我已经在Tensorflow中训练了我的NN,并像这样保存了模型:
def neural_net(x):
layer_1 = tf.layers.dense(inputs=x, units=195, activation=tf.nn.sigmoid)
out_layer = tf.layers.dense(inputs=layer_1, units=6)
return out_layer
train_x = pd.read_csv("data_x.csv", sep=" ")
train_y = pd.read_csv("data_y.csv", sep=" ")
train_x = train_x / 6 - 0.5
train_size = 0.9
train_cnt = int(floor(train_x.shape[0] * train_size))
x_train = train_x.iloc[0:train_cnt].values
y_train = train_y.iloc[0:train_cnt].values
x_test = train_x.iloc[train_cnt:].values
y_test = train_y.iloc[train_cnt:].values
x = tf.placeholder("float", [None, 386])
y = tf.placeholder("float", [None, 6])
nn_output = neural_net(x)
cost = tf.reduce_mean(tf.losses.mean_squared_error(labels=y, predictions=nn_output))
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
training_epochs = 5000
display_step = 1000
batch_size = 30
keep_prob = tf.placeholder("float")
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(training_epochs):
total_batch = int(len(x_train) / batch_size)
x_batches = np.array_split(x_train, total_batch)
y_batches = np.array_split(y_train, total_batch)
for i in range(total_batch):
batch_x, batch_y = x_batches[i], y_batches[i]
_, c = sess.run([optimizer, cost],
feed_dict={
x: batch_x,
y: batch_y,
keep_prob: 0.8
})
saver.save(sess, 'trained_model', global_step=1000)
现在我想在不同的文件中使用训练好的模型。当然,恢复和保存模型的例子还有很多,我经历了很多。我仍然无法使它们中的任何一个工作,总会有某种错误。所以这是我的恢复文件,你能帮我恢复保存的模型吗?
saver = tf.train.import_meta_graph('trained_model-1000.meta')
y_pred = []
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('./'))
sess.run([y_pred], feed_dict={x: input_values})
例如,此尝试给了我错误"会话图为空。在调用 run() 之前向图形添加操作。那么我应该向图形中添加什么操作以及如何添加?我不知道该操作在我的模型中应该是什么......我不明白在 Tensorflow 中保存/恢复的整个概念。还是我应该完全以不同的方式进行恢复?提前感谢!
错了,请原谅我,但tf.train.Saver()
只保存变量值而不是图形本身。这意味着,如果要将模型加载到不同的文件中,则需要重建图形或以某种方式加载图形。Tensorflow 文档指出:
tf.train.Saver 对象不仅将变量保存到检查点文件,还可以还原变量。请注意,从文件还原变量时,不必事先初始化它们。
请考虑以下示例:
一个保存模型的文件:
# Create some variables.
v1 = tf.get_variable("v1", shape=[3], initializer = tf.zeros_initializer)
v2 = tf.get_variable("v2", shape=[5], initializer = tf.zeros_initializer)
inc_v1 = v1.assign(v1+1)
dec_v2 = v2.assign(v2-1)
# Add an op to initialize the variables.
init_op = tf.global_variables_initializer()
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, initialize the variables, do some work, and save the
# variables to disk.
with tf.Session() as sess:
sess.run(init_op)
# Do some work with the model.
inc_v1.op.run()
dec_v2.op.run()
# Save the variables to disk.
save_path = saver.save(sess, "/tmp/model.ckpt")
print("Model saved in file: %s" % save_path)
加载以前保存的模型的另一个文件:
tf.reset_default_graph()
# Create some variables.
v1 = tf.get_variable("v1", shape=[3])
v2 = tf.get_variable("v2", shape=[5])
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, use the saver to restore variables from disk, and
# do some work with the model.
with tf.Session() as sess:
# Restore variables from disk.
saver.restore(sess, "/tmp/model.ckpt")
print("Model restored.")
