牛andmore牛
牛andmore牛

【Tensorflow2.0】8、tensorflow2.0_hdf5_savedmodel_pb模型转换[2]

文章目录

  • 1、生成分类模型
  • 2、分别用h5和saved model做推理
    • 2.1 h5模型推理
    • 2.2 saved_model进行推理
  • 3、模型转换pb
    • 3.1 h5转pb
    • 3.2 saved model转pb
  • 4、调用pb模型进行推理
    • 4.1 h5 pb的推理
    • 4.2 saved pb的推理
  • 5、h5和saved 尝试互转
    • 5.1 h5转saved
      • 5.1.1 h5 转saved后的模型推理
      • 5.1.2 h5转saved后的模型转pb
      • 5.1.3 h5转saved模型后转pb推理
    • 5.2 saved model转h5
      • 5.2.1 saved转h5后的模型推理
      • 5.2.2 saved 转h5后的模型转pb
      • 5.2.3 saved转h5后模型转pb后的推理
  • 6、互转部分总结
  • 6.1 精度对比
    • 6.2 模型大小对比
    • 总结：

前期工作（一年前，2019年11月）参见https://blog.csdn.net/u011119817/article/details/103264080，随着框架版本的发展，有些结果不尽相同，因此更新本次博客，建意两者都看看，以便给自己的工作提供指导。

本文更新于2020年11月2日，所用代码全部在tensorflow gpu 2.2版本下进行，对于pb的使用，理论上tensorflow 1.14及以上版本都是可以的。关于本次实验的结论，大家可以直接去看结论部分，总的来说就是h5 和savedmodel两种格式可以互相转换，转换后可以继续进行转pb,所有可以互转的工作全部可以做。

另外，本博客的结论是基于一个很简单的模型来做的，所以对于更加复杂的模型，更少见的算子等情况，还要自己动手做实验，毕竟模型转换是一种实验性工作。

1、生成分类模型

import tensorflow as tf
print(tf.__version__)

2.2.0

#use tf2.x to train a model,this code can be run both by tf1.14 and tf2.x

# This file contains functions for training a TensorFlow model
import tensorflow as tf
import numpy as np
import os
print("tensorflow version",tf.__version__)
def process_dataset():
    # Import the data
    (x_train, y_train),(x_test, y_test) = tf.keras.datasets.mnist.load_data()
    x_train, x_test = x_train / 255.0, x_test / 255.0

    # Reshape the data
    NUM_TRAIN = 60000
    NUM_TEST = 10000
    x_train = np.reshape(x_train, (NUM_TRAIN, 28, 28, 1))
    x_test = np.reshape(x_test, (NUM_TEST, 28, 28, 1))
    return x_train, y_train, x_test, y_test

def create_model():
    model = tf.keras.models.Sequential()
    model.add(tf.keras.layers.InputLayer(input_shape=[28,28, 1]))
    model.add(tf.keras.layers.Flatten())
    model.add(tf.keras.layers.Dense(512, activation=tf.nn.relu))
    model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax))
    model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
    return model


def main():
    x_train, y_train, x_test, y_test = process_dataset()
    model = create_model()
    model.summary()
    # Train the model on the data
    model.fit(x_train, y_train, epochs = 5, verbose = 1)
    # Evaluate the model on test data
    model.evaluate(x_test, y_test)
    model.save("models/lenet5.h5",save_format='h5')
    model.save("models/lenet5",save_format='tf')
    # save(model, filename="models/lenet5.pb")

# if __name__ == '__main__':
#     main()
if not os.path.exists('models'):
    os.mkdir('models')
main()

tensorflow version 2.2.0
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
flatten (Flatten)            (None, 784)               0         
_________________________________________________________________
dense (Dense)                (None, 512)               401920    
_________________________________________________________________
dense_1 (Dense)              (None, 10)                5130      
=================================================================
Total params: 407,050
Trainable params: 407,050
Non-trainable params: 0
_________________________________________________________________
Epoch 1/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.2001 - accuracy: 0.9414
Epoch 2/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0796 - accuracy: 0.9760
Epoch 3/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0525 - accuracy: 0.9833
Epoch 4/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0357 - accuracy: 0.9886
Epoch 5/5
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0283 - accuracy: 0.9905
313/313 [==============================] - 0s 1ms/step - loss: 0.0695 - accuracy: 0.9793
WARNING:tensorflow:From /home/tl/miniconda3/envs/tf2gpu/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py:1817: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
INFO:tensorflow:Assets written to: models/lenet5/assets

2、分别用h5和saved model做推理

从测试集中随意选一张图片，保存成png格式，用来以下的测试

2.1 h5模型推理

#生成保存结果的路径
if not os.path.exists('out_results'):
    os.mkdir('out_results')

import tensorflow as tf
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
    
def h5_infer(model_path=None,img=None):
    model = tf.keras.models.load_model(model_path)
    result= model.predict(img)
    return result

def main():
    model_path = "models/lenet5.h5"
    img = Image.open('5.png')
    plt.imshow(img)
    img= np.array(img).reshape(1,28,28,1)/255.0
    result = h5_infer(model_path,img)
    print("result.shape",result.shape)
    print(result)
    np.save('out_results/h5_result.npy',result)#保存结果，方便以后比较
main()

result.shape (1, 10)
[[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

【Tensorflow2.0】8、tensorflow2.0_hdf5_savedmodel_pb模型转换[2]_第1张图片

2.2 saved_model进行推理

import tensorflow as tf
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
    
def savedmodel_infer(model_path=None,img=None):
    model = tf.keras.models.load_model(model_path)
    result= model.predict(img)
    return result

def main():
    model_path = "models/lenet5"
    img = Image.open('5.png')
    plt.imshow(img)
    img= np.array(img).reshape(1,28,28,1)/255.0
    result = savedmodel_infer(model_path,img)
    print("result.shape",result.shape)
    print(result)
    np.save('out_results/savedmodel_result.npy',result)#保存结果，方便以后比较
main()

result.shape (1, 10)
[[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

【Tensorflow2.0】8、tensorflow2.0_hdf5_savedmodel_pb模型转换[2]_第2张图片

还有另一种推理方式

import tensorflow as tf
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
from tensorflow.python.saved_model import tag_constants

def savedmodel_infer(model_path=None,img=None):
    saved_model_loaded = tf.saved_model.load(model_path, tags=[tag_constants.SERVING])
    model = saved_model_loaded.signatures['serving_default']
    result= model(img)
    return result

def main():
    model_path = "models/lenet5"
    img = Image.open('5.png')
    plt.imshow(img)
    img= tf.constant(np.array(img).astype(np.float32).reshape(1,28,28,1)/255.0)
    result = savedmodel_infer(model_path,img)
    print(result) #获取的结果是个字典
    for k,v in result.items(): #key 是layername 
        value=v.numpy()
    print('k=%s with value:'% k,value)
    np.save('out_results/savedmodelanother_result.npy',value)#保存结果，方便以后比较
main()

{'dense_1': }
k=dense_1 with value: [[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

【Tensorflow2.0】8、tensorflow2.0_hdf5_savedmodel_pb模型转换[2]_第3张图片

3、模型转换pb

有两个思路，分别是h5转pb、saved model转pb

3.1 h5转pb

# use tf2.x(tf1.14 also ok) to convert the model hdf5 trained by tf2.x to pb
import tensorflow as tf

def freeze_session(model_path=None,clear_devices=True):
    tf.compat.v1.reset_default_graph()
    session=tf.compat.v1.keras.backend.get_session()
    graph = session.graph
    with graph.as_default():
        model = tf.keras.models.load_model(model_path)
        output_names = [out.op.name for out in model.outputs]
        print("output_names",output_names)
        input_names =[innode.op.name for innode in model.inputs]
        print("input_names",input_names)
        input_graph_def = graph.as_graph_def()
        for node in input_graph_def.node:
            print('node:', node.name)
        print("len node1",len(input_graph_def.node))
        if clear_devices:
            for node in input_graph_def.node:
                node.device = ""
        frozen_graph =  tf.compat.v1.graph_util.convert_variables_to_constants(session, input_graph_def,
                                                      output_names)
        
        outgraph = tf.compat.v1.graph_util.remove_training_nodes(frozen_graph)#去掉与推理无关的内容
        print("##################################################################")
        for node in outgraph.node:
            print('node:', node.name)
        print("length of  node",len(outgraph.node))
        tf.io.write_graph(frozen_graph, "./models", "lenet5_h5.pb", as_text=False)
        return outgraph

def main():  

    freeze_session("models/lenet5.h5",True)

main()

