alexnet_v2/conv1/biases not found in checkpoint - tensorflow

Question

I try to save and restore alxenet slim model. But I always get this error when I run the codesaver.restore(sess, tf.train.latest_checkpoint('I:/model/mnist/')).
And which throw the error:
NotFoundError (see above for traceback): Key alexnet_v2/conv1/biases not found in checkpoint.
When I run the tf.global_variables(), I can only get the weights of conv2d, and there is no biases in the result.
I don't understand what's the problem is. Here is my code:
here is my alex model
def alexnet_v2_arg_scope(weight_decay=0.0005,
stddev=0.1,
batch_norm_var_collection='moving_vars',
use_fused_batchnorm=True):
batch_norm_params = {
# Decay for the moving averages.
'decay': 0.9997,
# epsilon to prevent 0s in variance.
'epsilon': 0.001,
# collection containing update_ops.
'updates_collections': ops.GraphKeys.UPDATE_OPS,
# Use fused batch norm if possible.
'fused': use_fused_batchnorm,
# collection containing the moving mean and moving variance.
'variables_collections': {
'beta': None,
'gamma': None,
'moving_mean': [batch_norm_var_collection],
'moving_variance': [batch_norm_var_collection],
}
}
with slim.arg_scope([slim.conv2d, slim.fully_connected],
activation_fn=tf.nn.relu,
biases_initializer=tf.constant_initializer,
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params,
weights_regularizer=slim.l2_regularizer(weight_decay)):
with slim.arg_scope([slim.conv2d], padding='SAME'):
with slim.arg_scope([slim.max_pool2d], padding='VALID') as arg_sc:
return arg_sc
def alex_net(inputs,
num_classes=10,
is_training=True,
droupout_keep_prob=0.5,
spatial_squeze=True,
scope='alexnet_v2'):
with tf.variable_scope(scope, 'alexnet_v2',[inputs]) as sc:
end_points_collection = sc.name + '_end_points'
with slim.arg_scope([slim.conv2d],
weights_initializer=trunc_norm(0.1),
biases_initializer=tf.constant_initializer(0.1),
outputs_collections=end_points_collection):
inputs = tf.reshape(inputs,[-1,28,28,1])
net = slim.conv2d(inputs, 64, [3, 3], 1, padding='VALID', scope='conv1')
net = slim.max_pool2d(net, [2, 2], 2, scope='pool1')
net = slim.conv2d(net, 128, [3, 3], scope='conv2')
net = slim.max_pool2d(net, [3, 3], 2, scope='pool2')
# net = slim.conv2d(net, 384, [3, 3], scope='conv3')
# net = slim.conv2d(net, 384, [3, 3], scope='conv4')
net = slim.conv2d(net, 256, [3, 3], scope='conv3')
# net = slim.max_pool2d(net, [3, 3], 2, scope='pool5')
net = slim.conv2d(net, 512, [3, 3], scope='conv4')
with slim.arg_scope([slim.conv2d],
weights_initializer=trunc_norm(0.1),
biases_initializer=tf.constant_initializer(0.1)):
# net = slim.conv2d(net, 1028, [6, 6], padding='VALID', scope='fc6')
net = slim.avg_pool2d(net, [6,6], stride=1,padding='VALID',scope='avg_pool5' )
net = slim.dropout(net, droupout_keep_prob, is_training=is_training, scope='dropout6')
# net = slim.conv2d(net, 512, [1, 1], scope='fc7')
# net = slim.dropout(net, droupout_keep_prob, is_training=is_training, scope='dropout7')
net = slim.conv2d(net, num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
biases_initializer=tf.zeros_initializer(),
scope='fc7x')
end_points = slim.utils.convert_collection_to_dict(end_points_collection)
if spatial_squeze:
net = tf.squeeze(net, [1,2], name='fc8/squeezed')
end_points[sc.name + '/fc8'] = net
return net, end_point
save model
varialbes_to_restore = slim.get_variables_to_restore()
saver = tf.train.Saver(varialbes_to_restore)
saver.save(sess,'I:/model/mnist/')
restore model
with tf.Session() as sess:
logits, _ = _alex_slim.alex_net(teX[:200])
saver = tf.train.Saver()
saver.restore(sess, tf.train.latest_checkpoint('I:/model/mnist/'))
logits_var = sess.run(logits)
print(logits_var)

Answer 1

Perhapse tensorflow expects you to save it in a checkpoint because you put it in a scope.
You will get the same error if you give a name to a tensor which isn't being saved.
If you don't want to save it, don't give it a name or scope.