811/random-choice-with-pytorch
"""
import torch
import torch.nn as nn
in_features = 1
n_classes = 10
batch_size = n_classes
mdl = nn.Linear(in_features=in_features, out_features=n_classes)
x = torch.randn(batch_size, in_features)
y_logits = mdl(x) # scores/logits for each example in batch [B, n_classes]
# get for each example in batch the label/idx most likely according to score
# y_max_idx[b] = y_pred[b] = argmax_{idx \in [n_classes]} y_logit[idx]
y_max_scores, y_max_idx = y_logits.max(dim=1)
y_pred = y_max_idx # predictions are really the inx \in [n_classes] with the highest scores
y = torch.randint(high=n_classes, size=(batch_size,))
# accuracy for 1 batch
assert (y.size(0) == batch_size)
acc = (y == y_pred).sum() / y.size(0)
acc = acc.item()
print(y)
print(y_pred)
print(acc)
输出：
scores (logits) for each class for each example in batch (how likely a class is unnormalized)
tensor([[ 0.4912, 1.5143],
[ 1.2378, 0.3172],
[-1.0164, -1.2786],
[-1.6685, -0.6693]])
the max over entire tensor (not usually what we want)
tensor(1.5143)
the max over the n_classes dim. For each example in batch returns: 1) the highest score for each class (most likely class)
, and 2) the idx (=class) with that highest score
torch.return_types.max(
values=tensor([ 1.5143, 1.2378, -1.0164, -0.6693]),
indices=tensor([1, 0, 0, 1]))
-- calculate accuracy --
tensor([6, 1, 3, 5, 3, 9, 6, 5, 6, 6])
tensor([5, 5, 5, 5, 5, 7, 7, 5, 5, 7])
0.20000000298023224
如果您需要这样的输出
2022-08-08 12:26:48,472 Epoch [20/20], Step [144/148], Loss: 0.1878 Accuracy: 92.1875
2022-08-08 12:26:48,597 Epoch [20/20], Step [145/148], Loss: 0.1052 Accuracy: 96.8750
2022-08-08 12:26:48,723 Epoch [20/20], Step [146/148], Loss: 0.2459 Accuracy: 90.6250
2022-08-08 12:26:48,848 Epoch [20/20], Step [147/148], Loss: 0.1617 Accuracy: 95.3125
2022-08-08 12:26:48,970 Epoch [20/20], Step [148/148], Loss: 0.1481 Accuracy: 95.0820
2022-08-08 12:26:49,055 --->Epoch [20/20], Average Loss: 0.1596 Average Accuracy: 94.3924
Accuracy of the network on the 3925 test images: 69.98726114649682 %
Accuracy of the network on the 9469 Train images: 94.31830182701447 %
alex@pop-os:~/coding/cnn_2$
代码如下 -
# loop over our epochs
for epoch in range(0, num_epochs):
# set the model in training mode
model.train()
# initialize the total training and validation loss
totalTrainLoss = 0
totalValLoss = 0
# initialize the number of correct predictions in the training
# and validation step
trainAccuracy = 0
totalTrainAccuracy = 0
valCorrect = 0
# loop over the training set
for i, (images, labels) in enumerate(train_loader):
# send the input to the device
(images, labels) = (images.to(device), labels.to(device))
# perform a forward pass and calculate the training loss
outputs = model(images)
loss = lossFn(outputs, labels)
# zero out the gradients, perform the backpropagation step,
# and update the weights
opt.zero_grad()
loss.backward()
totalTrainLoss += loss
opt.step()
# Get the predicted values
_, predicted = torch.max(outputs.data, 1)
trainAccuracy = (predicted == labels).float().sum().item()
trainAccuracy = 100 * trainAccuracy / labels.size(0)
totalTrainAccuracy += trainAccuracy
# if (i // stepsize) % 10 == 0:
log.info(
"Epoch [{}/{}], Step [{}/{}], Loss: {:.4f} Accuracy: {:.4f}".format(
epoch + 1, num_epochs, i + 1, total_step, loss, trainAccuracy
)
)
avgTrainLoss = totalTrainLoss / len(train_loader)
avgAccuracy = totalTrainAccuracy / len(train_loader)
log.info(
"--->Epoch [{}/{}], Average Loss: {:.4f} Average Accuracy: {:.4f}".format(
epoch + 1, num_epochs, avgTrainLoss, avgAccuracy
)
)
要验证，代码如下
with torch.no_grad():
model.eval()
correct = 0
total = 0
for images, labels in test_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).float().sum().item()
print(
"Accuracy of the network on the {} test images: {} %".format(
total, 100 * correct / total
)
)
correct = 0
total = 0
for images, labels in train_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).float().sum().item()
print(
"Accuracy of the network on the {} Train images: {} %".format(
total, 100 * correct / total
)
)
完整代码在这里https://github.com/alexcpn/cnn_lenet_pytorch/blob/main/cnn/test4_cnn_imagenet_small.py
您可以使用 TorchMetrics 库中的 ACCURACY。
from torchmetrics import Accuracy
accuracy = Accuracy()
accuracy(output, labels)
以下解决方案适用于二元分类，并考虑了一些现实生活中的问题：
它使用
torch.mean()pred = torch.tensor([0.99, 0.78, 0.65, 0.21, 0.13, 0.09])
y = torch.tensor([1., 1., 0., 0., 1., 0.])
inaccuracy = torch.mean(torch.round(torch.abs(pred - y)))
accuracy = 1.0 - inaccuracy.item()
accuracy
这将打印 0.666。