output_names ['dense_1/Softmax']
input_names ['flatten_input']
node: flatten_input
node: flatten/Const
node: flatten/Reshape
node: dense/kernel/Initializer/random_uniform/shape
node: dense/kernel/Initializer/random_uniform/min
node: dense/kernel/Initializer/random_uniform/max
node: dense/kernel/Initializer/random_uniform/RandomUniform
node: dense/kernel/Initializer/random_uniform/sub
node: dense/kernel/Initializer/random_uniform/mul
node: dense/kernel/Initializer/random_uniform
node: dense/kernel
node: dense/kernel/IsInitialized/VarIsInitializedOp
node: dense/kernel/Assign
node: dense/kernel/Read/ReadVariableOp
node: dense/bias/Initializer/zeros
node: dense/bias
node: dense/bias/IsInitialized/VarIsInitializedOp
node: dense/bias/Assign
node: dense/bias/Read/ReadVariableOp
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/kernel/Initializer/random_uniform/shape
node: dense_1/kernel/Initializer/random_uniform/min
node: dense_1/kernel/Initializer/random_uniform/max
node: dense_1/kernel/Initializer/random_uniform/RandomUniform
node: dense_1/kernel/Initializer/random_uniform/sub
node: dense_1/kernel/Initializer/random_uniform/mul
node: dense_1/kernel/Initializer/random_uniform
node: dense_1/kernel
node: dense_1/kernel/IsInitialized/VarIsInitializedOp
node: dense_1/kernel/Assign
node: dense_1/kernel/Read/ReadVariableOp
node: dense_1/bias/Initializer/zeros
node: dense_1/bias
node: dense_1/bias/IsInitialized/VarIsInitializedOp
node: dense_1/bias/Assign
node: dense_1/bias/Read/ReadVariableOp
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
node: Placeholder
node: AssignVariableOp
node: ReadVariableOp
node: Placeholder_1
node: AssignVariableOp_1
node: ReadVariableOp_1
node: Placeholder_2
node: AssignVariableOp_2
node: ReadVariableOp_2
node: Placeholder_3
node: AssignVariableOp_3
node: ReadVariableOp_3
node: VarIsInitializedOp
node: VarIsInitializedOp_1
node: VarIsInitializedOp_2
node: VarIsInitializedOp_3
node: init
node: dense_1_target
node: total/Initializer/zeros
node: total
node: total/IsInitialized/VarIsInitializedOp
node: total/Assign
node: total/Read/ReadVariableOp
node: count/Initializer/zeros
node: count
node: count/IsInitialized/VarIsInitializedOp
node: count/Assign
node: count/Read/ReadVariableOp
node: metrics/accuracy/Squeeze
node: metrics/accuracy/ArgMax/dimension
node: metrics/accuracy/ArgMax
node: metrics/accuracy/Cast
node: metrics/accuracy/Equal
node: metrics/accuracy/Cast_1
node: metrics/accuracy/Const
node: metrics/accuracy/Sum
node: metrics/accuracy/AssignAddVariableOp
node: metrics/accuracy/ReadVariableOp
node: metrics/accuracy/Size
node: metrics/accuracy/Cast_2
node: metrics/accuracy/AssignAddVariableOp_1
node: metrics/accuracy/ReadVariableOp_1
node: metrics/accuracy/div_no_nan/ReadVariableOp
node: metrics/accuracy/div_no_nan/ReadVariableOp_1
node: metrics/accuracy/div_no_nan
node: metrics/accuracy/Identity
node: loss/dense_1_loss/Cast
node: loss/dense_1_loss/Shape
node: loss/dense_1_loss/Reshape/shape
node: loss/dense_1_loss/Reshape
node: loss/dense_1_loss/strided_slice/stack
node: loss/dense_1_loss/strided_slice/stack_1
node: loss/dense_1_loss/strided_slice/stack_2
node: loss/dense_1_loss/strided_slice
node: loss/dense_1_loss/Reshape_1/shape/0
node: loss/dense_1_loss/Reshape_1/shape
node: loss/dense_1_loss/Reshape_1
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits
node: loss/dense_1_loss/weighted_loss/Cast/x
node: loss/dense_1_loss/weighted_loss/Mul
node: loss/dense_1_loss/Const
node: loss/dense_1_loss/Sum
node: loss/dense_1_loss/num_elements
node: loss/dense_1_loss/num_elements/Cast
node: loss/dense_1_loss/Const_1
node: loss/dense_1_loss/Sum_1
node: loss/dense_1_loss/value
node: loss/mul/x
node: loss/mul
node: iter/Initializer/zeros
node: iter
node: iter/IsInitialized/VarIsInitializedOp
node: iter/Assign
node: iter/Read/ReadVariableOp
node: beta_1/Initializer/initial_value
node: beta_1
node: beta_1/IsInitialized/VarIsInitializedOp
node: beta_1/Assign
node: beta_1/Read/ReadVariableOp
node: beta_2/Initializer/initial_value
node: beta_2
node: beta_2/IsInitialized/VarIsInitializedOp
node: beta_2/Assign
node: beta_2/Read/ReadVariableOp
node: decay/Initializer/initial_value
node: decay
node: decay/IsInitialized/VarIsInitializedOp
node: decay/Assign
node: decay/Read/ReadVariableOp
node: learning_rate/Initializer/initial_value
node: learning_rate
node: learning_rate/IsInitialized/VarIsInitializedOp
node: learning_rate/Assign
node: learning_rate/Read/ReadVariableOp
node: dense/kernel/m/Initializer/zeros/shape_as_tensor
node: dense/kernel/m/Initializer/zeros/Const
node: dense/kernel/m/Initializer/zeros
node: dense/kernel/m
node: dense/kernel/m/IsInitialized/VarIsInitializedOp
node: dense/kernel/m/Assign
node: dense/kernel/m/Read/ReadVariableOp
node: dense/bias/m/Initializer/zeros
node: dense/bias/m
node: dense/bias/m/IsInitialized/VarIsInitializedOp
node: dense/bias/m/Assign
node: dense/bias/m/Read/ReadVariableOp
node: dense_1/kernel/m/Initializer/zeros/shape_as_tensor
node: dense_1/kernel/m/Initializer/zeros/Const
node: dense_1/kernel/m/Initializer/zeros
node: dense_1/kernel/m
node: dense_1/kernel/m/IsInitialized/VarIsInitializedOp
node: dense_1/kernel/m/Assign
node: dense_1/kernel/m/Read/ReadVariableOp
node: dense_1/bias/m/Initializer/zeros
node: dense_1/bias/m
node: dense_1/bias/m/IsInitialized/VarIsInitializedOp
node: dense_1/bias/m/Assign
node: dense_1/bias/m/Read/ReadVariableOp
node: dense/kernel/v/Initializer/zeros/shape_as_tensor
node: dense/kernel/v/Initializer/zeros/Const
node: dense/kernel/v/Initializer/zeros
node: dense/kernel/v
node: dense/kernel/v/IsInitialized/VarIsInitializedOp
node: dense/kernel/v/Assign
node: dense/kernel/v/Read/ReadVariableOp
node: dense/bias/v/Initializer/zeros
node: dense/bias/v
node: dense/bias/v/IsInitialized/VarIsInitializedOp
node: dense/bias/v/Assign
node: dense/bias/v/Read/ReadVariableOp
node: dense_1/kernel/v/Initializer/zeros/shape_as_tensor
node: dense_1/kernel/v/Initializer/zeros/Const
node: dense_1/kernel/v/Initializer/zeros
node: dense_1/kernel/v
node: dense_1/kernel/v/IsInitialized/VarIsInitializedOp
node: dense_1/kernel/v/Assign
node: dense_1/kernel/v/Read/ReadVariableOp
node: dense_1/bias/v/Initializer/zeros
node: dense_1/bias/v
node: dense_1/bias/v/IsInitialized/VarIsInitializedOp
node: dense_1/bias/v/Assign
node: dense_1/bias/v/Read/ReadVariableOp
node: VarIsInitializedOp_4
node: VarIsInitializedOp_5
node: VarIsInitializedOp_6
node: VarIsInitializedOp_7
node: VarIsInitializedOp_8
node: VarIsInitializedOp_9
node: VarIsInitializedOp_10
node: VarIsInitializedOp_11
node: VarIsInitializedOp_12
node: VarIsInitializedOp_13
node: VarIsInitializedOp_14
node: VarIsInitializedOp_15
node: VarIsInitializedOp_16
node: VarIsInitializedOp_17
node: VarIsInitializedOp_18
node: init_1
node: Placeholder_4
node: AssignVariableOp_4
node: ReadVariableOp_4
node: Placeholder_5
node: AssignVariableOp_5
node: ReadVariableOp_5
node: Placeholder_6
node: AssignVariableOp_6
node: ReadVariableOp_6
node: Placeholder_7
node: AssignVariableOp_7
node: ReadVariableOp_7
node: Placeholder_8
node: AssignVariableOp_8
node: ReadVariableOp_8
node: Placeholder_9
node: AssignVariableOp_9
node: ReadVariableOp_9
node: Placeholder_10
node: AssignVariableOp_10
node: ReadVariableOp_10
node: Placeholder_11
node: AssignVariableOp_11
node: ReadVariableOp_11
node: Placeholder_12
node: AssignVariableOp_12
node: ReadVariableOp_12
len node1 231
INFO:tensorflow:Froze 4 variables.
INFO:tensorflow:Converted 4 variables to const ops.
##################################################################
node: flatten_input
node: flatten/Const
node: flatten/Reshape
node: dense/kernel
node: dense/bias
node: dense/MatMul
node: dense/BiasAdd
node: dense/Relu
node: dense_1/kernel
node: dense_1/bias
node: dense_1/MatMul
node: dense_1/BiasAdd
node: dense_1/Softmax
length of  node 13

3.2 saved model转pb

import tensorflow as tf

def freeze_session(model_path=None,clear_devices=True):
    tf.compat.v1.reset_default_graph()
    session=tf.compat.v1.keras.backend.get_session()
    graph = session.graph
    with graph.as_default():
        model = tf.keras.models.load_model(model_path)
        output_names = [out.op.name for out in model.outputs]
        print("output_names",output_names)
        input_names =[innode.op.name for innode in model.inputs]
        print("input_names",input_names)        
        input_graph_def = graph.as_graph_def()
        for node in input_graph_def.node:
            print('node:', node.name)
        print("len node1",len(input_graph_def.node))
        if clear_devices:
            for node in input_graph_def.node:
                node.device = ""
        frozen_graph =  tf.compat.v1.graph_util.convert_variables_to_constants(session, input_graph_def,
                                                      output_names)
        
        outgraph = tf.compat.v1.graph_util.remove_training_nodes(frozen_graph)#去掉与推理无关的内容
        print("##################################################################")
        for node in outgraph.node:
            print('node:', node.name)
        print("length of  node",len(outgraph.node))
        tf.io.write_graph(frozen_graph, "./models", "lenet5_savedmodel.pb", as_text=False)

def main():  

    freeze_session("models/lenet5",True)
    

main()

