不同类别的预训练参数加载

参见链接：https://cv-tricks.com/tensorflow-tutorial/save-restore-tensorflow-models-quick-complete-tutorial/

使用resnet34进行训练时可以使用预训练参数减少训练时间，如果预训练参数是20类网络，而我们的模型是4分类的模型，同样可以使用预训练参数，只是需要对加载的预训练参数进行修改，模型的类别进行修改，如

......

saver = tf.train.import_meta_graph('vgg.meta')

# Access the graph

graph = tf.get_default_graph()

## Prepare the feed_dict for feeding data for fine-tuning

 

#Access the appropriate output for fine-tuning

fc7= graph.get_tensor_by_name('fc7:0')

 

#use this if you only want to change gradients of the last layer

fc7 = tf.stop_gradient(fc7) # It's an identity function

fc7_shape= fc7.get_shape().as_list()

 

new_outputs=2

weights = tf.Variable(tf.truncated_normal([fc7_shape[3], num_outputs], stddev=0.05))

biases = tf.Variable(tf.constant(0.05, shape=[num_outputs]))

output = tf.matmul(fc7, weights) + biases

pred = tf.nn.softmax(output)

 

# Now, you run this with fine-tuning data in sess.run()