模型没有属性 'shape' - VGG16 模型

Question

我正在尝试使用 VGG16 模型对 RAVDESS video_song 数据集进行分类。为此，我每秒从每个视频中提取 3 帧。然后，我使用 InceptionV3 从该帧中提取特征，并将其保存到 csv 文件中。现在，我正在尝试训练一个模型来根据给定的输入来预测情绪。

我正在使用 train_test_split 将我的数据拆分为随机训练和测试子集：

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)

在此之后，我构建了我的模型，在本例中为 VGG16，并尝试拟合它：

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)
)

x_train[0]的形状是(2048,)。

我在 (google colab)[colab.research.google.com] 上运行这段代码，这是我得到的错误：

---------------------------------------------------------------------------
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'

有人可以帮我吗？

Answer 1

问题是在error line中，你引入了你的VGG16模型作为输入，而你想要的是引入最后一层的输出，对吧？

因此，您应该更改下一行：

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

还有一点，你的input_tensor好像没用过，我错了吗？它应该是你的 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，那么你要改成：

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

模型没有属性 'shape' - VGG16 模型

Model has no attribute 'shape' - VGG16 Model

python

pattern-recognition

conv-neural-network

google-colaboratory