我不习惯使用TensorFlow或nn，所以请原谅我，如果我没有得到你们第一次说的话。
我目前正试图在我在互联网上获得的yolo v1代码中的每个卷积层之后添加一个批量规范化层。
以下代码是我使用的批量标准化功能。
def batchnorm(self, inp):
with tf.variable_scope("batchnorm"):
channels = inp.get_shape()[3]
offset = tf.get_variable("offset",
channels,
dtype=tf.float32,
initializer=tf.zeros_initializer())
scale = tf.get_variable("scale",
channels,
dtype=tf.float32,
initializer=tf.random_normal_initializer(1.0, 0.02))
mean, variance = tf.nn.moments(inp, axes=[0, 1, 2], keep_dims=False)
variance_epsilon = 1e-5
normalized = tf.nn.batch_normalization(inp, mean, variance,
offset, scale, variance_epsilon)
return normalized
以下代码是我使用
的yolov1代码的结构 if self.verbose:
print('Building Yolo Graph....')
# Reset default graph
tf.reset_default_graph()
# Input placeholder
self.x = tf.placeholder('float32', [None, 448, 448, 3])
self.label_batch = tf.placeholder('float32', [None, 73])
# conv1, pool1
self.conv1 = self.conv_layer(1, self.x, 64, 7, 2)
self.pool1 = self.maxpool_layer(2, self.conv1, 2, 2)
# size reduced to 64x112x112
# conv2, pool2
self.conv2 = self.conv_layer(3, self.pool1, 192, 3, 1)
self.pool2 = self.maxpool_layer(4, self.conv2, 2, 2)
# size reduced to 192x56x56
# conv3, conv4, conv5, conv6, pool3
self.conv3 = self.conv_layer(5, self.pool2, 128, 1, 1)
self.conv4 = self.conv_layer(6, self.conv3, 256, 3, 1)
self.conv5 = self.conv_layer(7, self.conv4, 256, 1, 1)
self.conv6 = self.conv_layer(8, self.conv5, 512, 3, 1)
self.pool3 = self.maxpool_layer(9, self.conv6, 2, 2)
# size reduced to 512x28x28
# conv7 - conv16, pool4
self.conv7 = self.conv_layer(10, self.pool3, 256, 1, 1)
self.conv8 = self.conv_layer(11, self.conv7, 512, 3, 1)
self.conv9 = self.conv_layer(12, self.conv8, 256, 1, 1)
self.conv10 = self.conv_layer(13, self.conv9, 512, 3, 1)
self.conv11 = self.conv_layer(14, self.conv10, 256, 1, 1)
self.conv12 = self.conv_layer(15, self.conv11, 512, 3, 1)
self.conv13 = self.conv_layer(16, self.conv12, 256, 1, 1)
self.conv14 = self.conv_layer(17, self.conv13, 512, 3, 1)
self.conv15 = self.conv_layer(18, self.conv14, 512, 1, 1)
self.conv16 = self.conv_layer(19, self.conv15, 1024, 3, 1)
self.pool4 = self.maxpool_layer(20, self.conv16, 2, 2)
# size reduced to 1024x14x14
# conv17 - conv24
self.conv17 = self.conv_layer(21, self.pool4, 512, 1, 1)
self.conv18 = self.conv_layer(22, self.conv17, 1024, 3, 1)
self.conv19 = self.conv_layer(23, self.conv18, 512, 1, 1)
self.conv20 = self.conv_layer(24, self.conv19, 1024, 3, 1)
self.conv21 = self.conv_layer(25, self.conv20, 1024, 3, 1)
self.conv22 = self.conv_layer(26, self.conv21, 1024, 3, 2)
self.conv23 = self.conv_layer(27, self.conv22, 1024, 3, 1)
self.conv24 = self.conv_layer(28, self.conv23, 1024, 3, 1)
# size reduced to 1024x7x7
# fc1, fc2, fc3
self.fc1 = self.fc_layer(29, self.conv24, 512,
flatten=True, linear=False)
self.fc2 = self.fc_layer(
30, self.fc1, 4096, flatten=False, linear=False)
self.fc3 = self.fc_layer(
31, self.fc2, 1470, flatten=False, linear=True)
varlist = self.print_tensors_in_checkpoint_file(file_name=self.weightFile, all_tensors=True, tensor_name=None)
variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
self.saver = tf.train.Saver(variables[:len(varlist)])
self.loss = self.calculate_loss_function(self.fc3 , self.label_batch)
self.sess = tf.Session()
self.saver.restore(self.sess, self.weightFile)
self.only_restore_conv20 = False
if self.only_restore_conv20:
after_20_initializer = [var.initializer for var in tf.global_variables()[3:]]
self.sess.run(after_20_initializer)
#exerpath = 'C:/Users/dml/PycharmProjects/YOLOv1-master/exer_ckpt/exer.ckpt'
self.training = tf.train.MomentumOptimizer(momentum=0.5, learning_rate=1e-4).minimize(self.loss)
Momentum_initializers = [var.initializer for var in tf.global_variables() if 'Momentum' in var.name]
self.sess.run(Momentum_initializers)
最后，我在将conv1orm层放在conv1层之后的错误之后得到了错误
self.conv1 = self.conv_layer(1, self.x, 64, 7, 2)
self.bn1 = self.batchnorm(self.conv1)
self.pool1 = self.maxpool_layer(2, self.bn1, 2, 2)
时
NotFoundError: Key batchnorm/offset not found in checkpoint
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
经过几天的努力，我发现它与在检查点文件中恢复权重有关。因为我的batchnorm变量不在检查点文件中。但我无法找到如何使我的代码工作。
答案 0 :(得分：1)
你是对的，问题是当你加载一个检查点时，TensorFlow想要恢复所有变量的值。如果在检查点文件中找不到某个变量，则会引发错误。
我猜您的检查点文件不包含新规范化层中的变量。如果是这样，这个检查点可能没用。当在新的网络结构（在每个转换层之后使用规范化层）中使用时，预先训练的变量值可能会产生相当糟糕的结果。
如果您仍想尝试使用检查点文件中预先训练的权重，则需要自己从检查点加载变量值。假设变量名称和形状没有改变，您应该能够在此gist中使用optimistic_restore函数的版本。这个要点显示了在创建检查点后添加图层的示例 - 您的确切情况。