英文:
How to use K-Fold cross validation with DenseNet121 model
问题
我正在使用预训练模型DensetNet121来对乳腺癌图像进行分类。我将数据集分为训练、测试和验证集。我想要应用k-fold交叉验证。我使用了sklearn库中的cross_validation，但在运行代码时出现了以下错误。我尝试解决它，但没有成功。有人知道如何解决吗？
错误信息：
TypeError: 无法克隆对象'<keras.engine.functional.Functional object at 0x000001F82E17E3A0>'（类型<class 'keras.engine.functional.Functional'>）：它似乎不是scikit-learn估计器，因为它没有实现'get_params'方法。
英文:
I am working on classification of images breast cancer using DensetNet121 pretrained model. I split the dataset into training, testing and validation. I want to apply k-fold cross validation. I used cross_validation from sklearn library, but I get the below error when I run the code. I tried to solve it but nothing solved the error. Anyone have idea how to solve this.
in_model = tf.keras.applications.DenseNet121(input_shape=(224,224,3),include_top=False,weights='imagenet',classes = 2)in_model.trainable = Falseinputs = tf.keras.Input(shape=(224,224,3))x = in_model(inputs)flat = Flatten()(x)dense_1 = Dense(1024,activation = 'relu')(flat)dense_2 = Dense(1024,activation = 'relu')(dense_1)prediction = Dense(2,activation = 'softmax')(dense_2)in_pred = Model(inputs = inputs,outputs = prediction)validation_data=(valid_data,valid_labels)#16in_pred.summary()in_pred.compile(optimizer = tf.keras.optimizers.Adagrad(learning_rate=0.0002), loss=tf.keras.losses.CategoricalCrossentropy(from_logits = False), metrics=['accuracy'])history=in_pred.fit(train_data,train_labels,epochs = 3,batch_size=32,validation_data=validation_data)model_result=cross_validation(in_pred, train_data, train_labels, 5)
The error:
TypeError: Cannot clone object '<keras.engine.functional.Functional object at 0x000001F82E17E3A0>'(type <class 'keras.engine.functional.Functional'>):it does not seem to be a scikit-learn estimator as it does not implement a 'get_params' method.
答案1
得分: 2
因为您的模型不是 scikit-learn 估计器，所以您将无法使用 sklearn 内置的 cross_validate 方法。
但是，您可以使用 k-fold 来将数据分成 k 个折叠，并获取每个折叠的度量。您也可以在这里使用 TF 的内置 model.evaluate，或者 sklearn 的度量。
from sklearn.model_selection import KFoldin_model = tf.keras.applications.DenseNet121(input_shape=(224, 224, 3), include_top=False, weights="imagenet", classes=2)in_model.trainable = Falseinputs = tf.keras.Input(shape=(224, 224, 3))x = in_model(inputs)flat = Flatten()(x)dense_1 = Dense(1024, activation="relu")(flat)dense_2 = Dense(1024, activation="relu")(dense_1)prediction = Dense(2, activation="softmax")(dense_2)in_pred = Model(inputs=inputs, outputs=prediction)validation_data = (valid_data, valid_labels)in_pred.summary()in_pred.compile(optimizer=tf.keras.optimizers.Adagrad(learning_rate=0.0002),loss=tf.keras.losses.CategoricalCrossentropy(from_logits=False),metrics=["accuracy"],)kf = KFold(n_splits=10)kf.get_n_splits(train_data)for i, (fold_train_index, fold_test_index) in enumerate(kf.split(train_data)):print(f"Fold {i}:")print(f" Train: index={fold_train_index}")print(f" Test: index={fold_test_index}")history = in_pred.fit(train_data[fold_train_index],train_labels[fold_train_index],epochs=3,batch_size=32,validation_data=validation_data,)in_pred.evaluate(train_data[fold_test_index], train_labels[fold_test_index])
这是您提供的代码的翻译部分。
英文:
Since your model is not a scikit-learn estimator, you won't be able to use sklearn's built-in cross_validate method.
You can, however use k-fold to split your data into k-folds and get the metrics for each fold. We can use TF's built in model.evaluate, or sklearn's metrics here, too).
from sklearn.model_selection import KFoldin_model = tf.keras.applications.DenseNet121(input_shape=(224, 224, 3), include_top=False, weights="imagenet", classes=2)in_model.trainable = Falseinputs = tf.keras.Input(shape=(224, 224, 3))x = in_model(inputs)flat = Flatten()(x)dense_1 = Dense(1024, activation="relu")(flat)dense_2 = Dense(1024, activation="relu")(dense_1)prediction = Dense(2, activation="softmax")(dense_2)in_pred = Model(inputs=inputs, outputs=prediction)validation_data = (valid_data, valid_labels)# 16in_pred.summary()in_pred.compile(optimizer=tf.keras.optimizers.Adagrad(learning_rate=0.0002),loss=tf.keras.losses.CategoricalCrossentropy(from_logits=False),metrics=["accuracy"],)kf = KFold(n_splits=10)kf.get_n_splits(train_data)for i, (fold_train_index, fold_test_index) in enumerate(kf.split(train_data)):print(f"Fold {i}:")print(f" Train: index={fold_train_index}")print(f" Test: index={fold_test_index}")history = in_pred.fit(train_data[fold_train_index],train_labels[fold_train_index],epochs=3,batch_size=32,validation_data=validation_data,)in_pred.evaluate(train_data[fold_test_index],train_labels[fold_test_index])
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论