是否可以使用 Tensorflow 将多类 SVM 作为 CNN 的最后一层答案

【问题标题】：Is it possible to have a multiclass SVM as the last layer of a CNN using Tensorflow是否可以使用 Tensorflow 将多类 SVM 作为 CNN 的最后一层
【发布时间】：2020-07-24 06:20:26
【问题描述】：

我想使用多类 RBF SVM 作为我在 Tensorflow 中构建的 CNN 模型的最后一层。

我目前有以下内容。但不是最后一层，是否可以插入一个 SVM？我有什么选择。我发现 Tensorflow 有一个叫做随机傅立叶特征的东西，我可以使用内核方法来模拟 SVM？这是一个选项吗？如果是这样，我将如何将它实施到我目前拥有的东西中？

net = x_noisy_image

# 1st convolutional layer.
net = tf.layers.conv2d(inputs=net, name='layer_conv1', padding='same',
                       filters=32, kernel_size=3, activation=tf.nn.relu)
# 2nd convolutional layer.
net = tf.layers.conv2d(inputs=net, name='layer_conv2', padding='same',
                       filters=32, kernel_size=3, activation=tf.nn.relu)
# Pooling layer
net = tf.layers.max_pooling2d(inputs=net, pool_size=2, strides=2)

# 3rd convolutional layer.
net = tf.layers.conv2d(inputs=net, name='layer_conv3', padding='same',
                       filters=64, kernel_size=3, activation=tf.nn.relu)
# 4th convolution layer
net = tf.layers.conv2d(inputs=net, name='layer_conv4', padding='same',
                       filters=64, kernel_size=3, activation=tf.nn.relu)
# Pooling layer
net = tf.layers.max_pooling2d(inputs=net, pool_size=2, strides=2)

# Flatten layer.This should eventually be replaced by:
# net = tf.layers.flatten(net)
net = tf.contrib.layers.flatten(net)

# 1st fully-connected / dense layer.
net = tf.layers.dense(inputs=net, name='layer_fc1',
                      units=200, activation=tf.nn.relu)
# 2nd fully-connected / dense layer.
net = tf.layers.dense(inputs=net, name='layer_fc2',
                      units=200, activation=tf.nn.relu)
# 3rd fully-connected / dense layer.
net = tf.layers.dense(inputs=net, name='layer_fc_out',
                      units=num_classes, activation=tf.nn.softmax)



# Unscaled output of the network.
logits = net
# Softmax output of the network.
y_pred = tf.nn.softmax(logits=logits)
# Loss measure to be optimized.
cross_entropy = tf.nn.softmax_cross_entropy_with_logits_v2(labels=y_true,
                                                           logits=logits)
loss = tf.reduce_mean(cross_entropy)

"""
Optimizer for Normal Training
"""
[var.name for var in tf.trainable_variables()]
optimizer = tf.train.AdamOptimizer(learning_rate=0.0001).minimize(loss)

【问题讨论】：

标签： tensorflow machine-learning neural-network svm

【解决方案1】：

我不知道多类 SVM，但我知道线性 SVM，为了做到这一点，您应该将激活更改为线性，将损失更改为铰链。检查此链接以获得澄清https://keras.io/examples/keras_recipes/quasi_svm/

【讨论】：