output_names ['dense_1/Softmax']
input_names ['input_1']
node: kernel/Initializer/random_uniform/shape
node: kernel/Initializer/random_uniform/min
node: kernel/Initializer/random_uniform/max
node: kernel/Initializer/random_uniform/RandomUniform
node: kernel/Initializer/random_uniform/sub
node: kernel/Initializer/random_uniform/mul
node: kernel/Initializer/random_uniform
node: kernel
node: kernel/IsInitialized/VarIsInitializedOp
node: kernel/Assign
node: kernel/Read/ReadVariableOp
node: bias/Initializer/zeros
node: bias
node: bias/IsInitialized/VarIsInitializedOp
node: bias/Assign
node: bias/Read/ReadVariableOp
node: kernel_1/Initializer/random_uniform/shape
node: kernel_1/Initializer/random_uniform/min
node: kernel_1/Initializer/random_uniform/max
node: kernel_1/Initializer/random_uniform/RandomUniform
node: kernel_1/Initializer/random_uniform/sub
node: kernel_1/Initializer/random_uniform/mul
node: kernel_1/Initializer/random_uniform
node: kernel_1
node: kernel_1/IsInitialized/VarIsInitializedOp
node: kernel_1/Assign
node: kernel_1/Read/ReadVariableOp
node: bias_1/Initializer/zeros
node: bias_1
node: bias_1/IsInitialized/VarIsInitializedOp
node: bias_1/Assign
node: bias_1/Read/ReadVariableOp
node: total/Initializer/zeros
node: total
node: total/IsInitialized/VarIsInitializedOp
node: total/Assign
node: total/Read/ReadVariableOp
node: count/Initializer/zeros
node: count
node: count/IsInitialized/VarIsInitializedOp
node: count/Assign
node: count/Read/ReadVariableOp
node: total_1/Initializer/zeros
node: total_1
node: total_1/IsInitialized/VarIsInitializedOp
node: total_1/Assign
node: total_1/Read/ReadVariableOp
node: count_1/Initializer/zeros
node: count_1
node: count_1/IsInitialized/VarIsInitializedOp
node: count_1/Assign
node: count_1/Read/ReadVariableOp
node: Adam/iter
node: Adam/iter/Read/ReadVariableOp
node: Adam/beta_1
node: Adam/beta_1/Read/ReadVariableOp
node: Adam/beta_2
node: Adam/beta_2/Read/ReadVariableOp
node: Adam/decay
node: Adam/decay/Read/ReadVariableOp
node: Adam/learning_rate
node: Adam/learning_rate/Read/ReadVariableOp
node: dense/kernel/m/Initializer/zeros/shape_as_tensor
node: dense/kernel/m/Initializer/zeros/Const
node: dense/kernel/m/Initializer/zeros
node: dense/kernel/m
node: dense/kernel/m/IsInitialized/VarIsInitializedOp
node: dense/kernel/m/Assign
node: dense/kernel/m/Read/ReadVariableOp
node: dense/bias/m/Initializer/zeros
node: dense/bias/m
node: dense/bias/m/IsInitialized/VarIsInitializedOp
node: dense/bias/m/Assign
node: dense/bias/m/Read/ReadVariableOp
node: dense_1/kernel/m/Initializer/zeros/shape_as_tensor
node: dense_1/kernel/m/Initializer/zeros/Const
node: dense_1/kernel/m/Initializer/zeros
node: dense_1/kernel/m
node: dense_1/kernel/m/IsInitialized/VarIsInitializedOp
node: dense_1/kernel/m/Assign
node: dense_1/kernel/m/Read/ReadVariableOp
node: dense_1/bias/m/Initializer/zeros
node: dense_1/bias/m
node: dense_1/bias/m/IsInitialized/VarIsInitializedOp
node: dense_1/bias/m/Assign
node: dense_1/bias/m/Read/ReadVariableOp
node: dense/kernel/v/Initializer/zeros/shape_as_tensor
node: dense/kernel/v/Initializer/zeros/Const
node: dense/kernel/v/Initializer/zeros
node: dense/kernel/v
node: dense/kernel/v/IsInitialized/VarIsInitializedOp
node: dense/kernel/v/Assign
node: dense/kernel/v/Read/ReadVariableOp
node: dense/bias/v/Initializer/zeros
node: dense/bias/v
node: dense/bias/v/IsInitialized/VarIsInitializedOp
node: dense/bias/v/Assign
node: dense/bias/v/Read/ReadVariableOp
node: dense_1/kernel/v/Initializer/zeros/shape_as_tensor
node: dense_1/kernel/v/Initializer/zeros/Const
node: dense_1/kernel/v/Initializer/zeros
node: dense_1/kernel/v
node: dense_1/kernel/v/IsInitialized/VarIsInitializedOp
node: dense_1/kernel/v/Assign
node: dense_1/kernel/v/Read/ReadVariableOp
node: dense_1/bias/v/Initializer/zeros
node: dense_1/bias/v
node: dense_1/bias/v/IsInitialized/VarIsInitializedOp
node: dense_1/bias/v/Assign
node: dense_1/bias/v/Read/ReadVariableOp
node: input_1
node: flatten/Const
node: flatten/Reshape
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
node: Const
node: RestoreV2/tensor_names
node: RestoreV2/shape_and_slices
node: RestoreV2
node: Identity
node: AssignVariableOp
node: RestoreV2_1/tensor_names
node: RestoreV2_1/shape_and_slices
node: RestoreV2_1
node: Identity_1
node: AssignVariableOp_1
node: RestoreV2_2/tensor_names
node: RestoreV2_2/shape_and_slices
node: RestoreV2_2
node: Identity_2
node: AssignVariableOp_2
node: RestoreV2_3/tensor_names
node: RestoreV2_3/shape_and_slices
node: RestoreV2_3
node: Identity_3
node: AssignVariableOp_3
node: RestoreV2_4/tensor_names
node: RestoreV2_4/shape_and_slices
node: RestoreV2_4
node: Identity_4
node: AssignVariableOp_4
node: RestoreV2_5/tensor_names
node: RestoreV2_5/shape_and_slices
node: RestoreV2_5
node: Identity_5
node: AssignVariableOp_5
node: RestoreV2_6/tensor_names
node: RestoreV2_6/shape_and_slices
node: RestoreV2_6
node: Identity_6
node: AssignVariableOp_6
node: RestoreV2_7/tensor_names
node: RestoreV2_7/shape_and_slices
node: RestoreV2_7
node: Identity_7
node: AssignVariableOp_7
node: RestoreV2_8/tensor_names
node: RestoreV2_8/shape_and_slices
node: RestoreV2_8
node: Identity_8
node: AssignVariableOp_8
node: Identity_9
node: AssignVariableOp_9
node: Identity_10
node: AssignVariableOp_10
node: Identity_11
node: AssignVariableOp_11
node: Identity_12
node: AssignVariableOp_12
node: Identity_13
node: AssignVariableOp_13
node: Identity_14
node: AssignVariableOp_14
node: Identity_15
node: AssignVariableOp_15
node: Identity_16
node: AssignVariableOp_16
node: Identity_17
node: AssignVariableOp_17
node: Identity_18
node: AssignVariableOp_18
node: Identity_19
node: AssignVariableOp_19
node: Identity_20
node: AssignVariableOp_20
node: dense_1_target
node: total_2/Initializer/zeros
node: total_2
node: total_2/IsInitialized/VarIsInitializedOp
node: total_2/Assign
node: total_2/Read/ReadVariableOp
node: count_2/Initializer/zeros
node: count_2
node: count_2/IsInitialized/VarIsInitializedOp
node: count_2/Assign
node: count_2/Read/ReadVariableOp
node: metrics/accuracy/Squeeze
node: metrics/accuracy/ArgMax/dimension
node: metrics/accuracy/ArgMax
node: metrics/accuracy/Cast
node: metrics/accuracy/Equal
node: metrics/accuracy/Cast_1
node: metrics/accuracy/Const
node: metrics/accuracy/Sum
node: metrics/accuracy/AssignAddVariableOp
node: metrics/accuracy/ReadVariableOp
node: metrics/accuracy/Size
node: metrics/accuracy/Cast_2
node: metrics/accuracy/AssignAddVariableOp_1
node: metrics/accuracy/ReadVariableOp_1
node: metrics/accuracy/div_no_nan/ReadVariableOp
node: metrics/accuracy/div_no_nan/ReadVariableOp_1
node: metrics/accuracy/div_no_nan
node: metrics/accuracy/Identity
node: loss/dense_1_loss/Cast
node: loss/dense_1_loss/Shape
node: loss/dense_1_loss/Reshape/shape
node: loss/dense_1_loss/Reshape
node: loss/dense_1_loss/strided_slice/stack
node: loss/dense_1_loss/strided_slice/stack_1
node: loss/dense_1_loss/strided_slice/stack_2
node: loss/dense_1_loss/strided_slice
node: loss/dense_1_loss/Reshape_1/shape/0
node: loss/dense_1_loss/Reshape_1/shape
node: loss/dense_1_loss/Reshape_1
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits
node: loss/dense_1_loss/weighted_loss/Cast/x
node: loss/dense_1_loss/weighted_loss/Mul
node: loss/dense_1_loss/Const
node: loss/dense_1_loss/Sum
node: loss/dense_1_loss/num_elements
node: loss/dense_1_loss/num_elements/Cast
node: loss/dense_1_loss/Const_1
node: loss/dense_1_loss/Sum_1
node: loss/dense_1_loss/value
node: loss/mul/x
node: loss/mul
node: VarIsInitializedOp
node: VarIsInitializedOp_1
node: VarIsInitializedOp_2
node: VarIsInitializedOp_3
node: VarIsInitializedOp_4
node: VarIsInitializedOp_5
node: VarIsInitializedOp_6
node: VarIsInitializedOp_7
node: VarIsInitializedOp_8
node: VarIsInitializedOp_9
node: VarIsInitializedOp_10
node: VarIsInitializedOp_11
node: VarIsInitializedOp_12
node: VarIsInitializedOp_13
node: VarIsInitializedOp_14
node: VarIsInitializedOp_15
node: VarIsInitializedOp_16
node: VarIsInitializedOp_17
node: init
len node1 265
INFO:tensorflow:Froze 4 variables.
INFO:tensorflow:Converted 4 variables to const ops.
##################################################################
node: kernel
node: bias
node: kernel_1
node: bias_1
node: input_1
node: flatten/Const
node: flatten/Reshape
node: dense/MatMul
node: dense/BiasAdd
node: dense/Relu
node: dense_1/MatMul
node: dense_1/BiasAdd
node: dense_1/Softmax
length of  node 13

4、调用pb模型进行推理

同样，有两个可以进行推理的pb,分别来自不同的转换源

4.1 h5 pb的推理

输入输出结点名称要参考上文中转pb过程中确定的input name 和output name

#use tf1.14 and tf2.x with pb to load the data are both ok
import tensorflow as tf 
from PIL import Image
import numpy as np

def load_graph(file_path):
    with tf.io.gfile.GFile(file_path,'rb') as f:
        graph_def = tf.compat.v1.GraphDef()
        graph_def.ParseFromString(f.read())
    with tf.compat.v1.Graph().as_default() as graph:
        tf.import_graph_def(graph_def,input_map = None,return_elements = None,name = "",op_dict = None,producer_op_list = None)
    graph_nodes = [n for n in graph_def.node]
    return graph,graph_nodes
def main():
    file_path='./models/lenet5_h5.pb'
    img= np.array(Image.open('5.png')).reshape(1,28,28,1)/255.0
    graph,graph_nodes = load_graph(file_path)
    print("num nodes",len(graph_nodes))
    for node in graph_nodes:
        print('node:', node.name)

    input_node = graph.get_tensor_by_name('flatten_input:0')
    print("input_node.shape:",input_node.shape)
    output = graph.get_tensor_by_name('dense_1/Softmax:0')  
    config = tf.compat.v1.ConfigProto()
    config.gpu_options.allow_growth = True
    with tf.compat.v1.Session(graph=graph,config=config) as sess:
        logits = sess.run(output, feed_dict = {input_node:img})
    print("logits:",logits)
    np.save('out_results/h5pb_result.npy',logits)
main()


WARNING:tensorflow:From :11: calling import_graph_def (from tensorflow.python.framework.importer) with op_dict is deprecated and will be removed in a future version.
Instructions for updating:
Please file an issue at https://github.com/tensorflow/tensorflow/issues if you depend on this feature.
num nodes 17
node: flatten_input
node: flatten/Const
node: flatten/Reshape
node: dense/kernel
node: dense/bias
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/kernel
node: dense_1/bias
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
input_node.shape: (None, 28, 28, 1)
logits: [[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

4.2 saved pb的推理

#use tf1.14 and tf2.x with pb to load the data are both ok
import tensorflow as tf 
from PIL import Image
import numpy as np

def load_graph(file_path):
    with tf.io.gfile.GFile(file_path,'rb') as f:
        graph_def = tf.compat.v1.GraphDef()
        graph_def.ParseFromString(f.read())
    with tf.compat.v1.Graph().as_default() as graph:
        tf.import_graph_def(graph_def,input_map = None,return_elements = None,name = "",op_dict = None,producer_op_list = None)
    graph_nodes = [n for n in graph_def.node]
    return graph,graph_nodes
def main():
    file_path='./models/lenet5_savedmodel.pb'
    img= np.array(Image.open('5.png')).reshape(1,28,28,1)/255.0
    graph,graph_nodes = load_graph(file_path)
    print("num nodes",len(graph_nodes))
    for node in graph_nodes:
        print('node:', node.name)

    input_node = graph.get_tensor_by_name('input_1:0')
    print("input_node.shape:",input_node.shape)
    output = graph.get_tensor_by_name('dense_1/Softmax:0')  

    with tf.compat.v1.Session(graph=graph) as sess:
        logits = sess.run(output, feed_dict = {input_node:img})
    print("logits:",logits)
    np.save('out_results/savedmodelpb_result.npy',logits)
main()


num nodes 17
node: kernel
node: bias
node: kernel_1
node: bias_1
node: input_1
node: flatten/Const
node: flatten/Reshape
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
input_node.shape: (None, 28, 28, 1)
logits: [[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

5、h5和saved 尝试互转

  • 从以上可以看出，h5 可以转pb,saved model也可以转pb,并且，都可以进行推理，并且结果正确
  • 还未看到h5模型是否能和saved model互转下面将试一下

5.1 h5转saved

def main():
    file_path='./models/lenet5.h5'
    model = tf.keras.models.load_model(file_path)
    model.save('./models/h5tosaved',save_format='tf')
    
main()

INFO:tensorflow:Assets written to: ./models/h5tosaved/assets

看起来是转成功了，那么用这个转换后的模型进行推理来难证正确性

5.1.1 h5 转saved后的模型推理

import tensorflow as tf
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
    
def savedmodel_infer(model_path=None,img=None):
    model = tf.keras.models.load_model(model_path)
    result= model.predict(img)
    return result

def main():
    model_path = "models/h5tosaved"
    img = Image.open('5.png')
    plt.imshow(img)
    img= np.array(img).reshape(1,28,28,1)/255.0
    result = savedmodel_infer(model_path,img)
    print("result.shape",result.shape)
    print(result)
    np.save('out_results/h5tosavedmodel_result.npy',result)#保存结果，方便以后比较
main()

result.shape (1, 10)
[[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

【Tensorflow2.0】8、tensorflow2.0_hdf5_savedmodel_pb模型转换[2]_第4张图片

另一种方法

import tensorflow as tf
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
from tensorflow.python.saved_model import tag_constants

def savedmodel_infer(model_path=None,img=None):
    saved_model_loaded = tf.saved_model.load(model_path, tags=[tag_constants.SERVING])
    model = saved_model_loaded.signatures['serving_default']
    result= model(img)
    return result

def main():
    model_path = "models/h5tosaved"
    img = Image.open('5.png')
    plt.imshow(img)
    img= tf.constant(np.array(img).astype(np.float32).reshape(1,28,28,1)/255.0)
    result = savedmodel_infer(model_path,img)
    print(result) #获取的结果是个字典
    for k,v in result.items(): #key 是layername 
        value=v.numpy()
    print('k=%s with value:'% k,value)
    np.save('out_results/h5tosavedmodelanother_result.npy',value)#保存结果，方便以后比较
main()

{'dense_1': }
k=dense_1 with value: [[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

【Tensorflow2.0】8、tensorflow2.0_hdf5_savedmodel_pb模型转换[2]_第5张图片

5.1.2 h5转saved后的模型转pb

import tensorflow as tf

def freeze_session(model_path=None,clear_devices=True):
    tf.compat.v1.reset_default_graph()
    session=tf.compat.v1.keras.backend.get_session()
    graph = session.graph
    with graph.as_default():
        model = tf.keras.models.load_model(model_path)
        output_names = [out.op.name for out in model.outputs]
        print("output_names",output_names)
        input_names =[innode.op.name for innode in model.inputs]
        print("input_names",input_names)        
        input_graph_def = graph.as_graph_def()
        for node in input_graph_def.node:
            print('node:', node.name)
        print("len node1",len(input_graph_def.node))
        if clear_devices:
            for node in input_graph_def.node:
                node.device = ""
        frozen_graph =  tf.compat.v1.graph_util.convert_variables_to_constants(session, input_graph_def,
                                                      output_names)
        
        outgraph = tf.compat.v1.graph_util.remove_training_nodes(frozen_graph)#去掉与推理无关的内容
        print("##################################################################")
        for node in outgraph.node:
            print('node:', node.name)
        print("length of  node",len(outgraph.node))
        tf.io.write_graph(frozen_graph, "./models", "h5tosaved_savedmodel.pb", as_text=False)

def main():  

    freeze_session("models/h5tosaved",True)
    

main()

output_names ['dense_1/Softmax']
input_names ['input_1']
node: kernel/Initializer/random_uniform/shape
node: kernel/Initializer/random_uniform/min
node: kernel/Initializer/random_uniform/max
node: kernel/Initializer/random_uniform/RandomUniform
node: kernel/Initializer/random_uniform/sub
node: kernel/Initializer/random_uniform/mul
node: kernel/Initializer/random_uniform
node: kernel
node: kernel/IsInitialized/VarIsInitializedOp
node: kernel/Assign
node: kernel/Read/ReadVariableOp
node: bias/Initializer/zeros
node: bias
node: bias/IsInitialized/VarIsInitializedOp
node: bias/Assign
node: bias/Read/ReadVariableOp
node: kernel_1/Initializer/random_uniform/shape
node: kernel_1/Initializer/random_uniform/min
node: kernel_1/Initializer/random_uniform/max
node: kernel_1/Initializer/random_uniform/RandomUniform
node: kernel_1/Initializer/random_uniform/sub
node: kernel_1/Initializer/random_uniform/mul
node: kernel_1/Initializer/random_uniform
node: kernel_1
node: kernel_1/IsInitialized/VarIsInitializedOp
node: kernel_1/Assign
node: kernel_1/Read/ReadVariableOp
node: bias_1/Initializer/zeros
node: bias_1
node: bias_1/IsInitialized/VarIsInitializedOp
node: bias_1/Assign
node: bias_1/Read/ReadVariableOp
node: iter
node: iter/Read/ReadVariableOp
node: beta_1
node: beta_1/Read/ReadVariableOp
node: beta_2
node: beta_2/Read/ReadVariableOp
node: decay
node: decay/Read/ReadVariableOp
node: learning_rate
node: learning_rate/Read/ReadVariableOp
node: dense_6/kernel/m/Initializer/zeros/shape_as_tensor
node: dense_6/kernel/m/Initializer/zeros/Const
node: dense_6/kernel/m/Initializer/zeros
node: dense_6/kernel/m
node: dense_6/kernel/m/IsInitialized/VarIsInitializedOp
node: dense_6/kernel/m/Assign
node: dense_6/kernel/m/Read/ReadVariableOp
node: dense_6/bias/m/Initializer/zeros
node: dense_6/bias/m
node: dense_6/bias/m/IsInitialized/VarIsInitializedOp
node: dense_6/bias/m/Assign
node: dense_6/bias/m/Read/ReadVariableOp
node: dense_1_5/kernel/m/Initializer/zeros/shape_as_tensor
node: dense_1_5/kernel/m/Initializer/zeros/Const
node: dense_1_5/kernel/m/Initializer/zeros
node: dense_1_5/kernel/m
node: dense_1_5/kernel/m/IsInitialized/VarIsInitializedOp
node: dense_1_5/kernel/m/Assign
node: dense_1_5/kernel/m/Read/ReadVariableOp
node: dense_1_5/bias/m/Initializer/zeros
node: dense_1_5/bias/m
node: dense_1_5/bias/m/IsInitialized/VarIsInitializedOp
node: dense_1_5/bias/m/Assign
node: dense_1_5/bias/m/Read/ReadVariableOp
node: dense_6/kernel/v/Initializer/zeros/shape_as_tensor
node: dense_6/kernel/v/Initializer/zeros/Const
node: dense_6/kernel/v/Initializer/zeros
node: dense_6/kernel/v
node: dense_6/kernel/v/IsInitialized/VarIsInitializedOp
node: dense_6/kernel/v/Assign
node: dense_6/kernel/v/Read/ReadVariableOp
node: dense_6/bias/v/Initializer/zeros
node: dense_6/bias/v
node: dense_6/bias/v/IsInitialized/VarIsInitializedOp
node: dense_6/bias/v/Assign
node: dense_6/bias/v/Read/ReadVariableOp
node: dense_1_5/kernel/v/Initializer/zeros/shape_as_tensor
node: dense_1_5/kernel/v/Initializer/zeros/Const
node: dense_1_5/kernel/v/Initializer/zeros
node: dense_1_5/kernel/v
node: dense_1_5/kernel/v/IsInitialized/VarIsInitializedOp
node: dense_1_5/kernel/v/Assign
node: dense_1_5/kernel/v/Read/ReadVariableOp
node: dense_1_5/bias/v/Initializer/zeros
node: dense_1_5/bias/v
node: dense_1_5/bias/v/IsInitialized/VarIsInitializedOp
node: dense_1_5/bias/v/Assign
node: dense_1_5/bias/v/Read/ReadVariableOp
node: input_1
node: flatten/Const
node: flatten/Reshape
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
node: Const
node: RestoreV2/tensor_names
node: RestoreV2/shape_and_slices
node: RestoreV2
node: Identity
node: AssignVariableOp
node: RestoreV2_1/tensor_names
node: RestoreV2_1/shape_and_slices
node: RestoreV2_1
node: Identity_1
node: AssignVariableOp_1
node: RestoreV2_2/tensor_names
node: RestoreV2_2/shape_and_slices
node: RestoreV2_2
node: Identity_2
node: AssignVariableOp_2
node: RestoreV2_3/tensor_names
node: RestoreV2_3/shape_and_slices
node: RestoreV2_3
node: Identity_3
node: AssignVariableOp_3
node: RestoreV2_4/tensor_names
node: RestoreV2_4/shape_and_slices
node: RestoreV2_4
node: Identity_4
node: AssignVariableOp_4
node: RestoreV2_5/tensor_names
node: RestoreV2_5/shape_and_slices
node: RestoreV2_5
node: Identity_5
node: AssignVariableOp_5
node: RestoreV2_6/tensor_names
node: RestoreV2_6/shape_and_slices
node: RestoreV2_6
node: Identity_6
node: AssignVariableOp_6
node: RestoreV2_7/tensor_names
node: RestoreV2_7/shape_and_slices
node: RestoreV2_7
node: Identity_7
node: AssignVariableOp_7
node: RestoreV2_8/tensor_names
node: RestoreV2_8/shape_and_slices
node: RestoreV2_8
node: Identity_8
node: AssignVariableOp_8
node: Identity_9
node: AssignVariableOp_9
node: Identity_10
node: AssignVariableOp_10
node: Identity_11
node: AssignVariableOp_11
node: Identity_12
node: AssignVariableOp_12
node: Identity_13
node: AssignVariableOp_13
node: Identity_14
node: AssignVariableOp_14
node: Identity_15
node: AssignVariableOp_15
node: Identity_16
node: AssignVariableOp_16
node: dense_1_target
node: total/Initializer/zeros
node: total
node: total/IsInitialized/VarIsInitializedOp
node: total/Assign
node: total/Read/ReadVariableOp
node: count/Initializer/zeros
node: count
node: count/IsInitialized/VarIsInitializedOp
node: count/Assign
node: count/Read/ReadVariableOp
node: metrics/accuracy/Squeeze
node: metrics/accuracy/ArgMax/dimension
node: metrics/accuracy/ArgMax
node: metrics/accuracy/Cast
node: metrics/accuracy/Equal
node: metrics/accuracy/Cast_1
node: metrics/accuracy/Const
node: metrics/accuracy/Sum
node: metrics/accuracy/AssignAddVariableOp
node: metrics/accuracy/ReadVariableOp
node: metrics/accuracy/Size
node: metrics/accuracy/Cast_2
node: metrics/accuracy/AssignAddVariableOp_1
node: metrics/accuracy/ReadVariableOp_1
node: metrics/accuracy/div_no_nan/ReadVariableOp
node: metrics/accuracy/div_no_nan/ReadVariableOp_1
node: metrics/accuracy/div_no_nan
node: metrics/accuracy/Identity
node: loss/dense_1_loss/Cast
node: loss/dense_1_loss/Shape
node: loss/dense_1_loss/Reshape/shape
node: loss/dense_1_loss/Reshape
node: loss/dense_1_loss/strided_slice/stack
node: loss/dense_1_loss/strided_slice/stack_1
node: loss/dense_1_loss/strided_slice/stack_2
node: loss/dense_1_loss/strided_slice
node: loss/dense_1_loss/Reshape_1/shape/0
node: loss/dense_1_loss/Reshape_1/shape
node: loss/dense_1_loss/Reshape_1
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits
node: loss/dense_1_loss/weighted_loss/Cast/x
node: loss/dense_1_loss/weighted_loss/Mul
node: loss/dense_1_loss/Const
node: loss/dense_1_loss/Sum
node: loss/dense_1_loss/num_elements
node: loss/dense_1_loss/num_elements/Cast
node: loss/dense_1_loss/Const_1
node: loss/dense_1_loss/Sum_1
node: loss/dense_1_loss/value
node: loss/mul/x
node: loss/mul
node: VarIsInitializedOp
node: VarIsInitializedOp_1
node: VarIsInitializedOp_2
node: VarIsInitializedOp_3
node: VarIsInitializedOp_4
node: VarIsInitializedOp_5
node: VarIsInitializedOp_6
node: VarIsInitializedOp_7
node: VarIsInitializedOp_8
node: VarIsInitializedOp_9
node: VarIsInitializedOp_10
node: VarIsInitializedOp_11
node: VarIsInitializedOp_12
node: VarIsInitializedOp_13
node: init
len node1 233
INFO:tensorflow:Froze 4 variables.
INFO:tensorflow:Converted 4 variables to const ops.
##################################################################
node: kernel
node: bias
node: kernel_1
node: bias_1
node: input_1
node: flatten/Const
node: flatten/Reshape
node: dense/MatMul
node: dense/BiasAdd
node: dense/Relu
node: dense_1/MatMul
node: dense_1/BiasAdd
node: dense_1/Softmax
length of  node 13

