Question

我正在尝试对通过Imagenet权重预训练的ResNet50模型进行PASCAL VOC 2012数据集的迁移学习。由于它是一个多标签数据集，因此我在最后一层使用了sigmoid激活函数，并且损失了binary_crossentropy。指标为precision,recall and accuracy。下面是我用来为20个类构建模型的代码（PASCAL VOC有20个类）。

img_height,img_width = 128,128
num_classes = 20
#If imagenet weights are being loaded,
#input must have a static square shape (one of (128, 128), (160, 160), (192, 192), or (224, 224))
base_model = applications.resnet50.ResNet50(weights= 'imagenet', include_top=False, input_shape= (img_height,img_width,3))
x = base_model.output
x = GlobalAveragePooling2D()(x)
#x = Dropout(0.7)(x)
predictions = Dense(num_classes, activation= 'sigmoid')(x)
model = Model(inputs = base_model.input, outputs = predictions)
for layer in model.layers[-2:]:
        layer.trainable=True
for layer in model.layers[:-3]:
        layer.trainable=False

adam = Adam(lr=0.0001)
model.compile(optimizer= adam, loss='binary_crossentropy', metrics=['accuracy',precision_m,recall_m])
#print(model.summary())

X_train, X_test, Y_train, Y_test = train_test_split(x_train, y, random_state=42, test_size=0.2)
savingcheckpoint = ModelCheckpoint('ResnetTL.h5',monitor='val_loss',verbose=1,save_best_only=True,mode='min')
earlystopcheckpoint = EarlyStopping(monitor='val_loss',patience=10,verbose=1,mode='min',restore_best_weights=True)
model.fit(X_train, Y_train, epochs=epochs, validation_data=(X_test,Y_test), batch_size=batch_size,callbacks=[savingcheckpoint,earlystopcheckpoint],shuffle=True)
model.save_weights('ResnetTLweights.h5')

它运行了35个时期，直到提前停止，指标如下（没有Dropout层）：

loss: 0.1195 - accuracy: 0.9551 - precision_m: 0.8200 - recall_m: 0.5420 - val_loss: 0.3535 - val_accuracy: 0.8358 - val_precision_m: 0.0583 - val_recall_m: 0.0757

即使是Dropout层，我也看不出太大差别。

loss: 0.1584 - accuracy: 0.9428 - precision_m: 0.7212 - recall_m: 0.4333 - val_loss: 0.3508 - val_accuracy: 0.8783 - val_precision_m: 0.0595 - val_recall_m: 0.0403

在辍学的情况下，经过几个时期，模型的验证精度和准确度达到了0.2，但没有高于此。

我看到，与有和没有辍学层的训练集相比，验证集的准确性和召回率都非常低。我该怎么解释？这是否意味着模型过度拟合。如果是这样，我该怎么办？到目前为止，模型预测是相当随机的（完全错误）。数据集大小为11000张图像。

Answer 1

请您可以如下修改代码并尝试执行

发件人：

predictions = Dense(num_classes, activation= 'sigmoid')(x)

收件人：

predictions = Dense(num_classes, activation= 'softmax')(x)

发件人：

model.compile(optimizer= adam, loss='binary_crossentropy', metrics=['accuracy',precision_m,recall_m])

收件人：

model.compile(optimizer= adam, loss='categorical_crossentropy', metrics=['accuracy',precision_m,recall_m])

ResNet50模型无法在keras中进行迁移学习

1 个答案: