#mermaid-svg-96sB5aZmwVCy6qSl .label{font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family);fill:#333;color:#333}#mermaid-svg-96sB5aZmwVCy6qSl .label text{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .node rect,#mermaid-svg-96sB5aZmwVCy6qSl .node circle,#mermaid-svg-96sB5aZmwVCy6qSl .node ellipse,#mermaid-svg-96sB5aZmwVCy6qSl .node polygon,#mermaid-svg-96sB5aZmwVCy6qSl .node path{fill:#ECECFF;stroke:#9370db;stroke-width:1px}#mermaid-svg-96sB5aZmwVCy6qSl .node .label{text-align:center;fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .node.clickable{cursor:pointer}#mermaid-svg-96sB5aZmwVCy6qSl .arrowheadPath{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .edgePath .path{stroke:#333;stroke-width:1.5px}#mermaid-svg-96sB5aZmwVCy6qSl .flowchart-link{stroke:#333;fill:none}#mermaid-svg-96sB5aZmwVCy6qSl .edgeLabel{background-color:#e8e8e8;text-align:center}#mermaid-svg-96sB5aZmwVCy6qSl .edgeLabel rect{opacity:0.9}#mermaid-svg-96sB5aZmwVCy6qSl .edgeLabel span{color:#333}#mermaid-svg-96sB5aZmwVCy6qSl .cluster rect{fill:#ffffde;stroke:#aa3;stroke-width:1px}#mermaid-svg-96sB5aZmwVCy6qSl .cluster text{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family);font-size:12px;background:#ffffde;border:1px solid #aa3;border-radius:2px;pointer-events:none;z-index:100}#mermaid-svg-96sB5aZmwVCy6qSl .actor{stroke:#ccf;fill:#ECECFF}#mermaid-svg-96sB5aZmwVCy6qSl text.actor>tspan{fill:#000;stroke:none}#mermaid-svg-96sB5aZmwVCy6qSl .actor-line{stroke:grey}#mermaid-svg-96sB5aZmwVCy6qSl .messageLine0{stroke-width:1.5;stroke-dasharray:none;stroke:#333}#mermaid-svg-96sB5aZmwVCy6qSl .messageLine1{stroke-width:1.5;stroke-dasharray:2, 2;stroke:#333}#mermaid-svg-96sB5aZmwVCy6qSl #arrowhead path{fill:#333;stroke:#333}#mermaid-svg-96sB5aZmwVCy6qSl .sequenceNumber{fill:#fff}#mermaid-svg-96sB5aZmwVCy6qSl #sequencenumber{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl #crosshead path{fill:#333;stroke:#333}#mermaid-svg-96sB5aZmwVCy6qSl .messageText{fill:#333;stroke:#333}#mermaid-svg-96sB5aZmwVCy6qSl .labelBox{stroke:#ccf;fill:#ECECFF}#mermaid-svg-96sB5aZmwVCy6qSl .labelText,#mermaid-svg-96sB5aZmwVCy6qSl .labelText>tspan{fill:#000;stroke:none}#mermaid-svg-96sB5aZmwVCy6qSl .loopText,#mermaid-svg-96sB5aZmwVCy6qSl .loopText>tspan{fill:#000;stroke:none}#mermaid-svg-96sB5aZmwVCy6qSl .loopLine{stroke-width:2px;stroke-dasharray:2, 2;stroke:#ccf;fill:#ccf}#mermaid-svg-96sB5aZmwVCy6qSl .note{stroke:#aa3;fill:#fff5ad}#mermaid-svg-96sB5aZmwVCy6qSl .noteText,#mermaid-svg-96sB5aZmwVCy6qSl .noteText>tspan{fill:#000;stroke:none}#mermaid-svg-96sB5aZmwVCy6qSl .activation0{fill:#f4f4f4;stroke:#666}#mermaid-svg-96sB5aZmwVCy6qSl .activation1{fill:#f4f4f4;stroke:#666}#mermaid-svg-96sB5aZmwVCy6qSl .activation2{fill:#f4f4f4;stroke:#666}#mermaid-svg-96sB5aZmwVCy6qSl .mermaid-main-font{font-family:"trebuchet ms", verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .section{stroke:none;opacity:0.2}#mermaid-svg-96sB5aZmwVCy6qSl .section0{fill:rgba(102,102,255,0.49)}#mermaid-svg-96sB5aZmwVCy6qSl .section2{fill:#fff400}#mermaid-svg-96sB5aZmwVCy6qSl .section1,#mermaid-svg-96sB5aZmwVCy6qSl .section3{fill:#fff;opacity:0.2}#mermaid-svg-96sB5aZmwVCy6qSl .sectionTitle0{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .sectionTitle1{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .sectionTitle2{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .sectionTitle3{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .sectionTitle{text-anchor:start;font-size:11px;text-height:14px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .grid .tick{stroke:#d3d3d3;opacity:0.8;shape-rendering:crispEdges}#mermaid-svg-96sB5aZmwVCy6qSl .grid .tick text{font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .grid path{stroke-width:0}#mermaid-svg-96sB5aZmwVCy6qSl .today{fill:none;stroke:red;stroke-width:2px}#mermaid-svg-96sB5aZmwVCy6qSl .task{stroke-width:2}#mermaid-svg-96sB5aZmwVCy6qSl .taskText{text-anchor:middle;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .taskText:not([font-size]){font-size:11px}#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutsideRight{fill:#000;text-anchor:start;font-size:11px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutsideLeft{fill:#000;text-anchor:end;font-size:11px}#mermaid-svg-96sB5aZmwVCy6qSl .task.clickable{cursor:pointer}#mermaid-svg-96sB5aZmwVCy6qSl .taskText.clickable{cursor:pointer;fill:#003163 !important;font-weight:bold}#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutsideLeft.clickable{cursor:pointer;fill:#003163 !important;font-weight:bold}#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutsideRight.clickable{cursor:pointer;fill:#003163 !important;font-weight:bold}#mermaid-svg-96sB5aZmwVCy6qSl .taskText0,#mermaid-svg-96sB5aZmwVCy6qSl .taskText1,#mermaid-svg-96sB5aZmwVCy6qSl .taskText2,#mermaid-svg-96sB5aZmwVCy6qSl .taskText3{fill:#fff}#mermaid-svg-96sB5aZmwVCy6qSl .task0,#mermaid-svg-96sB5aZmwVCy6qSl .task1,#mermaid-svg-96sB5aZmwVCy6qSl .task2,#mermaid-svg-96sB5aZmwVCy6qSl .task3{fill:#8a90dd;stroke:#534fbc}#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutside0,#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutside2{fill:#000}#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutside1,#mermaid-svg-96sB5aZmwVCy6qSl .taskTextOutside3{fill:#000}#mermaid-svg-96sB5aZmwVCy6qSl .active0,#mermaid-svg-96sB5aZmwVCy6qSl .active1,#mermaid-svg-96sB5aZmwVCy6qSl .active2,#mermaid-svg-96sB5aZmwVCy6qSl .active3{fill:#bfc7ff;stroke:#534fbc}#mermaid-svg-96sB5aZmwVCy6qSl .activeText0,#mermaid-svg-96sB5aZmwVCy6qSl .activeText1,#mermaid-svg-96sB5aZmwVCy6qSl .activeText2,#mermaid-svg-96sB5aZmwVCy6qSl .activeText3{fill:#000 !important}#mermaid-svg-96sB5aZmwVCy6qSl .done0,#mermaid-svg-96sB5aZmwVCy6qSl .done1,#mermaid-svg-96sB5aZmwVCy6qSl .done2,#mermaid-svg-96sB5aZmwVCy6qSl .done3{stroke:grey;fill:#d3d3d3;stroke-width:2}#mermaid-svg-96sB5aZmwVCy6qSl .doneText0,#mermaid-svg-96sB5aZmwVCy6qSl .doneText1,#mermaid-svg-96sB5aZmwVCy6qSl .doneText2,#mermaid-svg-96sB5aZmwVCy6qSl .doneText3{fill:#000 !important}#mermaid-svg-96sB5aZmwVCy6qSl .crit0,#mermaid-svg-96sB5aZmwVCy6qSl .crit1,#mermaid-svg-96sB5aZmwVCy6qSl .crit2,#mermaid-svg-96sB5aZmwVCy6qSl .crit3{stroke:#f88;fill:red;stroke-width:2}#mermaid-svg-96sB5aZmwVCy6qSl .activeCrit0,#mermaid-svg-96sB5aZmwVCy6qSl .activeCrit1,#mermaid-svg-96sB5aZmwVCy6qSl .activeCrit2,#mermaid-svg-96sB5aZmwVCy6qSl .activeCrit3{stroke:#f88;fill:#bfc7ff;stroke-width:2}#mermaid-svg-96sB5aZmwVCy6qSl .doneCrit0,#mermaid-svg-96sB5aZmwVCy6qSl .doneCrit1,#mermaid-svg-96sB5aZmwVCy6qSl .doneCrit2,#mermaid-svg-96sB5aZmwVCy6qSl .doneCrit3{stroke:#f88;fill:#d3d3d3;stroke-width:2;cursor:pointer;shape-rendering:crispEdges}#mermaid-svg-96sB5aZmwVCy6qSl .milestone{transform:rotate(45deg) scale(0.8, 0.8)}#mermaid-svg-96sB5aZmwVCy6qSl .milestoneText{font-style:italic}#mermaid-svg-96sB5aZmwVCy6qSl .doneCritText0,#mermaid-svg-96sB5aZmwVCy6qSl .doneCritText1,#mermaid-svg-96sB5aZmwVCy6qSl .doneCritText2,#mermaid-svg-96sB5aZmwVCy6qSl .doneCritText3{fill:#000 !important}#mermaid-svg-96sB5aZmwVCy6qSl .activeCritText0,#mermaid-svg-96sB5aZmwVCy6qSl .activeCritText1,#mermaid-svg-96sB5aZmwVCy6qSl .activeCritText2,#mermaid-svg-96sB5aZmwVCy6qSl .activeCritText3{fill:#000 !important}#mermaid-svg-96sB5aZmwVCy6qSl .titleText{text-anchor:middle;font-size:18px;fill:#000;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl g.classGroup text{fill:#9370db;stroke:none;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family);font-size:10px}#mermaid-svg-96sB5aZmwVCy6qSl g.classGroup text .title{font-weight:bolder}#mermaid-svg-96sB5aZmwVCy6qSl g.clickable{cursor:pointer}#mermaid-svg-96sB5aZmwVCy6qSl g.classGroup rect{fill:#ECECFF;stroke:#9370db}#mermaid-svg-96sB5aZmwVCy6qSl g.classGroup line{stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl .classLabel .box{stroke:none;stroke-width:0;fill:#ECECFF;opacity:0.5}#mermaid-svg-96sB5aZmwVCy6qSl .classLabel .label{fill:#9370db;font-size:10px}#mermaid-svg-96sB5aZmwVCy6qSl .relation{stroke:#9370db;stroke-width:1;fill:none}#mermaid-svg-96sB5aZmwVCy6qSl .dashed-line{stroke-dasharray:3}#mermaid-svg-96sB5aZmwVCy6qSl #compositionStart{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl #compositionEnd{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl #aggregationStart{fill:#ECECFF;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl #aggregationEnd{fill:#ECECFF;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl #dependencyStart{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl #dependencyEnd{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl #extensionStart{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl #extensionEnd{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl .commit-id,#mermaid-svg-96sB5aZmwVCy6qSl .commit-msg,#mermaid-svg-96sB5aZmwVCy6qSl .branch-label{fill:lightgrey;color:lightgrey;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .pieTitleText{text-anchor:middle;font-size:25px;fill:#000;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .slice{font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl g.stateGroup text{fill:#9370db;stroke:none;font-size:10px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl g.stateGroup text{fill:#9370db;fill:#333;stroke:none;font-size:10px}#mermaid-svg-96sB5aZmwVCy6qSl g.statediagram-cluster .cluster-label text{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl g.stateGroup .state-title{font-weight:bolder;fill:#000}#mermaid-svg-96sB5aZmwVCy6qSl g.stateGroup rect{fill:#ECECFF;stroke:#9370db}#mermaid-svg-96sB5aZmwVCy6qSl g.stateGroup line{stroke:#9370db;stroke-width:1}#mermaid-svg-96sB5aZmwVCy6qSl .transition{stroke:#9370db;stroke-width:1;fill:none}#mermaid-svg-96sB5aZmwVCy6qSl .stateGroup .composit{fill:white;border-bottom:1px}#mermaid-svg-96sB5aZmwVCy6qSl .stateGroup .alt-composit{fill:#e0e0e0;border-bottom:1px}#mermaid-svg-96sB5aZmwVCy6qSl .state-note{stroke:#aa3;fill:#fff5ad}#mermaid-svg-96sB5aZmwVCy6qSl .state-note text{fill:black;stroke:none;font-size:10px}#mermaid-svg-96sB5aZmwVCy6qSl .stateLabel .box{stroke:none;stroke-width:0;fill:#ECECFF;opacity:0.7}#mermaid-svg-96sB5aZmwVCy6qSl .edgeLabel text{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .stateLabel text{fill:#000;font-size:10px;font-weight:bold;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-96sB5aZmwVCy6qSl .node circle.state-start{fill:black;stroke:black}#mermaid-svg-96sB5aZmwVCy6qSl .node circle.state-end{fill:black;stroke:white;stroke-width:1.5}#mermaid-svg-96sB5aZmwVCy6qSl #statediagram-barbEnd{fill:#9370db}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-cluster rect{fill:#ECECFF;stroke:#9370db;stroke-width:1px}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-cluster rect.outer{rx:5px;ry:5px}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-state .divider{stroke:#9370db}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-state .title-state{rx:5px;ry:5px}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-cluster.statediagram-cluster .inner{fill:white}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-cluster.statediagram-cluster-alt .inner{fill:#e0e0e0}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-cluster .inner{rx:0;ry:0}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-state rect.basic{rx:5px;ry:5px}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-state rect.divider{stroke-dasharray:10,10;fill:#efefef}#mermaid-svg-96sB5aZmwVCy6qSl .note-edge{stroke-dasharray:5}#mermaid-svg-96sB5aZmwVCy6qSl .statediagram-note rect{fill:#fff5ad;stroke:#aa3;stroke-width:1px;rx:0;ry:0}:root{--mermaid-font-family: '"trebuchet ms", verdana, arial';--mermaid-font-family: "Comic Sans MS", "Comic Sans", cursive}#mermaid-svg-96sB5aZmwVCy6qSl .error-icon{fill:#522}#mermaid-svg-96sB5aZmwVCy6qSl .error-text{fill:#522;stroke:#522}#mermaid-svg-96sB5aZmwVCy6qSl .edge-thickness-normal{stroke-width:2px}#mermaid-svg-96sB5aZmwVCy6qSl .edge-thickness-thick{stroke-width:3.5px}#mermaid-svg-96sB5aZmwVCy6qSl .edge-pattern-solid{stroke-dasharray:0}#mermaid-svg-96sB5aZmwVCy6qSl .edge-pattern-dashed{stroke-dasharray:3}#mermaid-svg-96sB5aZmwVCy6qSl .edge-pattern-dotted{stroke-dasharray:2}#mermaid-svg-96sB5aZmwVCy6qSl .marker{fill:#333}#mermaid-svg-96sB5aZmwVCy6qSl .marker.cross{stroke:#333}:root { --mermaid-font-family: "trebuchet ms", verdana, arial;}#mermaid-svg-96sB5aZmwVCy6qSl {color: rgba(0, 0, 0, 0.75);font: ;}

输入图像大小：(batch_size,3,224,224)
第一层卷积:  (96,3,11,11) ,padding = 2,stride = 4     输出大小：(batch_size,96,55,55)ReLU(), Local Response Normalizationmax pooling(3,stride = 2)                        输出大小：(batch_size,96,27,27)
第二层卷积: (256,96,5,5) padding = 2,stride = 1     输出大小：(batch_size,256,27,27)ReLU(), Local Response Normalizationmax pooling(3,stride = 2)                        输出大小：(batch_size,256,13,13)
第三层卷积: (384,256,3,3) padding = 1,stride = 1     输出大小：(batch_size,384,13,13)ReLU()