5.1.3 h5转saved模型后转pb推理

#use tf1.14 and tf2.x with pb to load the data are both ok
import tensorflow as tf 
from PIL import Image
import numpy as np

def load_graph(file_path):
    with tf.io.gfile.GFile(file_path,'rb') as f:
        graph_def = tf.compat.v1.GraphDef()
        graph_def.ParseFromString(f.read())
    with tf.compat.v1.Graph().as_default() as graph:
        tf.import_graph_def(graph_def,input_map = None,return_elements = None,name = "",op_dict = None,producer_op_list = None)
    graph_nodes = [n for n in graph_def.node]
    return graph,graph_nodes
def main():
    file_path='./models/h5tosaved_savedmodel.pb'
    img= np.array(Image.open('5.png')).reshape(1,28,28,1)/255.0
    graph,graph_nodes = load_graph(file_path)
    print("num nodes",len(graph_nodes))
    for node in graph_nodes:
        print('node:', node.name)

    input_node = graph.get_tensor_by_name('input_1:0')
    print("input_node.shape:",input_node.shape)
    output = graph.get_tensor_by_name('dense_1/Softmax:0')  

    with tf.compat.v1.Session(graph=graph) as sess:
        logits = sess.run(output, feed_dict = {input_node:img})
    print("logits:",logits)
    np.save('out_results/h5tosaved_savedmodelpb_result.npy',logits)
main()


num nodes 17
node: kernel
node: bias
node: kernel_1
node: bias_1
node: input_1
node: flatten/Const
node: flatten/Reshape
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
input_node.shape: (None, 28, 28, 1)
logits: [[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

以上过程说明，h5转saved没问题，以后saved转pb也是可以

5.2 saved model转h5

def main():
    file_path='./models/lenet5'
    model = tf.keras.models.load_model(file_path)
    model.save('./models/savedtoh5.h5',save_format='h5')
    
main()

5.2.1 saved转h5后的模型推理

import tensorflow as tf
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
    
def h5_infer(model_path=None,img=None):
    model = tf.keras.models.load_model(model_path)
    result= model.predict(img)
    return result

def main():
    model_path = "models/savedtoh5.h5"
    img = Image.open('5.png')
    plt.imshow(img)
    img= np.array(img).reshape(1,28,28,1)/255.0
    result = h5_infer(model_path,img)
    print("result.shape",result.shape)
    print(result)
    np.save('out_results/savedtoh5_result.npy',result)#保存结果，方便以后比较
main()

result.shape (1, 10)
[[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

【Tensorflow2.0】8、tensorflow2.0_hdf5_savedmodel_pb模型转换[2]_第6张图片

5.2.2 saved 转h5后的模型转pb

# use tf2.x(tf1.14 also ok) to convert the model hdf5 trained by tf2.x to pb
import tensorflow as tf

def freeze_session(model_path=None,clear_devices=True):
    tf.compat.v1.reset_default_graph()
    session=tf.compat.v1.keras.backend.get_session()
    graph = session.graph
    with graph.as_default():
        model = tf.keras.models.load_model(model_path)
        output_names = [out.op.name for out in model.outputs]
        print("output_names",output_names)
        input_names =[innode.op.name for innode in model.inputs]
        print("input_names",input_names)
        input_graph_def = graph.as_graph_def()
        for node in input_graph_def.node:
            print('node:', node.name)
        print("len node1",len(input_graph_def.node))
        if clear_devices:
            for node in input_graph_def.node:
                node.device = ""
        frozen_graph =  tf.compat.v1.graph_util.convert_variables_to_constants(session, input_graph_def,
                                                      output_names)
        
        outgraph = tf.compat.v1.graph_util.remove_training_nodes(frozen_graph)#去掉与推理无关的内容
        print("##################################################################")
        for node in outgraph.node:
            print('node:', node.name)
        print("length of  node",len(outgraph.node))
        tf.io.write_graph(frozen_graph, "./models", "savedtoh5_h5.pb", as_text=False)
        return outgraph

def main():  

    freeze_session("models/savedtoh5.h5",True)

main()

output_names ['dense_1/Softmax']
input_names ['flatten_input']
node: flatten_input
node: flatten/Const
node: flatten/Reshape
node: dense/kernel/Initializer/random_uniform/shape
node: dense/kernel/Initializer/random_uniform/min
node: dense/kernel/Initializer/random_uniform/max
node: dense/kernel/Initializer/random_uniform/RandomUniform
node: dense/kernel/Initializer/random_uniform/sub
node: dense/kernel/Initializer/random_uniform/mul
node: dense/kernel/Initializer/random_uniform
node: dense/kernel
node: dense/kernel/IsInitialized/VarIsInitializedOp
node: dense/kernel/Assign
node: dense/kernel/Read/ReadVariableOp
node: dense/bias/Initializer/zeros
node: dense/bias
node: dense/bias/IsInitialized/VarIsInitializedOp
node: dense/bias/Assign
node: dense/bias/Read/ReadVariableOp
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/kernel/Initializer/random_uniform/shape
node: dense_1/kernel/Initializer/random_uniform/min
node: dense_1/kernel/Initializer/random_uniform/max
node: dense_1/kernel/Initializer/random_uniform/RandomUniform
node: dense_1/kernel/Initializer/random_uniform/sub
node: dense_1/kernel/Initializer/random_uniform/mul
node: dense_1/kernel/Initializer/random_uniform
node: dense_1/kernel
node: dense_1/kernel/IsInitialized/VarIsInitializedOp
node: dense_1/kernel/Assign
node: dense_1/kernel/Read/ReadVariableOp
node: dense_1/bias/Initializer/zeros
node: dense_1/bias
node: dense_1/bias/IsInitialized/VarIsInitializedOp
node: dense_1/bias/Assign
node: dense_1/bias/Read/ReadVariableOp
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
node: Placeholder
node: AssignVariableOp
node: ReadVariableOp
node: Placeholder_1
node: AssignVariableOp_1
node: ReadVariableOp_1
node: Placeholder_2
node: AssignVariableOp_2
node: ReadVariableOp_2
node: Placeholder_3
node: AssignVariableOp_3
node: ReadVariableOp_3
node: VarIsInitializedOp
node: VarIsInitializedOp_1
node: VarIsInitializedOp_2
node: VarIsInitializedOp_3
node: init
node: dense_1_target
node: total/Initializer/zeros
node: total
node: total/IsInitialized/VarIsInitializedOp
node: total/Assign
node: total/Read/ReadVariableOp
node: count/Initializer/zeros
node: count
node: count/IsInitialized/VarIsInitializedOp
node: count/Assign
node: count/Read/ReadVariableOp
node: metrics/accuracy/Squeeze
node: metrics/accuracy/ArgMax/dimension
node: metrics/accuracy/ArgMax
node: metrics/accuracy/Cast
node: metrics/accuracy/Equal
node: metrics/accuracy/Cast_1
node: metrics/accuracy/Const
node: metrics/accuracy/Sum
node: metrics/accuracy/AssignAddVariableOp
node: metrics/accuracy/ReadVariableOp
node: metrics/accuracy/Size
node: metrics/accuracy/Cast_2
node: metrics/accuracy/AssignAddVariableOp_1
node: metrics/accuracy/ReadVariableOp_1
node: metrics/accuracy/div_no_nan/ReadVariableOp
node: metrics/accuracy/div_no_nan/ReadVariableOp_1
node: metrics/accuracy/div_no_nan
node: metrics/accuracy/Identity
node: loss/dense_1_loss/Cast
node: loss/dense_1_loss/Shape
node: loss/dense_1_loss/Reshape/shape
node: loss/dense_1_loss/Reshape
node: loss/dense_1_loss/strided_slice/stack
node: loss/dense_1_loss/strided_slice/stack_1
node: loss/dense_1_loss/strided_slice/stack_2
node: loss/dense_1_loss/strided_slice
node: loss/dense_1_loss/Reshape_1/shape/0
node: loss/dense_1_loss/Reshape_1/shape
node: loss/dense_1_loss/Reshape_1
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape
node: loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits
node: loss/dense_1_loss/weighted_loss/Cast/x
node: loss/dense_1_loss/weighted_loss/Mul
node: loss/dense_1_loss/Const
node: loss/dense_1_loss/Sum
node: loss/dense_1_loss/num_elements
node: loss/dense_1_loss/num_elements/Cast
node: loss/dense_1_loss/Const_1
node: loss/dense_1_loss/Sum_1
node: loss/dense_1_loss/value
node: loss/mul/x
node: loss/mul
len node1 115
INFO:tensorflow:Froze 4 variables.
INFO:tensorflow:Converted 4 variables to const ops.
##################################################################
node: flatten_input
node: flatten/Const
node: flatten/Reshape
node: dense/kernel
node: dense/bias
node: dense/MatMul
node: dense/BiasAdd
node: dense/Relu
node: dense_1/kernel
node: dense_1/bias
node: dense_1/MatMul
node: dense_1/BiasAdd
node: dense_1/Softmax
length of  node 13

5.2.3 saved转h5后模型转pb后的推理

#use tf1.14 and tf2.x with pb to load the data are both ok
import tensorflow as tf 
from PIL import Image
import numpy as np

def load_graph(file_path):
    with tf.io.gfile.GFile(file_path,'rb') as f:
        graph_def = tf.compat.v1.GraphDef()
        graph_def.ParseFromString(f.read())
    with tf.compat.v1.Graph().as_default() as graph:
        tf.import_graph_def(graph_def,input_map = None,return_elements = None,name = "",op_dict = None,producer_op_list = None)
    graph_nodes = [n for n in graph_def.node]
    return graph,graph_nodes
def main():
    file_path='./models/savedtoh5_h5.pb'
    img= np.array(Image.open('5.png')).reshape(1,28,28,1)/255.0
    graph,graph_nodes = load_graph(file_path)
    print("num nodes",len(graph_nodes))
    for node in graph_nodes:
        print('node:', node.name)

    input_node = graph.get_tensor_by_name('flatten_input:0')
    print("input_node.shape:",input_node.shape)
    output = graph.get_tensor_by_name('dense_1/Softmax:0')  

    with tf.compat.v1.Session(graph=graph) as sess:
        logits = sess.run(output, feed_dict = {input_node:img})
    print("logits:",logits)
    np.save('out_results/savedtoh5_pb_result.npy',logits)
main()


num nodes 17
node: flatten_input
node: flatten/Const
node: flatten/Reshape
node: dense/kernel
node: dense/bias
node: dense/MatMul/ReadVariableOp
node: dense/MatMul
node: dense/BiasAdd/ReadVariableOp
node: dense/BiasAdd
node: dense/Relu
node: dense_1/kernel
node: dense_1/bias
node: dense_1/MatMul/ReadVariableOp
node: dense_1/MatMul
node: dense_1/BiasAdd/ReadVariableOp
node: dense_1/BiasAdd
node: dense_1/Softmax
input_node.shape: (None, 28, 28, 1)
logits: [[2.6573987e-14 1.6878349e-10 1.6627098e-07 1.4200980e-04 1.8240679e-23
  9.9985778e-01 4.3281314e-16 4.1571907e-12 2.4773154e-12 3.5959408e-10]]

