keras 保存成hdf5文件, 1.保存模型和参数, 2.只保存参数
保存模型:
Fashion-MNIST总共有十个类别的图像。每一个类别由训练数据集6000张图像和测试数据集1000张图像。所以训练集和测试集分别包含60000张和10000张。测试训练集用于评估模型的性能。
每一个输入图像的高度和宽度均为28像素。数据集由灰度图像组成。Fashion-MNIST,中包含十个类别,分别是t-shirt,trouser,pillover,dress,coat,sandal,shirt,sneaker,bag,ankle boot。
# 导包
from tensorflow import keras
import numpy as np
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
# 时尚数据导入
fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]
# 标准化
from sklearn.preprocessing import StandardScaler # preprocessing 预处理
scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train.astype(np.float32).reshape(-1, 784))
x_valid_scaled = scaler.fit_transform(x_valid.astype(np.float32).reshape(-1, 784))
x_test_scaled = scaler.fit_transform(x_test.astype(np.float32).reshape(-1, 784))
# 创建模型
model = keras.models.Sequential([keras.layers.Dense(512, activation = 'relu', input_shape = (784, )),
keras.layers.Dense(256, activation = 'relu'),
keras.layers.Dense(128, activation = 'relu'),
keras.layers.Dense(10, activation = 'softmax')])
model.compile(loss = 'sparse_categorical_crossentropy',
optimizer = 'adam',
metrics = ['accuracy'])
# 保存模型
import os
logdir = './graph_def_and_weights'
if not os.path.exists(logdir):
os.mkdir(logdir)
output_model_file = os.path.join(logdir, 'fashion_mnist_weight.h5')
callbacks = [keras.callbacks.TensorBoard(logdir), # 保存地址
# 保存效果最好的模型: save_best_only
keras.callbacks.ModelCheckpoint(output_model_file,
save_best_only = True,
save_weights_only = True),
keras.callbacks.EarlyStopping(patience = 5, min_delta = 1e-3)]
history = model.fit(x_train_scaled, y_train, epochs = 10,
validation_data= (x_valid_scaled, y_valid),
callbacks = callbacks)
# 保存模型
output_model_file2 = os.path.join(logdir, 'fashion_mnist_model.h5')
model.save(output_model_file2)
保存参数
# 另一种保存参数的方法
model.save_weights(os.path.join(logdir, 'fashion_mnist_weights_2.h5'))
# evaluate 评估
model.evaluate(x_valid_scaled, y_valid) # [0.35909169912338257, 0.88919997215271]
# 加载模型
model2 = keras.models.load_model(output_model_file2)
model2.evaluate(x_valid_scaled, y_valid) # [0.35909169912338257, 0.88919997215271]
# 把keras模型保存成savedmodel格式
tf.saved_model.save(model, './keras_saved_model')
# 加载savedmodel模型
loaded_saved_model = tf.saved_model.load('./keras_saved_model')
loaded_saved_model
# 保存模型
import os
logdir = './graph_def_and_weights'
if not os.path.exists(logdir):
os.mkdir(logdir)
output_model_file = os.path.join(logdir, 'fashion_mnist_weight.h5')
model.load_weights(output_model_file)
from tensorflow import keras
import numpy as np
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
import os
with open('./tflite_models/concrete_func_tf_lite', 'rb') as f:
concrete_func_tflite = f.read()
# 创建interpreter
interpreter = tf.lite.Interpreter(model_content = concrete_func_tflite)
# 分配内存
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
input_data = tf.constant(np.ones(input_details[0]['shape'], dtype = np.float32))
# 传入预测数据
interpreter.set_tensor(input_details[0]['index'], input_data)
# 执行预测
interpreter.invoke()
# 获取输出
output_results = interpreter.get_tensor(output_details[0]['index'])
print(output_results)
# 从文件加载
loaded_keras_model = keras.models.load_model('./graph_def_and_weights/fashion_mnist_model.h5')
loaded_keras_model(np.ones((1, 784)))
# 把keras模型转化为concrete function
run_model = tf.function(lambda x: loaded_keras_model(x))
keras_concrete_func = run_model.get_concrete_function(tf.TensorSpec(loaded_keras_model.inputs[0].shape,
loaded_keras_model.inputs[0].dtype))
# 使用
keras_concrete_func(tf.constant(np.ones((1, 784), dtype = np.float32)))
# 从文件加载
loaded_keras_model = keras.models.load_model('./graph_def_and_weights/fashion_mnist_model.h5')
loaded_keras_model
# lite 精简版模型 # 创建转化器
keras_to_tflite_converter = tf.lite.TFLiteConverter.from_keras_model(loaded_keras_model)
keras_to_tflite_converter
# 给converter添加量化的优化 # 把32位的浮点数变成8位整数
keras_to_tflite_converter.optimizations = [tf.lite.Optimize.OPTIMIZE_FOR_SIZE]
# 执行转化
keras_tflite = keras_to_tflite_converter.convert()
# 写入指定文件
import os
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)
# 把keras模型转化成concrete function
run_model = tf.function(lambda x: loaded_keras_model(x))
keras_concrete_func = run_model.get_concrete_function(tf.TensorSpec(loaded_keras_model.inputs[0].shape,
loaded_keras_model.inputs[0].dtype))
concrete_func_to_tflite_converter = tf.lite.TFLiteConverter.from_concrete_functions([keras_concrete_func])
concrete_func_to_tflite_converter.optimizations = [tf.lite.Optimize.OPTIMIZE_FOR_SIZE]
concrete_func_tflite = concrete_func_to_tflite_converter.convert()
with open('./tflite_models/quantized_concrete_func_tf_lite', 'wb') as f:
f.write(concrete_func_tflite)
saved_model_to_tflite_converter = tf.lite.TFLiteConverter.from_saved_model('./keras_saved_model/')
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)