我有一个Tensorflow v1模型，其权重是从.npy文件中加载的。该模型的代码和权重的加载如下：
class AlexNet(object):
"""Implementation of the AlexNet."""
def __init__(self, x, keep_prob, num_classes, skip_layer,
weights_path='DEFAULT'):
"""Create the graph of the AlexNet model.
Args:
x: Placeholder for the input tensor.
keep_prob: Dropout probability.
num_classes: Number of classes in the dataset.
skip_layer: List of names of the layer, that get trained from
scratch
weights_path: Complete path to the pretrained weight file, if it
isn't in the same folder as this code
"""
# Parse input arguments into class variables
self.X = x
self.NUM_CLASSES = num_classes
self.KEEP_PROB = keep_prob
self.SKIP_LAYER = skip_layer
if weights_path == 'DEFAULT':
self.WEIGHTS_PATH = 'bvlc_alexnet.npy'
else:
self.WEIGHTS_PATH = weights_path
# Call the create function to build the computational graph of AlexNet
self.create()
def create(self):
"""Create the network graph."""
# 1st Layer: Conv (w ReLu) -> Lrn -> Pool
conv1 = conv(self.X, 11, 11, 96, 4, 4, padding='VALID', name='conv1')
norm1 = lrn(conv1, 2, 2e-05, 0.75, name='norm1')
pool1 = max_pool(norm1, 3, 3, 2, 2, padding='VALID', name='pool1')
# 2nd Layer: Conv (w ReLu) -> Lrn -> Pool with 2 groups
conv2 = conv(pool1, 5, 5, 256, 1, 1, groups=2, name='conv2')
norm2 = lrn(conv2, 2, 2e-05, 0.75, name='norm2')
pool2 = max_pool(norm2, 3, 3, 2, 2, padding='VALID', name='pool2')
# 3rd Layer: Conv (w ReLu)
self.conv3 = conv(pool2, 3, 3, 384, 1, 1, name='conv3')
self.flattened = tf.reshape(self.conv3, [1, 64896], name='output')
def load_initial_weights(self, session):
"""Load weights from file into network.
As the weights from http://www.cs.toronto.edu/~guerzhoy/tf_alexnet/
come as a dict of lists (e.g. weights['conv1'] is a list) and not as
dict of dicts (e.g. weights['conv1'] is a dict with keys 'weights' &
'biases') we need a special load function
"""
# Load the weights into memory
weights_dict = np.load(self.WEIGHTS_PATH, encoding='bytes').item()
# Loop over all layer names stored in the weights dict
for op_name in weights_dict:
# Check if layer should be trained from scratch
if op_name not in self.SKIP_LAYER:
with tf.compat.v1.variable_scope(op_name, reuse=True):
# Assign weights/biases to their corresponding tf variable
for data in weights_dict[op_name]:
# Biases
if len(data.shape) == 1:
var = tf.compat.v1.get_variable('biases', trainable=False, use_resource=False)
session.run(var.assign(data))
# Weights
else:
var = tf.compat.v1.get_variable('weights', trainable=False, use_resource=False)
session.run(var.assign(data))
def conv(x, filter_height, filter_width, num_filters, stride_y, stride_x, name,
padding='SAME', groups=1):
"""Create a convolution layer.
Adapted from: https://github.com/ethereon/caffe-tensorflow
"""
# Get number of input channels
input_channels = int(x.get_shape()[-1])
# Create lambda function for the convolution
convolve = lambda i, k: tf.nn.conv2d(input=i, filters=k,
strides=[1, stride_y, stride_x, 1],
padding=padding)
with tf.compat.v1.variable_scope(name) as scope:
# Create tf variables for the weights and biases of the conv layer
weights = tf.compat.v1.get_variable('weights', shape=[filter_height,
int(filter_width),
int(input_channels/groups),
num_filters], use_resource=False)
biases = tf.compat.v1.get_variable('biases', shape=[num_filters], use_resource=False)
if groups == 1:
conv = convolve(x, weights)
# In the cases of multiple groups, split inputs & weights and
else:
# Split input and weights and convolve them separately
input_groups = tf.split(axis=3, num_or_size_splits=groups, value=x)
weight_groups = tf.split(axis=3, num_or_size_splits=groups,
value=weights)
output_groups = [convolve(i, k) for i, k in zip(input_groups, weight_groups)]
# Concat the convolved output together again
conv = tf.concat(axis=3, values=output_groups)
# Add biases
bias = tf.reshape(tf.nn.bias_add(conv, biases), tf.shape(input=conv))
# Apply relu function
relu = tf.nn.relu(bias, name=scope.name)
return relu
def fc(x, num_in, num_out, name, relu=True):
"""Create a fully connected layer."""
with tf.compat.v1.variable_scope(name) as scope:
# Create tf variables for the weights and biases
weights = tf.compat.v1.get_variable('weights', shape=[num_in, num_out],
trainable=True, use_resource=False)
biases = tf.compat.v1.get_variable('biases', [num_out], trainable=True, use_resource=False)
# Matrix multiply weights and inputs and add bias
act = tf.compat.v1.nn.xw_plus_b(x, weights, biases, name=scope.name)
if relu:
# Apply ReLu non linearity
relu = tf.nn.relu(act)
return relu
else:
return act
def max_pool(x, filter_height, filter_width, stride_y, stride_x, name,
padding='SAME'):
"""Create a max pooling layer."""
return tf.nn.max_pool2d(input=x, ksize=[1, filter_height, filter_width, 1],
strides=[1, stride_y, stride_x, 1],
padding=padding, name=name)
def lrn(x, radius, alpha, beta, name, bias=1.0):
"""Create a local response normalization layer."""
return tf.nn.local_response_normalization(x, depth_radius=radius,
alpha=alpha, beta=beta,
bias=bias, name=name)
def dropout(x, keep_prob):
"""Create a dropout layer."""
return tf.nn.dropout(x, 1 - (keep_prob))
g = tf.Graph()
with g.as_default():
# Initialize all variables
x = tf.compat.v1.placeholder(tf.float32, [1, 227, 227, 3])
y = tf.compat.v1.placeholder(tf.float32, [1, 1000])
keep_prob = tf.compat.v1.placeholder(tf.float32)
alex_net = AlexNet(x, keep_prob, 1000, ["conv4", "conv5", "pool5", "fc6", "fc7", "fc8"])
output = alex_net.flattened
saver = tf.compat.v1.train.Saver()
sess = tf.compat.v1.Session()
init = tf.compat.v1.global_variables_initializer()
sess.run(init)
# Load the pretrained weights into the non-trainable layer
alex_net.load_initial_weights(sess)
graph_def = g.as_graph_def()
正如您所看到的，我使用张量流提供的转换器将v1模型转换为v2模型，但这主要是使用compat.v1模式。无论如何，我想用这些权重以这种格式保存该模型，以便新的TensorflowLite转换器可以将其转换为.tflite文件。我知道它需要一个keras模型（h5），一个具体函数（此处不适用或我错了吗？）或一个保存的模型。
现在的问题是：如何保存该模型，或者将这个图形定义保存为与TensorflowLite v2转换器兼容的保存的模型格式？我必须对模型进行任何更改吗？