6、互转部分总结

对于所有模型的互转我们在精度上和模型大小上进行总结。因为这前把所有推理结果都保存了，自然就直接可以对比的

6.1 精度对比

所有模型的结果都保存在out_results中，都读取出来然后进行比较

import numpy as np
# h5模型结果
h5_result=np.load('out_results/h5_result.npy')
# h5转pb后的pb模型的结果
h5pb_result=np.load('out_results/h5pb_result.npy')
# h5转savedmodel的模型的结果
h5tosavedmodel_result=np.load('out_results/h5tosavedmodel_result.npy')
# h5转savedmodel的模型的另一种调用方法做的结果，也就是说模型相同，但调用方法不同
h5tosavedmodelanother_result=np.load('out_results/h5tosavedmodelanother_result.npy')
############################分割线################################
#saved model 结果
savedmodel_result=np.load('out_results/savedmodel_result.npy')
#saved model 另一种调用方式的结果
savedmodelanother_result=np.load('out_results/savedmodelanother_result.npy')
#saved model 转pb 的结果
savedmodelpb_result=np.load('out_results/savedmodelpb_result.npy')
#saved 模型转h5模型的推理结果
savedtoh5_result=np.load('out_results/savedtoh5_result.npy')
#saved 模型转 h5后转pb的结果
savedtoh5_pb_result=np.load('out_results/savedtoh5_pb_result.npy')

以上一共有10个结果我们都与第一个做对比即可

np.testing.assert_array_almost_equal(h5_result,h5pb_result)
np.testing.assert_array_almost_equal(h5_result,h5tosavedmodel_result)
np.testing.assert_array_almost_equal(h5_result,h5tosavedmodelanother_result)
np.testing.assert_array_almost_equal(h5_result,savedmodel_result)
np.testing.assert_array_almost_equal(h5_result,savedmodelanother_result)
np.testing.assert_array_almost_equal(h5_result,savedmodelpb_result)
np.testing.assert_array_almost_equal(h5_result,savedtoh5_result)
np.testing.assert_array_almost_equal(h5_result,savedtoh5_pb_result)

以上代码执行过程中，没有报任何信息，说明所有结果全部相同

6.2 模型大小对比

一共有8个模型我们对比模型大小以及md5sum值来查看

%%bash
#各个h5模型的比较，有两个
#第一个原始的h5模型
du models/lenet5.h5
md5sum -b models/lenet5.h5
#第二个模型 saved 转换成的h5模型
du models/savedtoh5.h5
md5sum -b models/savedtoh5.h5

4800	models/lenet5.h5
810d4ceb0ac0c5de599528378b84c1a9 *models/lenet5.h5
1604	models/savedtoh5.h5
19067c2a5d4587521e2d77df582abd30 *models/savedtoh5.h5

可以看到，saved model转的h5模型小不少，但是结果是一样的

%%bash
#所有saved model的比较，有两个
#第一个是原始的saved model 
du models/lenet5
md5sum -b models/lenet5/saved_model.pb
#第二个是h5转换的saved 模型
du models/h5tosaved
md5sum -b models/h5tosaved/saved_model.pb

4784	models/lenet5/variables
4	models/lenet5/assets
4868	models/lenet5
5064cad4d06f58b98c2013a34e65a658 *models/lenet5/saved_model.pb
4784	models/h5tosaved/variables
4	models/h5tosaved/assets
4864	models/h5tosaved
6a9a41e1f3e7ee543934faa793be2962 *models/h5tosaved/saved_model.pb

从以上可以看出二都差不多大

%%bash
#所有pb模型的比较，共有四个
#第一个h5转的pb
du models/lenet5_h5.pb
md5sum -b models/lenet5_h5.pb
#第二个saved model转pb模型
du models/lenet5_savedmodel.pb
md5sum -b models/lenet5_savedmodel.pb
#第三个模型是h5转savedmodel后再转的pb
du models/h5tosaved_savedmodel.pb
md5sum -b models/h5tosaved_savedmodel.pb
#第四个saved 模型转h5再转pb模型
du models/savedtoh5_h5.pb
md5sum -b models/savedtoh5_h5.pb

1592	models/lenet5_h5.pb
1c76f6947f41758bee1c0892877dfea2 *models/lenet5_h5.pb
1636	models/lenet5_savedmodel.pb
c37c6991c6192b11d88b890f13c953f0 *models/lenet5_savedmodel.pb
1632	models/h5tosaved_savedmodel.pb
a00a3395a985482bf2a3cc365505ec48 *models/h5tosaved_savedmodel.pb
1592	models/savedtoh5_h5.pb
a7239f1e842e761aaf75fb79ddfd0e04 *models/savedtoh5_h5.pb

以上四个模型大小相差不大，但不完全相同，还不清楚是什么是原因

总结：

以上为本文第一部分,所用环境为tensorflow2.2gpu版

  • h5和saved可以互转
  • 互转后的模型可以顺利完成后续所有工作，总的来说精度是一样的，大小saved model转h5模型最小，和所有pb差不多大
  • pb模型结点名称各种h5转来的一样，saved model 转pb的名称一样

你可能感兴趣的:(#,Tensorflow,saved模型转h5,saved模型转pb,h5模型转pb,tensorflow)

