升级到tf 2.0后, 训练的模型想转成1.x版本的.pb模型, 但之前提供的通过ckpt转pb模型的方法都不可用(因为保存的ckpt不再有.meta)文件, 尝试了好久, 终于找到了一个方法可以迂回转到1.x版本的pb模型.
Note: 本方法首先有些要求需要满足:
在tf1.x的环境下, 将tf2.0保存的weights转为pb模型:
如果在tf2.0下保存的模型符合上述的三个定义, 那么这个.h5文件在1.x环境下其实是可以直接用的, 因为都是通过tf.keras高级封装了,2.0版本和1.x版本不存在特别大的区别,我自己的模型是可以直接用的.
import tensorflow as tf
import os
from nets.efficientNet import *
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
# 这个代码网上说需要加上, 如果模型里有dropout , bn层的话, 我测试过加不加结果都一样, 保险起见还是加上吧
tf.keras.backend.set_learning_phase(0)
# 首先是定义你的模型, 这个需要和tf2.0下一毛一样
inputs = tf.keras.Input(shape=(224, 224, 3), name='modelInput')
outputs = yourModel(inputs, training=False)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
model.load_weights('save_weights.h5')
def freeze_session(session, keep_var_names=None, output_names=None, clear_devices=True):
"""
Freezes the state of a session into a pruned computation graph.
Creates a new computation graph where variable nodes are replaced by
constants taking their current value in the session. The new graph will be
pruned so subgraphs that are not necessary to compute the requested
outputs are removed.
@param session The TensorFlow session to be frozen.
@param keep_var_names A list of variable names that should not be frozen,
or None to freeze all the variables in the graph.
@param output_names Names of the relevant graph outputs.
@param clear_devices Remove the device directives from the graph for better portability.
@return The frozen graph definition.
"""
from tensorflow.python.framework.graph_util import convert_variables_to_constants
graph = session.graph
with graph.as_default():
freeze_var_names = list(set(v.op.name for v in tf.global_variables()).difference(keep_var_names or []))
output_names = output_names or []
output_names += [v.op.name for v in tf.global_variables()]
# Graph -> GraphDef ProtoBuf
input_graph_def = graph.as_graph_def(add_shapes=True)
if clear_devices:
for node in input_graph_def.node:
node.device = ""
frozen_graph = convert_variables_to_constants(session, input_graph_def,
output_names, freeze_var_names)
return frozen_graph
frozen_graph = freeze_session(tf.keras.backend.get_session(), output_names=[out.op.name for out in model.outputs])
tf.train.write_graph(frozen_graph, "model", "tf_model.pb", as_text=False)
运行成功后, 会在当前目录下生成一个model文件夹, 里面有生成的tf_model.pb文件, 至此, 我们就完成了将tf2.0下训练的模型转到tf1.x下的pb模型, 这样,就可以用这个pb模型做其它推理或者转tvm ncnn等模型转换工作.
这个转换的重点就是通过keras这个中间商来完成, 所以我们定义的模型就必须要满足这个中间商定义的条件