【发布时间】：2020-02-28 04:53:38
【问题描述】：
我正在使用 Pytorch 为一项任务做一个 CNN，但它不会学习和提高准确性。我制作了一个使用 MNIST 数据集的版本，所以我可以在这里发布。我只是在寻找为什么它不起作用的答案。架构很好，我在 Keras 中实现了它，并且在 3 个 epoch 后我的准确率超过了 92%。注意：我将 MNIST 重新整形为 60x60 图片，因为这就是图片在我的“真实”问题中的样子。
import numpy as np
from PIL import Image
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import DataLoader
from torch.autograd import Variable
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
def resize(pics):
pictures = []
for image in pics:
image = Image.fromarray(image).resize((dim, dim))
image = np.array(image)
pictures.append(image)
return np.array(pictures)
dim = 60
x_train, x_test = resize(x_train), resize(x_test) # because my real problem is in 60x60
x_train = x_train.reshape(-1, 1, dim, dim).astype('float32') / 255
x_test = x_test.reshape(-1, 1, dim, dim).astype('float32') / 255
y_train, y_test = y_train.astype('float32'), y_test.astype('float32')
if torch.cuda.is_available():
x_train = torch.from_numpy(x_train)[:10_000]
x_test = torch.from_numpy(x_test)[:4_000]
y_train = torch.from_numpy(y_train)[:10_000]
y_test = torch.from_numpy(y_test)[:4_000]
class ConvNet(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1, 32, 3)
self.conv2 = nn.Conv2d(32, 64, 3)
self.conv3 = nn.Conv2d(64, 128, 3)
self.fc1 = nn.Linear(5*5*128, 1024)
self.fc2 = nn.Linear(1024, 2048)
self.fc3 = nn.Linear(2048, 1)
def forward(self, x):
x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
x = F.max_pool2d(F.relu(self.conv2(x)), (2, 2))
x = F.max_pool2d(F.relu(self.conv3(x)), (2, 2))
x = x.view(x.size(0), -1)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.dropout(x, 0.5)
x = torch.sigmoid(self.fc3(x))
return x
net = ConvNet()
optimizer = optim.Adam(net.parameters(), lr=0.03)
loss_function = nn.BCELoss()
class FaceTrain:
def __init__(self):
self.len = x_train.shape[0]
self.x_train = x_train
self.y_train = y_train
def __getitem__(self, index):
return x_train[index], y_train[index].unsqueeze(0)
def __len__(self):
return self.len
class FaceTest:
def __init__(self):
self.len = x_test.shape[0]
self.x_test = x_test
self.y_test = y_test
def __getitem__(self, index):
return x_test[index], y_test[index].unsqueeze(0)
def __len__(self):
return self.len
train = FaceTrain()
test = FaceTest()
train_loader = DataLoader(dataset=train, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test, batch_size=64, shuffle=True)
epochs = 10
steps = 0
train_losses, test_losses = [], []
for e in range(epochs):
running_loss = 0
for images, labels in train_loader:
optimizer.zero_grad()
log_ps = net(images)
loss = loss_function(log_ps, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
else:
test_loss = 0
accuracy = 0
with torch.no_grad():
for images, labels in test_loader:
log_ps = net(images)
test_loss += loss_function(log_ps, labels)
ps = torch.exp(log_ps)
top_p, top_class = ps.topk(1, dim=1)
equals = top_class.type('torch.LongTensor') == labels.type(torch.LongTensor).view(*top_class.shape)
accuracy += torch.mean(equals.type('torch.FloatTensor'))
train_losses.append(running_loss/len(train_loader))
test_losses.append(test_loss/len(test_loader))
print("[Epoch: {}/{}] ".format(e+1, epochs),
"[Training Loss: {:.3f}] ".format(running_loss/len(train_loader)),
"[Test Loss: {:.3f}] ".format(test_loss/len(test_loader)),
"[Test Accuracy: {:.3f}]".format(accuracy/len(test_loader)))
【问题讨论】：
-
comp.ai.neural-netsFAQs 有一些很棒的建议，如果你的神经网络没有学习，应该去哪里看；我建议从那里开始。 -
损失函数、网络的输出形状和目标标签在这里没有意义（至少这种组合是错误的）。 MNIST 有 10 个类，标签是 0 到 9 之间的整数。BCELoss 期望每个目标有一个 0 到 1 之间的单个值。您应该改为输出 10 个 logits（不一定是 sigmoided），然后使用
nn.CrossEntropyLoss处理单类分类问题。nn.CrossEntropyLoss将 softmax 和 NLLLoss 作为单个操作应用，所以不要先使用 softmax。 -
或者，如果你想做一个回归问题，即估计一个实际数字作为输出（不推荐用于分类类型问题），那么你可以尝试
nn.MSELoss，但是你要么需要调整目标，所以它们落在 sigmoid 输出的范围内，或者在最后一层之后不应用 sigmoid。 -
你有没有让它这样工作？现在它告诉我
RuntimeError: multi-target not supported。 -
你需要压缩标签的维度（它应该是批量大小的整数的一维张量）
标签： python conv-neural-network pytorch