  • 机器学习与深度学习间关系与区别 ℒℴѵℯ心·动ꦿ໊ོ꫞ 人工智能学习深度学习python
    一、机器学习概述定义机器学习（MachineLearning,ML）是一种通过数据驱动的方法，利用统计学和计算算法来训练模型，使计算机能够从数据中学习并自动进行预测或决策。机器学习通过分析大量数据样本，识别其中的模式和规律，从而对新的数据进行判断。其核心在于通过训练过程，让模型不断优化和提升其预测准确性。主要类型1.监督学习（SupervisedLearning）监督学习是指在训练数据集中包含输入
  • LocalDateTime 转 String igotyback java开发语言
    importjava.time.LocalDateTime;importjava.time.format.DateTimeFormatter;publicclassMain{publicstaticvoidmain(String[]args){//获取当前时间LocalDateTimenow=LocalDateTime.now();//定义日期格式化器DateTimeFormatterformat
  • 消息中间件有哪些常见类型 xmh-sxh-1314 java
    消息中间件根据其设计理念和用途，可以大致分为以下几种常见类型：点对点消息队列（Point-to-PointMessagingQueues）：在这种模型中，消息被发送到特定的队列中，消费者从队列中取出并处理消息。队列中的消息只能被一个消费者消费，消费后即被删除。常见的实现包括IBM的MQSeries、RabbitMQ的部分使用场景等。适用于任务分发、负载均衡等场景。发布/订阅消息模型（Pub/Sub
  • 直抒《紫罗兰永恒花园外传》 雷姆的黑色童话
    没看过《紫罗兰永恒花园》的我莫名的看完了《紫罗兰永恒花园外传》，又莫名的被故事中的姐妹之情狠狠地感动了的一把。感动何在：困苦中相依为命的姐妹二人被迫分离，用一个人的自由换取另一个人的幸福。之后，虽相隔不知几许依旧心心念念彼此牵挂。这种深深的姐妹情谊就是令我为之动容的所在。贝拉和泰勒分别影片开始，海天之间一个孩童凭栏眺望，手中拿着折旧的信纸。镜头一转，挑灯伏案的薇尔莉特正在打字机前奋笔疾书。这些片段
  • LLM 词汇表 落难Coder LLMsNLP大语言模型大模型llama人工智能
    Contextwindow“上下文窗口”是指语言模型在生成新文本时能够回溯和参考的文本量。这不同于语言模型训练时所使用的大量数据集，而是代表了模型的“工作记忆”。较大的上下文窗口可以让模型理解和响应更复杂和更长的提示，而较小的上下文窗口可能会限制模型处理较长提示或在长时间对话中保持连贯性的能力。Fine-tuning微调是使用额外的数据进一步训练预训练语言模型的过程。这使得模型开始表示和模仿微调数
  • 探索OpenAI和LangChain的适配器集成：轻松切换模型提供商 nseejrukjhad langchaineasyui前端python
    #探索OpenAI和LangChain的适配器集成：轻松切换模型提供商##引言在人工智能和自然语言处理的世界中，OpenAI的模型提供了强大的能力。然而，随着技术的发展，许多人开始探索其他模型以满足特定需求。LangChain作为一个强大的工具，集成了多种模型提供商，通过提供适配器，简化了不同模型之间的转换。本篇文章将介绍如何使用LangChain的适配器与OpenAI集成，以便轻松切换模型提供商
  • 使用Apify加载Twitter消息以进行微调的完整指南 nseejrukjhad twittereasyui前端python
    #使用Apify加载Twitter消息以进行微调的完整指南##引言在自然语言处理领域，微调模型以适应特定任务是提升模型性能的常见方法。本文将介绍如何使用Apify从Twitter导出聊天信息，以便进一步进行微调。##主要内容###使用Apify导出推文首先，我们需要从Twitter导出推文。Apify可以帮助我们做到这一点。通过Apify的强大功能，我们可以批量抓取和导出数据，适用于各类应用场景。
  • 如何部分格式化提示模板:LangChain中的高级技巧 nseejrukjhad langchainjava服务器python
    标题:如何部分格式化提示模板:LangChain中的高级技巧内容:如何部分格式化提示模板:LangChain中的高级技巧引言在使用大型语言模型(LLM)时,提示工程是一个关键环节。LangChain提供了强大的提示模板功能,让我们能更灵活地构建和管理提示。本文将介绍LangChain中一个高级特性-部分格式化提示模板,这个技巧可以让你的提示管理更加高效和灵活。什么是部分格式化提示模板?部分格式化提
  • 人工智能时代，程序员如何保持核心竞争力？ jmoych 人工智能
    随着AIGC（如chatgpt、midjourney、claude等）大语言模型接二连三的涌现，AI辅助编程工具日益普及，程序员的工作方式正在发生深刻变革。有人担心AI可能取代部分编程工作，也有人认为AI是提高效率的得力助手。面对这一趋势,程序员应该如何应对?是专注于某个领域深耕细作，还是广泛学习以适应快速变化的技术环境?又或者，我们是否应该将重点转向AI无法轻易替代的软技能？让我们一起探讨程序员
  • 数据仓库——维度表一致性 墨染丶eye 背诵数据仓库
    数据仓库基础笔记思维导图已经整理完毕，完整连接为：数据仓库基础知识笔记思维导图维度一致性问题从逻辑层面来看，当一系列星型模型共享一组公共维度时，所涉及的维度称为一致性维度。当维度表存在不一致时，短期的成功难以弥补长期的错误。维度时确保不同过程中信息集成起来实现横向钻取货活动的关键。造成横向钻取失败的原因维度结构的差别，因为维度的差别，分析工作涉及的领域从简单到复杂，但是都是通过复杂的报表来弥补设计
  • 【华为OD技术面试真题 - 技术面】- python八股文真题题库（1） 算法大师 华为od面试python
    华为OD面试真题精选专栏：华为OD面试真题精选目录:2024华为OD面试手撕代码真题目录以及八股文真题目录文章目录华为OD面试真题精选1.数据预处理流程数据预处理的主要步骤工具和库2.介绍线性回归、逻辑回归模型线性回归（LinearRegression）模型形式：关键点：逻辑回归（LogisticRegression）模型形式：关键点：参数估计与评估：3.python浅拷贝及深拷贝浅拷贝（Shal
  • Xinference如何注册自定义模型 玩人工智能的辣条哥 人工智能AI大模型Xinference
    环境：Xinference问题描述：Xinference如何注册自定义模型解决方案：1.写个model_config.json，内容如下{"version":1,"context_length":2048,"model_name":"custom-llama-3","model_lang":["en","ch"],"model_ability":["generate","chat"],"model
  • Python中深拷贝与浅拷贝的区别 yuxiaoyu.
    转自：http://blog.csdn.net/u014745194/article/details/70271868定义：在Python中对象的赋值其实就是对象的引用。当创建一个对象，把它赋值给另一个变量的时候，python并没有拷贝这个对象，只是拷贝了这个对象的引用而已。浅拷贝：拷贝了最外围的对象本身，内部的元素都只是拷贝了一个引用而已。也就是，把对象复制一遍，但是该对象中引用的其他对象我不复
  • Python开发常用的三方模块如下： 换个网名有点难 python开发语言
    Python是一门功能强大的编程语言，拥有丰富的第三方库，这些库为开发者提供了极大的便利。以下是100个常用的Python库，涵盖了多个领域：1、NumPy，用于科学计算的基础库。2、Pandas，提供数据结构和数据分析工具。3、Matplotlib，一个绘图库。4、Scikit-learn，机器学习库。5、SciPy，用于数学、科学和工程的库。6、TensorFlow，由Google开发的开源机
  • 希望和悲伤都是照亮我们人生的一缕光 山月映雪
    我开始并不想读《云边有个小卖部》，但看到好几个学生就都在读这本书，为了了解学生的阅读实际，我就拿起这本书翻看起来。读了十几页，发现小说的语言中不时有一些粗俗的字眼，感觉自己读不下去了。小说一开始把云边镇风景写的特别的美好，我错判为脱离现实的鸳鸯蝴蝶派小说，对于人为制造的童话世界的人与物，我真的不太感兴趣，所以就没有再读了。有天在教室闲转，顺手又拿起了这本书看了起来，这次我才真的看进去了。这部小说除
  • 网络编程基础 记得开心一点啊 网络
    目录♫什么是网络编程♫Socket套接字♪什么是Socket套接字♪数据报套接字♪流套接字♫数据报套接字通信模型♪数据报套接字通讯模型♪DatagramSocket♪DatagramPacket♪实现UDP的服务端代码♪实现UDP的客户端代码♫流套接字通信模型♪流套接字通讯模型♪ServerSocket♪Socket♪实现TCP的服务端代码♪实现TCP的客户端代码♫什么是网络编程网络编程，指网络上
  • 简单了解 JVM 记得开心一点啊 jvm
    目录♫什么是JVM♫JVM的运行流程♫JVM运行时数据区♪虚拟机栈♪本地方法栈♪堆♪程序计数器♪方法区/元数据区♫类加载的过程♫双亲委派模型♫垃圾回收机制♫什么是JVMJVM是JavaVirtualMachine的简称，意为Java虚拟机。虚拟机是指通过软件模拟的具有完整硬件功能的、运行在一个完全隔离的环境中的完整计算机系统（如：JVM、VMwave、VirtualBox）。JVM和其他两个虚拟机
  • Python实现简单的机器学习算法 master_chenchengg pythonpython办公效率python开发IT
    Python实现简单的机器学习算法开篇：初探机器学习的奇妙之旅搭建环境：一切从安装开始必备工具箱第一步：安装Anaconda和JupyterNotebook小贴士：如何配置Python环境变量算法初体验：从零开始的Python机器学习线性回归：让数据说话数据准备：从哪里找数据编码实战：Python实现线性回归模型评估：如何判断模型好坏逻辑回归：从分类开始理论入门：什么是逻辑回归代码实现：使用skl
  • 推荐算法_隐语义-梯度下降 _feivirus_ 算法机器学习和数学推荐算法机器学习隐语义
    importnumpyasnp1.模型实现"""inputrate_matrix:M行N列的评分矩阵，值为P*Q.P:初始化用户特征矩阵M*K.Q:初始化物品特征矩阵K*N.latent_feature_cnt:隐特征的向量个数max_iteration:最大迭代次数alpha:步长lamda:正则化系数output分解之后的P和Q"""defLFM_grad_desc(rate_matrix,l
  • 基于Python给出的PDF文档转Markdown文档的方法 程序媛了了 pythonpdf开发语言
    注：网上有很多将Markdown文档转为PDF文档的方法，但是却很少有将PDF文档转为Markdown文档的方法。就算有，比如某些网站声称可以将PDF文档转为Markdown文档，尝试过，不太符合自己的要求，而且无法保证文档没有泄露风险。于是本人为了解决这个问题，借助GPT（能使用GPT镜像或者有条件直接使用GPT的，反正能调用GPT接口就行）生成Python代码来完成这个功能。笔记、代码难免存在
  • BART&BERT Ambition_LAO 深度学习
    BART和BERT都是基于Transformer架构的预训练语言模型。模型架构：BERT(BidirectionalEncoderRepresentationsfromTransformers)主要是一个编码器（Encoder）模型，它使用了Transformer的编码器部分来处理输入的文本，并生成文本的表示。BERT特别擅长理解语言的上下文，因为它在预训练阶段使用了掩码语言模型（MLM）任务，即
  • 系统架构设计师 需求分析篇二 AmHardy 软件架构设计师系统架构需求分析面向对象分析分析模型UML和SysML
    面向对象分析方法1.用例模型构建用例模型一般需要经历4个阶段：识别参与者：识别与系统交互的所有事物。合并需求获得用例：将需求分配给予其相关的参与者。细化用例描述：详细描述每个用例的功能。调整用例模型：优化用例之间的关系和结构，前三个阶段是必需的。2.用例图的三元素参与者：使用系统的用户或其他外部系统和设备。用例：系统所提供的服务。通信关联：参与者和用例之间的关系，或用例与用例之间的关系。3.识别参
  • 难念的经 轩辕一风
    今天中午从公司出来办事，站在马路旁边招手打的。不久来了一辆，路边停下，坐上，一转脸准备告诉师傅去哪的地址，惊呼，姚师傅？啊，咋是你？这也太巧了吧。在上海，出租车少说也有上万辆吧，而且地方这么大，况且在我出来的这个时间点上碰上了，有时候解释不了，就是那么巧。我和姚师傅咋认识的呢？因工作的原因，我要经常去外地出差，家住的离火车站比较远，每次都是打车过去。可能家在郊区的原因，平时门口公路上的出租车并不多
  • python tif转png Python与遥感 python开发语言
    importosfromosgeoimportgdalimportnumpyasnpfromPILimportImage#提取432三波段fromspectralimport*#输入文件夹路径defget_img(dataset_img):width=dataset_img.RasterXSize#获取行列数height=dataset_img.RasterYSizebands=dataset_i
  • python怎么将png转为tif_png转tif weixin_39977276
    发国外的文章要求图片是tif，cmyk色彩空间的。大小尺寸还有要求。比如网上大神多，找到了一段代码，感谢！https://www.jianshu.com/p/ec2af4311f56https://github.com/KevinZc007/image2Tifimportjava.awt.image.BufferedImage;importjava.io.File;importjava.io.Fi
  • 如何用matlab灵活控制feko的求解 NingrLi matlab开发语言
    https://bbs.rfeda.cn/read.php?tid=3778Feko中的模型和求解设置等都可以通过editfeko进行设置，其文件存储为.pre文件，该文件可以用文本打开，因此，我们可以通过VB、VC、matlab等工具对.pre文件进行读写操作，以达到更灵活的使用feko。同样，对于.out文件，我们也可以进行读操作。熟练使用对.pre文件和.out文件的操作后，我们可以方便的计
  • tiff批量转png 诺有缸的高飞鸟 opencv图像处理pythonopencv图像处理
    目录写在前面代码完写在前面1、本文内容tiff批量转png2、平台/环境opencv,python3、转载请注明出处：https://blog.csdn.net/qq_41102371/article/details/132975023代码importnumpyasnpimportcv2importosdeffindAllFile(base):file_list=[]forroot,ds,fsin
  • 计算机网络八股总结 Petrichorzncu 八股总结计算机网络笔记
    这里写目录标题网络模型划分（五层和七层）及每一层的功能五层网络模型七层网络模型（OSI模型）==三次握手和四次挥手具体过程及原因==三次握手四次挥手TCP/IP协议组成==UDP协议与TCP/IP协议的区别==Http协议相关知识网络地址，子网掩码等相关计算网络模型划分（五层和七层）及每一层的功能五层网络模型应用层：负责处理网络应用程序，如电子邮件、文件传输和网页浏览。主要协议包括HTTP、FTP
  • 《转介绍方法论》学习笔记 小可乐的妈妈
