Question

我正在训练keras中的多标签分类器，我想将其转换为pytorch，我对如何处理损失感到困惑，这就是代码的样子

model = keras.applications.densenet.DenseNet121(include_top=False, input_shape=(224, 224, 3))
x = model.output
x = Flatten()(x)
x = Dense(512)(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
output1 = Dense(1, activation = 'sigmoid')(x)
output2 = Dense(1, activation = 'sigmoid')(x)
output3 = Dense(1, activation = 'sigmoid')(x)
output4 = Dense(1, activation = 'sigmoid')(x)
output5 = Dense(1, activation = 'sigmoid')(x)
output6 = Dense(1, activation = 'sigmoid')(x)
output7 = Dense(1, activation = 'sigmoid')(x)
output8 = Dense(1, activation = 'sigmoid')(x)
model = Model(model.inputs,[output1,output2,output3,output4,output5, output6, output7, output8])
# print(model.summary())
model.compile(optimizers.rmsprop(lr = 0.0001, decay = 1e-6),
loss = ["binary_crossentropy","binary_crossentropy","binary_crossentropy","binary_crossentropy", "binary_crossentropy","binary_crossentropy","binary_crossentropy","binary_crossentropy"],metrics = ["accuracy"])

我该如何在pytorch中执行此操作，这是我到目前为止所拥有的

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(2304, 256)
        self.fc2 = nn.Linear(256, 8)

    def forward(self, x):

        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(x.size(0), -1) # Flatten layer
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.sigmoid(x)

model = Net().cuda() 
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)



def train(epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        # data, target = data.cuda(async=True), target.cuda(async=True) # On GPU

        data, target = Variable(data).cuda(), Variable(target).float().cuda()
        optimizer.zero_grad()
        output = model(data)

        loss = F.binary_cross_entropy(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 10 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))


for epoch in range(1, 10):
    train(epoch)

在此先感谢您的任何建议

从keras转换为pytorch

0 个答案: