I have the pretty common use case of freezing the bottom layers of Inception and training only the first two layers, after which I lower the learning rate and fine tune the entire Inception model.
Here is my code for running the first part
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)
which runs properly, then my code for running the second part
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)
Notice that in the second part, I do not pass anything into create_train_op's variables_to_train parameter. This error is then shown
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"]()]]
I suspect that it's looking for the RMSProp variables for the InceptionV3/Conv2d_4a_3x3 layer, which is non-existent, because I didn't train that layer in the previous checkpoint. I'm not sure how to achieve what I want, as I can see no examples in the documentation about how to do this.
