模型没有 "形状 "属性 - VGG16模型

Question

我想用 VGG16 模型来对RAVDESS视频_歌曲数据集进行分类。为了做到这一点，我从每个视频中每秒提取3帧。然后，我使用InceptionV3从这些帧中提取特征，将其保存到csv文件中。现在，我试图训练一个模型，根据给定的输入来预测情绪。

我使用的是 train_test_split 来将我的数据分成随机的训练和测试子集。

p_x_train, p_x_test, p_y_train, p_y_test = train_test_split(deep_features_csv, emotion_classes_csv, test_size=.3, random_state=42, stratify=emotion_classes_csv)

x_train = preprocess_input(p_x_train.values)
x_test = preprocess_input(p_x_test.values)
y_train = preprocess_input(p_y_train.values)
y_test = preprocess_input(p_y_test.values)

在这之后，我建立了我的模型，在这种情况下是VGG16，并尝试着去适应它。

emotions = { 0: "neutral", 1: "calm", 2: "happy", 3: "sad", 4: "angry", 5: "fearful" }

num_classes = len(emotions)

input_tensor = Input(shape=x_train[0].shape, name='input_tensor')

vgg16 = VGG16(weights='imagenet', include_top=False)
vgg16.trainable = False

x = tf.keras.layers.Flatten(name='flatten')(vgg16)
x = tf.keras.layers.Dense(512, activation='relu', name='fc1')(vgg16)
x = tf.keras.layers.Dense(512, activation='relu', name='fc2')(x)
x = tf.keras.layers.Dense(10, activation='softmax', name='predictions')(x)
new_model = tf.keras.models.Model(inputs=vgg16.input, outputs=x)
new_model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

hist_vgg16 = new_model.fit(x_train, y_train,
    batch_size = 32,
    epochs = 50,
    verbose = 1,
    validation_data = (x_test, y_test)
)

这个模型的形状 x_train[0] 是 (2048,).

我在(google colab)[colab.research.google.com]上运行这个代码，这就是我得到的错误。

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-30-311ade600318> in <module>()
      8 vgg16.trainable = False
      9 
---> 10 x = tf.keras.layers.Flatten(name='flatten')(vgg16)
     11 x = tf.keras.layers.Dense(512, activation='relu', name='fc1')(vgg16)
     12 x = tf.keras.layers.Dense(512, activation='relu', name='fc2')(x)

2 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    164         spec.min_ndim is not None or
    165         spec.max_ndim is not None):
--> 166       if x.shape.ndims is None:
    167         raise ValueError('Input ' + str(input_index) + ' of layer ' +
    168                          layer_name + ' is incompatible with the layer: '

AttributeError: 'Model' object has no attribute 'shape'

谁能帮帮我？

Answer 1

问题是在错误行中，你引入了VGG16模型作为输入，而你想要的是引入最后一层的输出，对吗？

所以，你应该修改下一行。

x = tf.keras.layers.Flatten(name='flatten')(vgg16.output) 
x = tf.keras.layers.Dense(512, activation='relu', name='fc1')(x) #I suppose the input of this layer, is the output of Flatten

还有一件事，你的input_tensor似乎没有被使用，我说错了吗？ 是你的vgg16的输入还是你想要一个多输入模型？

如果你的input_tensor是vgg16的输入，所以你要改。

vgg16 = VGG16(input_tensor=input_tensor, weights='imagenet', include_top=False)