我正在尝试使用两个预训练模型（resnet和mobilenet）提取的特征作为输入来训练一个Keras的功能模型。我需要使用softmax层将图像分类为1、2或3类别。
我的model.fit函数返回以下错误：
ValueError: No gradients provided for any variable: ['dense_66/kernel:0', 'dense_66/bias:0', 'dense_64/kernel:0', 'dense_64/bias:0', 'dense_67/kernel:0', 'dense_67/bias:0', 'dense_65/kernel:0', 'dense_65/bias:0', 'dense_68/kernel:0', 'dense_68/bias:0', 'dense_69/kernel:0', 'dense_69/bias:0', 'dense_70/kernel:0', 'dense_70/bias:0'].这是相关代码部分：
创建数据集
def datasetgenerator(url,BATCH_SIZE,IMG_SIZE): data=image_dataset_from_directory(url, shuffle=True, batch_size=BATCH_SIZE, image_size=IMG_SIZE, label_mode='int' ) return dataBATCH_SIZE = 20IMG_SIZE = (160, 160)train_dir='wound_dataset2/train'train_dataset = datasetgenerator(url=train_dir,BATCH_SIZE=BATCH_SIZE,IMG_SIZE= IMG_SIZE)val_dir='wound_dataset2/val'validation_dataset = datasetgenerator(url=val_dir,BATCH_SIZE=BATCH_SIZE,IMG_SIZE= IMG_SIZE)test_dir='wound_dataset2/test'test_dataset = datasetgenerator(url=test_dir,BATCH_SIZE=BATCH_SIZE,IMG_SIZE= IMG_SIZE)print(train_dataset)特征提取
mobilenet_features = np.empty([20, 1280])resnet_features = np.empty([20, 2048])for data in train_dataset: image_batch, label_batch = data image_batch = data_augmentation(image_batch) preprocess_input_image_resnet = preprocess_input_resnet(image_batch) preprocess_input_image_mobilenet = preprocess_input_mobilenet(image_batch) feature_batch_resnet = base_model_resnet(preprocess_input_image_resnet) feature_batch_average_resnet = global_average_layer(feature_batch_resnet) feature_batch_mobilenet = base_model_mobilenet(preprocess_input_image_mobilenet) feature_batch_average_mobilenet = global_average_layer(feature_batch_mobilenet) mobilenet_features = np.concatenate((mobilenet_features, np.array(feature_batch_average_mobilenet))) resnet_features = np.concatenate((resnet_features, np.array(feature_batch_average_resnet)))模型生成
from tensorflow.keras.layers import concatenate# define two sets of inputsinputA = tf.keras.Input(shape=(1280,))inputB = tf.keras.Input(shape=(2048,))# the first branch operates on the first inputx = tf.keras.layers.Dense(8, activation="relu")(inputA)x = tf.keras.layers.Dense(4, activation="relu")(x)x = tf.keras.Model(inputs=inputA, outputs=x)# the second branch opreates on the second inputy = tf.keras.layers.Dense(64, activation="relu")(inputB)y = tf.keras.layers.Dense(32, activation="relu")(y)y = tf.keras.layers.Dense(4, activation="relu")(y)y = tf.keras.Model(inputs=inputB, outputs=y)# combine the output of the two branchescombined = concatenate([x.output, y.output])fc_layers = [1024, 1024]dropout = 0.5# apply a FC layer and then a regression prediction on the# combined outputsz = Flatten()(combined)for fc in fc_layers: # New FC layer, random init z = Dense(fc, activation='relu')(z) z = Dropout(dropout)(z)# New softmax layerpredictions = Dense(3, activation='softmax')(z)# our model will accept the inputs of the two branches and# then output a single valuemodel = tf.keras.Model(inputs=[x.input, y.input], outputs=z)训练
model.compile(optimizer=tf.keras.optimizers.Adam(1e-3), loss= tf.keras.losses.CategoricalCrossentropy(from_logits=True), metrics=['accuracy'])history = model.fit((mobilenet_features, resnet_features), batch_size=20, epochs=10)我正在尝试这种方法来提高我使用迁移学习所获得的准确性。任何帮助将不胜感激。
回答：
z = Flatten()(combined)z = Dense(fc, activation='relu')(z) z = Dropout(dropout)(z)z = Dense(fc, activation='relu')(z) z = Dropout(dropout)(z)predictions = Dense(3, activation='softmax')(z)# use the prediction as output layermodel = tf.keras.Model(inputs=[x.input, y.input], outputs=predictions)#add target tensor to the fit methodhistory = model.fit((mobilenet_features, resnet_features),youTarget, batch_size=20, epochs=10)