Question

现在好几天，我试图用pytorch复制我的keras训练结果。无论我做什么，pytorch模型都会在keras中过早地设置到更强的验证集。对于pytorch，我使用https://github.com/Cadene/pretrained-models.pytorch中的相同XCeption代码。

数据加载，扩充，验证，培训计划等等。我错过了一些明显的东西吗某处肯定存在普遍问题。我尝试了数千个不同的模块星座，但似乎没有任何东西接近keras训练。有人可以帮忙吗？

Keras模型：val精度＆gt; 90％

# base model
base_model = applications.Xception(weights='imagenet', include_top=False, input_shape=(img_width, img_height, 3))

# top model
x = base_model.output
x = GlobalMaxPooling2D()(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
predictions = Dense(4, activation='softmax')(x)

# this is the model we will train
model = Model(inputs=base_model.input, outputs=predictions)

# Compile model
from keras import optimizers
adam = optimizers.Adam(lr=0.0001)
model.compile(loss='categorical_crossentropy', 
optimizer=adam, metrics=['accuracy'])

# LROnPlateau etc. with equivalent settings as pytorch

Pytorch模型：val精度~81％

from xception import xception
import torch.nn.functional as F

# modified from https://github.com/Cadene/pretrained-models.pytorch
class XCeption(nn.Module):
    def __init__(self, num_classes):
        super(XCeption, self).__init__()

        original_model = xception(pretrained="imagenet")

        self.features=nn.Sequential(*list(original_model.children())[:-1])
        self.last_linear = nn.Sequential(
             nn.Linear(original_model.last_linear.in_features, 512),
             nn.ReLU(),
             nn.Dropout(p=0.5),
             nn.Linear(512, num_classes)
        )

    def logits(self, features):
        x = F.relu(features)
        x = F.adaptive_max_pool2d(x, (1, 1))
        x = x.view(x.size(0), -1)
        x = self.last_linear(x)
        return x

    def forward(self, input):
        x = self.features(input)
        x = self.logits(x)
        return x 

device = torch.device("cuda")
model=XCeption(len(class_names))
if torch.cuda.device_count() > 1:
    print("Let's use", torch.cuda.device_count(), "GPUs!")
    # dim = 0 [30, xxx] -> [10, ...], [10, ...], [10, ...] on 3 GPUs
    model = nn.DataParallel(model)
model.to(device)

criterion = nn.CrossEntropyLoss(size_average=False)
optimizer = optim.Adam(model.parameters(), lr=0.0001)
scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, 'min', factor=0.2, patience=5, cooldown=5)

非常感谢！

更新：设定：

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=lr)
scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, 'min', factor=0.2, patience=5, cooldown=5)

model = train_model(model, train_loader, val_loader, 
                        criterion, optimizer, scheduler, 
                        batch_size, trainmult=8, valmult=10, 
                        num_epochs=200, epochs_top=0)

清理培训功能：

def train_model(model, train_loader, val_loader, criterion, optimizer, scheduler, batch_size, trainmult=1, valmult=1, num_epochs=None, epochs_top=0):
  for epoch in range(num_epochs):                        
    for phase in ['train', 'val']:
        running_loss = 0.0
        running_acc = 0
        total = 0
        # Iterate over data.
        if phase=="train":
            model.train(True)  # Set model to training mode
            for i in range(trainmult):
                for data in train_loader:
                    # get the inputs
                    inputs, labels = data
                    inputs, labels = inputs.to(torch.device("cuda")), labels.to(torch.device("cuda"))
                    # zero the parameter gradients
                    optimizer.zero_grad()
                    # forward
                    outputs = model(inputs) # notinception
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)
                    # backward + optimize only if in training phase
                    loss.backward()
                    optimizer.step()
                    # statistics                      
                    total += labels.size(0)
                    running_loss += loss.item()*labels.size(0)
                    running_acc += torch.sum(preds == labels)
                    train_loss=(running_loss/total)
                    train_acc=(running_acc.double()/total)
    else:
        model.train(False)  # Set model to evaluate mode
        with torch.no_grad():
            for i in range(valmult):
                for data in val_loader:
                    # get the inputs
                    inputs, labels = data
                    inputs, labels = inputs.to(torch.device("cuda")), labels.to(torch.device("cuda"))
                    # zero the parameter gradients
                    optimizer.zero_grad()
                    # forward
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels.data)
                    # statistics
                    total += labels.size(0)
                    running_loss += loss.item()*labels.size(0)
                    running_acc += torch.sum(preds == labels)
                    val_loss=(running_loss/total)
                    val_acc=(running_acc.double()/total)  
        scheduler.step(val_loss)
return model

Answer 1

这可能是因为您使用的重量初始化类型否则就不会发生在两个模型中尝试使用相同的初始化程序

Answer 2

self.features=nn.Sequential(*list(original_model.children())[:-1])

您确定此行以完全相同的方式重新实例化模型吗？您使用的是NN.Sequential，而不是原始XCeption模型的前向功能。如果该前向函数中有任何与使用nn.Sequential完全不同的东西，它将无法再现相同的性能。

您可以更改此顺序，而不是将其包装在顺序中

my_model = Xception()
# load weights before you change the architecture
my_model = load_weights(path_to_weights)
# overwrite the original's last_linear with your own
my_model.last_linear = nn.Sequential(
             nn.Linear(original_model.last_linear.in_features, 512),
             nn.ReLU(),
             nn.Dropout(p=0.5),
             nn.Linear(512, num_classes)
        )

Pytorch vs. Keras：Pytorch模型严重过度

2 个答案: