Tensorflow 如何使用不同的可训练变量从Inception-3检查点恢复训练
我有一个非常常见的用例,冻结Inception的底层,只训练前两层,然后降低学习率并微调整个Inception模型 下面是我运行第一部分的代码Tensorflow 如何使用不同的可训练变量从Inception-3检查点恢复训练,tensorflow,tf-slim,Tensorflow,Tf Slim,我有一个非常常见的用例,冻结Inception的底层,只训练前两层,然后降低学习率并微调整个Inception模型 下面是我运行第一部分的代码 train_dir='/home/ubuntu/pynb/TF play/log-inceptionv3flowers' with tf.Graph().as_default(): tf.logging.set_verbosity(tf.logging.INFO) dataset = get_dataset() images,
train_dir='/home/ubuntu/pynb/TF play/log-inceptionv3flowers'
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = get_dataset()
images, _, labels = load_batch(dataset, batch_size=32)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits, _ = inception.inception_v3(images, num_classes=5, is_training=True)
# Specify the loss function:
one_hot_labels = slim.one_hot_encoding(labels, 5)
tf.losses.softmax_cross_entropy(one_hot_labels, logits)
total_loss = tf.losses.get_total_loss()
# Create some summaries to visualize the training process:
tf.summary.scalar('losses/Total Loss', total_loss)
# Specify the optimizer and create the train op:
optimizer = tf.train.RMSPropOptimizer(0.001, 0.9,
momentum=0.9, epsilon=1.0)
train_op = slim.learning.create_train_op(total_loss, optimizer, variables_to_train=get_variables_to_train())
# Run the training:
final_loss = slim.learning.train(
train_op,
logdir=train_dir,
init_fn=get_init_fn(),
number_of_steps=4500,
save_summaries_secs=30,
save_interval_secs=30,
session_config=tf.ConfigProto(gpu_options=gpu_options))
print('Finished training. Last batch loss %f' % final_loss)
正确运行的代码,然后是运行第二部分的代码
train_dir='/home/ubuntu/pynb/TF play/log-inceptionv3flowers'
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = get_dataset()
images, _, labels = load_batch(dataset, batch_size=32)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits, _ = inception.inception_v3(images, num_classes=5, is_training=True)
# Specify the loss function:
one_hot_labels = slim.one_hot_encoding(labels, 5)
tf.losses.softmax_cross_entropy(one_hot_labels, logits)
total_loss = tf.losses.get_total_loss()
# Create some summaries to visualize the training process:
tf.summary.scalar('losses/Total Loss', total_loss)
# Specify the optimizer and create the train op:
optimizer = tf.train.RMSPropOptimizer(0.0001, 0.9,
momentum=0.9, epsilon=1.0)
train_op = slim.learning.create_train_op(total_loss, optimizer)
# Run the training:
final_loss = slim.learning.train(
train_op,
logdir=train_dir,
init_fn=get_init_fn(),
number_of_steps=10000,
save_summaries_secs=30,
save_interval_secs=30,
session_config=tf.ConfigProto(gpu_options=gpu_options))
print('Finished training. Last batch loss %f' % final_loss)
请注意,在第二部分中,我没有将任何内容传递到create\u train\u op
的variables\u to\u train
参数中。然后显示此错误
NotFoundError (see above for traceback): Key InceptionV3/Conv2d_4a_3x3/BatchNorm/beta/RMSProp not found in checkpoint
[[Node: save_1/RestoreV2_49 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_1/Const_0, save_1/RestoreV2_49/tensor_names, save_1/RestoreV2_49/shape_and_slices)]]
[[Node: save_1/Assign_774/_1550 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_2911_save_1/Assign_774", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
我怀疑它正在为InceptionV3/Conv2d_4a_3x3层寻找RMSProp变量,该层不存在,因为我没有在上一个检查点中训练该层。我不确定如何实现我想要的,因为我在文档中看不到关于如何实现的示例。TF Slim支持从变量名不匹配的检查点读取,如下所述: 您可以指定检查点中的变量名称如何映射到模型中的变量 我希望这有帮助