笔记摘自《Google老师亲授 TensorFlow2.0 入门到进阶_课程》
1. 模型保存和部署流程
TensorFlow 2.0的模型保存和部署流程如下：
2. 模型的保存
（1）保存为HDF5
直接修改callback的参数列表如下：
# tf.keras.models.Sequential()
model = keras.models.Sequential([
keras.layers.Flatten(input_shape=[28, 28]),
keras.layers.Dense(300, activation='relu'),
keras.layers.Dense(100, activation='relu'),
keras.layers.Dense(10, activation='softmax')
])
model.compile(loss="sparse_categorical_crossentropy",
optimizer = "sgd",
metrics = ["accuracy"])
logdir = './graph_def_and_weights'
if not os.path.exists(logdir):
os.mkdir(logdir)
output_model_file = os.path.join(logdir,
"fashion_mnist_model.h5")
# 修改callback的参数列表,选择需要保存的参数
callbacks = [
keras.callbacks.TensorBoard(logdir),
keras.callbacks.ModelCheckpoint(output_model_file,
save_best_only = True,
save_weights_only = False),
keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
# 添加参数callbacks
history = model.fit(x_train_scaled, y_train, epochs=10,
validation_data=(x_valid_scaled, y_valid),
callbacks = callbacks)
model.evaluate(x_test_scaled, y_test, verbose=0)
# 选择只保存weight和bias
model.save_weights(os.path.join(logdir, "fashion_mnist_weights.h5"))
将保存的权重赋值给模型时，需要先建立一个与训练一模一样的模型：
# tf.keras.models.Sequential()
model = keras.models.Sequential([
keras.layers.Flatten(input_shape=[28, 28]),
keras.layers.Dense(300, activation='relu'),
keras.layers.Dense(100, activation='relu'),
keras.layers.Dense(10, activation='softmax')
])
model.compile(loss="sparse_categorical_crossentropy",
optimizer = "sgd",
metrics = ["accuracy"])
logdir = './graph_def_and_weights'
if not os.path.exists(logdir):
os.mkdir(logdir)
output_model_file = os.path.join(logdir,
"fashion_mnist_model.h5")
model.load_weights(output_model_file)
model.evaluate(x_test_scaled, y_test, verbose=0)
（2）保存为SaveModel
使用tf.saved_model.save()直接保存模型所有内容
保存路径："./keras_saved_graph"
# tf.keras.models.Sequential()
model = keras.models.Sequential([
keras.layers.Flatten(input_shape=[28, 28]),
keras.layers.Dense(300, activation='relu'),
keras.layers.Dense(100, activation='relu'),
keras.layers.Dense(10, activation='softmax')
])
model.compile(loss="sparse_categorical_crossentropy",
optimizer = "sgd",
metrics = ["accuracy"])
history = model.fit(x_train_scaled, y_train, epochs=10,
validation_data=(x_valid_scaled, y_valid))
# 保存模型
tf.saved_model.save(model, "./keras_saved_graph")
查看保存内容：
!saved_model_cli show --dir ./keras_saved_graph --all
可以看到关于输入和输出的签名信息。如下：
使用tf.saved_model.load()加载模型，验证模型保存是否正确：
loaded_saved_model = tf.saved_model.load('./keras_saved_graph')
print(list(loaded_saved_model.signatures.keys()))
# ['serving_default']
inference = loaded_saved_model.signatures['serving_default']
print(inference.structured_outputs)
# {'dense_2': TensorSpec(shape=(None, 10), dtype=tf.float32, name='dense_2')}
results = inference(tf.constant(x_test_scaled[0:1]))
print(results['dense_2'])
# tf.Tensor([[3.3287105e-07 6.5204258e-05 7.5596186e-06 9.7430329e-06 6.4412257e-06 8.6376350e-03 2.2177779e-05 5.3723875e-02 4.3917933e-04 9.3708795e-01]], shape=(1, 10), dtype=float32)
3. 转为TFLite
签名函数转为SavedModel、h5 model转为concrete_function这里不列出，只讨论如何从h5和SavedModel直接转为tflite model。
（1）h5转为TFLite model
使用tf.lite.TFLiteConverter直接将h5转为TFLite model。
# 加载模型
loaded_keras_model = keras.models.load_model(
'./graph_def_and_weights/fashion_mnist_model.h5')
# 转换
keras_to_tflite_converter = tf.lite.TFLiteConverter.from_keras_model(
loaded_keras_model)
keras_tflite = keras_to_tflite_converter.convert()
# 保存
if not os.path.exists('./tflite_models'):
os.mkdir('./tflite_models')
with open('./tflite_models/keras_tflite', 'wb') as f:
f.write(keras_tflite)
（2）SaveModel转为 tf.lite model
直接传入 SaveModel的路径即可。
这里与上述第二种保存方式的保存目录相对应。
saved_model_to_tflite_converter = tf.lite.TFLiteConverter.from_saved_model('./keras_saved_graph/')
saved_model_tflite = saved_model_to_tflite_converter.convert()
with open('./tflite_models/saved_model_tflite', 'wb') as f:
f.write(saved_model_tflite)
4. 量化TFLite模型
量化的意思是把32位精度变为8位，简化模型。
直接给convetor设置一个optimization即可。
（1）量化h5模型
loaded_keras_model = keras.models.load_model(
'./graph_def_and_weights/fashion_mnist_model.h5')
keras_to_tflite_converter = tf.lite.TFLiteConverter.from_keras_model(
loaded_keras_model)
# 量化
keras_to_tflite_converter.optimizations = [
tf.lite.Optimize.OPTIMIZE_FOR_SIZE]
keras_tflite = keras_to_tflite_converter.convert()
if not os.path.exists('./tflite_models'):
os.mkdir('./tflite_models')
with open('./tflite_models/quantized_keras_tflite', 'wb') as f:
f.write(keras_tflite)
（2）量化SaveModel
saved_model_to_tflite_converter = tf.lite.TFLiteConverter.from_saved_model('./keras_saved_graph/')
saved_model_to_tflite_converter.optimizations = [
tf.lite.Optimize.OPTIMIZE_FOR_SIZE]
saved_model_tflite = saved_model_to_tflite_converter.convert()
with open('./tflite_models/quantized_saved_model_tflite', 'wb') as f:
f.write(saved_model_tflite)