# Check the values of the variables
print("v1 : %s" % v1.eval())
print("v2 : %s" % v2.eval())
output = sess.run(nn_output, feed_dict={ x: batch_x, keep_prob: 0.8 })
其中nn_output
名称是网络最后一层的输出变量。您可以使用以下命令保存变量:
saver = tf.train.Saver([nn_output])
saver.save(sess, 'my_test_model',global_step=1000) # save every 1000 steps
因此在您的代码中:
out_layer = tf.layers.dense(inputs=layer_1, units=6)
应该是 :
out_layer = tf.layers.dense(inputs=layer_1, units=6, name='nn_output')
要恢复:
with tf.Session() as sess:
saver = tf.train.import_meta_graph('my_test_model')
saver.restore(sess,tf.train.latest_checkpoint('./'))
现在,您应该可以访问图形的该节点。如果未指定名称,则很难恢复该特定图层。
知道使用tf.saved_model.builder.SavedModelBuilder
函数。
保存的主要行:
builder = tf.saved_model.builder.SavedModelBuilder(graph_location)
builder.add_meta_graph_and_variables(sess, ["cnn_mnist"])
builder.save()
保存模型的代码:
...
def main(_):
# Import data
mnist = input_data.read_data_sets(FLAGS.data_dir)
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
# Define loss and optimizer
y_ = tf.placeholder(tf.int64, [None])
# Build the graph for the deep net
y_conv, keep_prob = deepnn(x) # an unknow model model
with tf.name_scope('loss'):
cross_entropy = tf.losses.sparse_softmax_cross_entropy(
labels=y_, logits=y_conv)
cross_entropy = tf.reduce_mean(cross_entropy)
with tf.name_scope('adam_optimizer'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.argmax(y_conv, 1), y_)
correct_prediction = tf.cast(correct_prediction, tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
graph_location ="tmp/"
print('Saving graph to: %s' % graph_location)
**builder = tf.saved_model.builder.SavedModelBuilder(graph_location)**
train_writer = tf.summary.FileWriter(graph_location)
train_writer.add_graph(tf.get_default_graph())
saver = tf.train.Saver(max_to_keep=1)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
**builder.add_meta_graph_and_variables(sess, ["cnn_mnist"])**
for i in range(20000):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch[0], y_: batch[1], keep_prob: 1.0})
print('step %d, training accuracy %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
**builder.save()**
saver.save(sess, "tmp/my_checkpoint.ckpt", global_step =0)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str,
default='/tmp/tensorflow/mnist/input_data',
help='Directory for storing input data')
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
`
恢复模型的代码:
import tensorflow as tf
# récupération des poids
export_dir = "tmp"
sess = tf.Session()
tf.saved_model.loader.load(sess,["cnn_mnist"], export_dir)
#trainable_var = tf.trainable_variables()
trainable_var = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
for var in trainable_var:
print(var.name)`
这个问题很老了。但是,如果其他人正在努力使用经过训练的模型(使用 TF 1.x)进行预测,则此代码可能会有所帮助。
注意
-
您的网络构建/定义代码必须在创建
Saver()
实例之前执行。否则,您会收到错误:ValueError: No variables to save
。在下面的代码中,LeNet(x)
方法构造了输入占位符x
的网络。 -
不应初始化会话中的变量。因为显然您是从保存的模型中加载它们的。
# all the network construction code
# (e.g. defining the variables and layers)
# must be exectured before the creation of
# the Saver() object. Otherwise you get the
# error: ValueError: No variables to save.
logits = LeNet(x)
saver = tf.train.Saver()
index = random.randint(0, len(X_train))
image = X_train[index].squeeze()
label = y_train[index]
print("Label: ", label)
plt.figure(figsize=(1,1))
plt.imshow(image, cmap="gray")
plt.show()
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('./checkpoints/'))
logits_output = sess.run(logits, feed_dict={x: image.reshape((1, 32, 32, 1))})
logits_output = logits_output.squeeze()
pred_output = np.exp(logits_output)/sum(np.exp(logits_output)) #softmax
print("Logits: ", logits_output)
print("Prediction output:", pred_output)
print("Predicted Label: ", np.argmax(pred_output))