    一、高效转介绍的流程：价值观---执行----方案一）转介绍发生的背景：1、对象：谁向谁转介绍？全员营销，人人参与。①员工的激励政策、客户的转介绍诱因制作客户画像：a信任；支付能力；意愿度；便利度（根据家长具备四个特征的个数分为四类）B性格分类C职业分类D年龄性别②执行：套路，策略，方法，流程2、诱因：为什么要转介绍？认同信任；多方共赢；传递美好；零风险承诺打动人心，超越期待。选择做教育，就是选择
  • 2022-06-29 感恩学习相信小陶
    感恩！六点签到相信很多人都有过这样的经验，拼命想的时候答案怎么都想不出来，不去想的时候，答案却自动冒出来了。为什么？这是因为潜意识也会工作，它非常神奇。你要相信，那些百思不得其解的问题早已扎根在你的头脑中，即使你不再刻意去想，潜意识也会自动围着它转。或许有一天，你会突然得到答案。这也是为什么有时我们会有顿悟的感觉。学会等待，也是进行持续思考的一个重要方法。
  • 深入浅出Java Annotation(元注解和自定义注解） Josh_Persistence Java Annotation元注解自定义注解
    一、基本概述     　　 Annontation是Java5开始引入的新特征。中文名称一般叫注解。它提供了一种安全的类似注释的机制，用来将任何的信息或元数据（metadata）与程序元素（类、方法、成员变量等）进行关联。   　　更通俗的意思是为程序的元素（类、方法、成员变量）加上更直观更明了的说明，这些说明信息是与程序的业务逻辑无关，并且是供指定的工具或
  • mysql优化特定类型的查询 annan211 java工作mysql
    本节所介绍的查询优化的技巧都是和特定版本相关的，所以对于未来mysql的版本未必适用。 1 优化count查询 对于count这个函数的网上的大部分资料都是错误的或者是理解的都是一知半解的。在做优化之前我们先来看看 真正的count()函数的作用到底是什么。 count()是一个特殊的函数，有两种非常不同的作用，他可以统计某个列值的数量，也可以统计行数。 在统
  • MAC下安装多版本JDK和切换几种方式 棋子chessman jdk
    环境： MAC AIR,OS X 10.10,64位   历史： 过去 Mac 上的 Java 都是由 Apple 自己提供，只支持到 Java 6，并且OS X 10.7 开始系统并不自带（而是可选安装）（原自带的是1.6）。 后来 Apple 加入 OpenJDK 继续支持 Java 6，而 Java 7 将由 Oracle 负责提供。   在终端中输入jav
  • javaScript （1） Array_06 JavaScriptjava浏览器
    JavaScript 1、运算符 　　运算符就是完成操作的一系列符号，它有七类： 　　赋值运算符（=,+=,-=,*=,/=,%=,<<=,>>=,|=,&=）、算术运算符(+,-,*,/,++,--,%)、比较运算符(>,<,<=,>=,==,===,!=,!==)、逻辑运算符(||,&&,!)、条件运算(?:)、位
  • 国内顶级代码分享网站 袁潇含 javajdkoracle.netPHP
           现在国内很多开源网站感觉都是为了利益而做的                  当然利益是肯定的,否则谁也不会免费的去做网站      &
  • Elasticsearch、MongoDB和Hadoop比较 随意而生 mongodbhadoop搜索引擎
      IT界在过去几年中出现了一个有趣的现象。很多新的技术出现并立即拥抱了“大数据”。稍微老一点的技术也会将大数据添进自己的特性，避免落大部队太远，我们看到了不同技术之间的边际的模糊化。假如你有诸如Elasticsearch或者Solr这样的搜索引擎，它们存储着JSON文档，MongoDB存着JSON文档，或者一堆JSON文档存放在一个Hadoop集群的HDFS中。你可以使用这三种配
  • mac os 系统科研软件总结 张亚雄 mac os
    1.1 Microsoft Office for Mac 2011      大客户版，自行搜索。      1.2 Latex （MacTex）:      系统环境：https://tug.org/mactex/     &nb
  • Maven实战（四）生命周期 AdyZhang maven
    1. 三套生命周期     Maven拥有三套相互独立的生命周期，它们分别为clean，default和site。 每个生命周期包含一些阶段，这些阶段是有顺序的，并且后面的阶段依赖于前面的阶段，用户和Maven最直接的交互方式就是调用这些生命周期阶段。 以clean生命周期为例，它包含的阶段有pre-clean, clean 和 post
  • Linux下Jenkins迁移 aijuans Jenkins
    1. 将Jenkins程序目录copy过去      源程序在/export/data/tomcatRoot/ofctest-jenkins.jd.com下面            tar -cvzf jenkins.tar.gz ofctest-jenkins.jd.com &
  • request.getInputStream()只能获取一次的问题 ayaoxinchao requestInputstream
    问题：在使用HTTP协议实现应用间接口通信时，服务端读取客户端请求过来的数据，会用到request.getInputStream()，第一次读取的时候可以读取到数据，但是接下来的读取操作都读取不到数据   原因： 1. 一个InputStream对象在被读取完成后，将无法被再次读取，始终返回-1； 2. InputStream并没有实现reset方法（可以重
  • 数据库SQL优化大总结之 百万级数据库优化方案 BigBird2012 SQL优化
    网上关于SQL优化的教程很多，但是比较杂乱。近日有空整理了一下，写出来跟大家分享一下，其中有错误和不足的地方，还请大家纠正补充。 这篇文章我花费了大量的时间查找资料、修改、排版，希望大家阅读之后，感觉好的话推荐给更多的人，让更多的人看到、纠正以及补充。 1.对查询进行优化，要尽量避免全表扫描，首先应考虑在 where 及 order by 涉及的列上建立索引。 2.应尽量避免在 where
  • jsonObject的使用 bijian1013 javajson
            在项目中难免会用java处理json格式的数据，因此封装了一个JSONUtil工具类。 JSONUtil.java package com.bijian.json.study; import java.util.ArrayList; import java.util.Date; import java.util.HashMap;
  • [Zookeeper学习笔记之六]Zookeeper源代码分析之Zookeeper.WatchRegistration bit1129 zookeeper
    Zookeeper类是Zookeeper提供给用户访问Zookeeper service的主要API，它包含了如下几个内部类     首先分析它的内部类，从WatchRegistration开始，为指定的znode path注册一个Watcher，   /** * Register a watcher for a particular p
  • 【Scala十三】Scala核心七：部分应用函数 bit1129 scala
    何为部分应用函数？ Partially applied function: A function that’s used in an expression and that misses some of its arguments.For instance, if function f has type Int => Int => Int, then f and f(1) are p
  • Tomcat Error listenerStart 终极大法 ronin47 tomcat
    Tomcat报的错太含糊了，什么错都没报出来，只提示了Error listenerStart。为了调试，我们要获得更详细的日志。可以在WEB-INF/classes目录下新建一个文件叫logging.properties，内容如下 Java代码  handlers = org.apache.juli.FileHandler, java.util.logging.ConsoleHa
  • 不用加减符号实现加减法 BrokenDreams 实现
            今天有群友发了一个问题，要求不用加减符号(包括负号)来实现加减法。         分析一下，先看最简单的情况，假设1+1，按二进制算的话结果是10，可以看到从右往左的第一位变为0，第二位由于进位变为1。    
  • 读《研磨设计模式》-代码笔记-状态模式-State bylijinnan java设计模式
    声明： 本文只为方便我个人查阅和理解，详细的分析以及源代码请移步 原作者的博客http://chjavach.iteye.com/ /* 当一个对象的内在状态改变时允许改变其行为，这个对象看起来像是改变了其类 状态模式主要解决的是当控制一个对象状态的条件表达式过于复杂时的情况 把状态的判断逻辑转移到表示不同状态的一系列类中，可以把复杂的判断逻辑简化 如果在
  • CUDA程序block和thread超出硬件允许值时的异常 cherishLC CUDA
    调用CUDA的核函数时指定block 和 thread大小，该大小可以是dim3类型的（三维数组），只用一维时可以是usigned int型的。 以下程序验证了当block或thread大小超出硬件允许值时会产生异常！！！GPU根本不会执行运算！！！ 所以验证结果的正确性很重要！！！ 在VS中创建CUDA项目会有一个模板，里面有更详细的状态验证。 以下程序在K5000GPU上跑的。
  • 诡异的超长时间GC问题定位 chenchao051 jvmcmsGChbaseswap
    HBase的GC策略采用PawNew+CMS, 这是大众化的配置，ParNew经常会出现停顿时间特别长的情况，有时候甚至长到令人发指的地步，例如请看如下日志： 2012-10-17T05:54:54.293+0800: 739594.224: [GC 739606.508: [ParNew: 996800K->110720K(996800K), 178.8826900 secs] 3700
  • maven环境快速搭建 daizj 安装mavne环境配置
    一 下载maven 安装maven之前，要先安装jdk及配置JAVA_HOME环境变量。这个安装和配置java环境不用多说。 maven下载地址：http://maven.apache.org/download.html，目前最新的是这个apache-maven-3.2.5-bin.zip，然后解压在任意位置，最好地址中不要带中文字符，这个做java 的都知道，地址中出现中文会出现很多
  • PHP网站安全，避免PHP网站受到攻击的方法 dcj3sjt126com PHP
    对于PHP网站安全主要存在这样几种攻击方式:1、命令注入(Command Injection)2、eval注入(Eval Injection)3、客户端脚本攻击(Script Insertion)4、跨网站脚本攻击(Cross Site Scripting, XSS)5、SQL注入攻击(SQL injection)6、跨网站请求伪造攻击(Cross Site Request Forgerie
  • yii中给CGridView设置默认的排序根据时间倒序的方法 dcj3sjt126com GridView
    public function searchWithRelated() {         $criteria = new CDbCriteria;         $criteria->together = true; //without th
  • Java集合对象和数组对象的转换 dyy_gusi java集合
        在开发中，我们经常需要将集合对象（List，Set）转换为数组对象，或者将数组对象转换为集合对象。Java提供了相互转换的工具，但是我们使用的时候需要注意，不能乱用滥用。 1、数组对象转换为集合对象     最暴力的方式是new一个集合对象，然后遍历数组，依次将数组中的元素放入到新的集合中，但是这样做显然过
  • nginx同一主机部署多个应用 geeksun nginx
    近日有一需求，需要在一台主机上用nginx部署2个php应用，分别是wordpress和wiki，探索了半天，终于部署好了，下面把过程记录下来。 1.   在nginx下创建vhosts目录，用以放置vhost文件。 mkdir vhosts   2.   修改nginx.conf的配置， 在http节点增加下面内容设置，用来包含vhosts里的配置文件 #
  • ubuntu添加admin权限的用户账号 hongtoushizi ubuntuuseradd
    ubuntu创建账号的方式通常用到两种：useradd 和adduser . 本人尝试了useradd方法，步骤如下： 1:useradd    使用useradd时，如果后面不加任何参数的话，如：sudo useradd sysadm 创建出来的用户将是默认的三无用户：无home directory ,无密码,无系统shell。 顾应该如下操作：  
  • 第五章 常用Lua开发库2-JSON库、编码转换、字符串处理 jinnianshilongnian nginxlua
      JSON库   在进行数据传输时JSON格式目前应用广泛，因此从Lua对象与JSON字符串之间相互转换是一个非常常见的功能；目前Lua也有几个JSON库，本人用过cjson、dkjson。其中cjson的语法严格（比如unicode \u0020\u7eaf），要求符合规范否则会解析失败（如\u002），而dkjson相对宽松，当然也可以通过修改cjson的源码来完成
  • Spring定时器配置的两种实现方式OpenSymphony Quartz和java Timer详解 yaerfeng1989 timerquartz定时器
    原创整理不易，转载请注明出处：Spring定时器配置的两种实现方式OpenSymphony Quartz和java Timer详解 代码下载地址：http://www.zuidaima.com/share/1772648445103104.htm 有两种流行Spring定时器配置：Java的Timer类和OpenSymphony的Quartz。 1.Java Timer定时 首先继承jav
  • Linux下df与du两个命令的差别？ pda158 linux
    　一、df显示文件系统的使用情况，与du比較，就是更全盘化。 　　最经常使用的就是 df -T，显示文件系统的使用情况并显示文件系统的类型。 　　举比例如以下： 　　[root@localhost ~]# df -T 　　Filesystem                   Type &n
  • [转]SQLite的工具类 ---- 通过反射把Cursor封装到VO对象 ctfzh VOandroidsqlite反射Cursor
    在写DAO层时，觉得从Cursor里一个一个的取出字段值再装到VO(值对象)里太麻烦了，就写了一个工具类，用到了反射，可以把查询记录的值装到对应的VO里，也可以生成该VO的List。   使用时需要注意： 考虑到Android的性能问题，VO没有使用Setter和Getter，而是直接用public的属性。 表中的字段名需要和VO的属性名一样，要是不一样就得在查询的SQL中
  • 该学习笔记用到的Employee表 vipbooks oraclesql工作
        这是我在学习Oracle是用到的Employee表，在该笔记中用到的就是这张表，大家可以用它来学习和练习。 drop table Employee; -- 员工信息表 create table Employee( -- 员工编号 EmpNo number(3) primary key, -- 姓
按字母分类： ABCDEFGHIJKLMNOPQRSTUVWXYZ其他