![](/img/trans.png)
[英]How to change output of a layer in a pre-trained CNN model in Keras?
[英]How to get the output of certain layer of trained CNN model [Tensorflow]
我有一个用于image classification
的CNN
模型,该模型已针对我的数据集进行了训练。 该模型是这样的
Convolution
Relu
pooling
Convolution
Relu
Convolution
Relu
pooling
flat
fully connected (FC1)
Relu
fully connected (FC2)
softmax
训练后,我想获得输入到预训练模型中的图像的特征向量,即我想获得FC1
层的输出。 有什么方法可以获取它,我浏览了网络,但找不到任何有用的建议,对您有很大帮助。
训练脚本
# input
x = tf.placeholder(tf.float32, shape=[None, img_size_h, img_size_w, num_channels], name='x')
# lables
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
y_true_cls = tf.argmax(y_true, axis=1)
y_pred = build_model(x) # Builds model architecture
y_pred_cls = tf.argmax(y_pred, axis=1)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits_v2(logits=y_pred, labels=y_true)
cost = tf.reduce_mean(cross_entropy)
optimizer = tf.train.MomentumOptimizer(learn_rate, 0.9, use_locking=False, use_nesterov=True).minimize(cost)
accuracy = tf.reduce_mean(tf.cast(tf.equal(y_pred_cls, y_true_cls), tf.float32))
sess = tf.Session()
sess.run(tf.global_variables_initializer())
tf_saver = tf.train.Saver()
train(num_iteration) # Trains the network and saves the model
sess.close()
测试脚本
sess = tf.Session()
tf_saver = tf.train.import_meta_graph('model/model.meta')
tf_saver.restore(sess, tf.train.latest_checkpoint('model'))
x = tf.get_default_graph().get_tensor_by_name('x:0')
y_true = tf.get_default_graph().get_tensor_by_name('y_true:0')
y_true_cls = tf.argmax(y_true, axis=1)
y_pred = tf.get_default_graph().get_tensor_by_name('y_pred:0') # refers to FC2 in the model
y_pred_cls = tf.argmax(y_pred, axis=1)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
images, labels = read_data() # read data for testing
feed_dict_test = {x: images, y_true: labels}
test_acc = sess.run(accuracy, feed_dict=feed_dict_test)
sess.close()
您可以只在正确的张量上执行sess.run来获取值。 首先,您需要张量。 您可以在build_model内通过添加名称参数(可以对任何张量执行此操作)为其命名,例如:
FC1 = tf.add(tf.multiply(Flat, W1), b1, name="FullyConnected1")
稍后,您可以获取完全连接层的张量并对其进行评估:
with tf.Session() as sess:
FC1 = tf.get_default_graph().get_tensor_by_name('FullyConnected1:0')
FC1_values = sess.run(FC1, feed_dict={x: input_img_arr})
(这是假设图中没有其他称为FullyConnected1的层)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.