第四层卷积: (384,384,3,3) padding = 1,stride = 1     输出大小：(batch_size,384,13,13)ReLU()
第五层卷积: (256,384,3,3) padding = 1,stride = 1     输出大小：(batch_size,256,13,13)ReLU()max pooling(3,stride = 2)                        输出大小：(batch_size,256,6,6)
第六/七/八层全连接层(256*6*6,4096)   ReLU()  Dropout()        输出大小：(batch_size,4096)(4096,4096)      ReLU()  Dropout()          输出大小：(batch_size,4096)(4096,1000)输出大小：(batch_size,1000)

# -*- coding: utf-8 -*-
# @Time : 2020/1/21 11:18
# @Author : Zhao HL
# @File : alexnet-paddle.py
import os, sys
from PIL import Image
import numpy as np
import pandas as pd
import paddle
from paddle import fluid
from paddle.fluid.layers import data, conv2d, pool2d, flatten, fc, cross_entropy, accuracy, mean
from my_utils import process_show, draw_loss_acc# region parameters
# region paths
Data_path = "./data/my_imagenet"
Data_csv_path = "./data/my_imagenet.csv"
Model_path = 'model/'
Model_file_tf = "model/alexnet_tf.ckpt"
Model_file_keras = "model/alexnet_keras.h5"
Model_file_torch = "model/alexnet_torch.pth"
Model_file_paddle = "model/alexnet_paddle.model"
# endregion# region image parameter
Img_size = 227
Img_chs = 3
Label_size = 1
Label_class = {'n02091244': 'Ibizan hound','n02114548': 'white wolf','n02138441': 'meerkat','n03584254': 'iPod','n03075370': 'combination lock','n09256479': 'coral reef','n03980874': 'poncho','n02174001': 'rhinoceros beetle','n03770439': 'miniskirt','n03773504': 'missile'}
Labels_nums = len(Label_class)
# endregion# region net parameter
Conv1_kernel_size = 11
Conv1_chs = 96
Conv2_kernel_size = 5
Conv2_chs = 256
Conv3_kernel_size = 3
Conv3_chs = 384
Conv4_kernel_size = 3
Conv4_chs = 384
Conv5_kernel_size = 3
Conv5_chs = 256
Flatten_size = 6 * 6 * 256
Fc1_size = 4096
Fc2_size = 4096
Fc3_size = Labels_nums
# endregion# region hpyerparameter
Learning_rate = 1e-4
Batch_size = 32
Buffer_size = 256
Infer_size = 1
Epochs = 10
Train_num = 700
Train_batch_num = Train_num // Batch_size
Val_num = 100
Val_batch_num = Val_num // Batch_size
Test_num = 200
Test_batch_num = Test_num // Batch_size
# endregion
place = fluid.CUDAPlace(0) if fluid.cuda_places() else fluid.CPUPlace()
# endregionclass MyDataset():def __init__(self, root_path, batch_size, files_list=None,):self.root_path = root_pathself.files_list = files_list if files_list else os.listdir(root_path)self.size = len(files_list)self.batch_size = batch_sizedef __len__(self):return self.sizedef dataset_reader(self):passfiles_list = self.files_list if self.files_list is not None else os.listdir(self.root_path)def reader():np.random.shuffle(files_list)for file_name in files_list:label_str = file_name[:9]label = list(Label_class.keys()).index(label_str)img = Image.open(os.path.join(self.root_path, file_name))yield img, labelreturn paddle.batch(paddle.reader.xmap_readers(self.transform, reader, 2, Buffer_size), batch_size=self.batch_size)def transform(self,sample):def Normalize(image, means, stds):for band in range(len(means)):image[:, :, band] = image[:, :, band] / 255.0image[:, :, band] = (image[:, :, band] - means[band]) / stds[band]image = np.transpose(image, [2, 1, 0])return imagepassimage, label = sampleimage = image.resize((Img_size, Img_size), Image.ANTIALIAS)image = Normalize(np.array(image).astype(np.float), [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])return image, labelclass AlexNet:def __init__(self, structShow=False):self.structShow = structShowself.image = data(shape=[Img_chs, Img_size, Img_size], dtype='float32', name='image')self.label = data(shape=[Label_size], dtype='int64', name='label')self.predict = self.get_alexNet()def get_alexNet(self):conv1 = conv2d(self.image, Conv1_chs, filter_size=Conv1_kernel_size, stride=4, padding=0, act='relu')pool1 = pool2d(conv1, 3, pool_stride=2, pool_type='max')conv2 = conv2d(pool1, Conv2_chs, filter_size=Conv2_kernel_size, padding=2, act='relu')pool2 = pool2d(conv2, 3, pool_stride=2, pool_type='max')conv3 = conv2d(pool2, Conv3_chs, filter_size=Conv3_kernel_size, padding=1, act='relu')conv4 = conv2d(conv3, Conv4_chs, filter_size=Conv4_kernel_size, padding=1, act='relu')conv5 = conv2d(conv4, Conv5_chs, filter_size=Conv5_kernel_size, padding=1, act='relu')pool3 = pool2d(conv5, 3, pool_stride=2, pool_type='max')flt = flatten(pool3, axis=1)fc1 = fc(flt, Fc1_size, act='relu')fc2 = fc(fc1, Fc2_size, act='relu')fc3 = fc(fc1, Fc3_size, act='softmax')if self.structShow:print(conv1.name, conv1.shape)print(pool1.name, pool1.shape)print(conv2.name, conv2.shape)print(pool2.name, pool2.shape)print(conv3.name, conv3.shape)print(conv4.name, conv4.shape)print(conv5.name, conv5.shape)print(pool3.name, pool3.shape)print(flt.name, flt.shape)print(fc1.name, fc1.shape)print(fc2.name, fc2.shape)print(fc3.name, fc3.shape)return fc3def train():net = AlexNet(structShow=True)image, label, predict = net.image, net.label, net.predictfeeder = fluid.DataFeeder(place=place, feed_list=[image, label])df = pd.read_csv(Data_csv_path, header=0, index_col=0)train_list = df[df['split'] == 'train']['filename'].tolist()val_list = df[df['split'] == 'val']['filename'].tolist()train_reader = MyDataset(Data_path, batch_size=Batch_size, files_list=train_list).dataset_reader()val_reader =  MyDataset(Data_path, batch_size=Batch_size, files_list=val_list).dataset_reader()loss = cross_entropy(input=predict, label=label)loss_mean = mean(loss)acc = accuracy(input=predict, label=label)optimizer = fluid.optimizer.AdamOptimizer(learning_rate=Learning_rate)optimizer.minimize(loss_mean)val_program = fluid.default_main_program().clone(for_test=True)exe = fluid.Executor(place)exe.run(fluid.default_startup_program())train_losses = np.ones(Epochs)train_accs = np.ones(Epochs)val_losses = np.ones(Epochs)val_accs = np.ones(Epochs)best_loss = float("inf")best_loss_epoch = 0for epoch in range(Epochs):print('Epoch %d/%d:' % (epoch + 1, Epochs))train_sum_loss = 0train_sum_acc = 0val_sum_loss = 0val_sum_acc = 0for batch_num, data in enumerate(train_reader()):train_loss, train_acc = exe.run(program=fluid.default_main_program(),  # 运行主程序feed=feeder.feed(data),  # 给模型喂入数据fetch_list=[loss_mean, acc])  # fetch 误差、准确率train_sum_loss += train_loss[0]train_sum_acc += train_acc[0]process_show(batch_num + 1, Train_num / Batch_size, train_acc, train_loss, prefix='train:')for batch_num, data in enumerate(val_reader()):val_loss, val_acc = exe.run(program=val_program,  # 执行训练程序feed=feeder.feed(data),  # 喂入数据fetch_list=[loss_mean, acc])  # fetch 误差、准确率val_sum_loss += val_loss[0]val_sum_acc += val_acc[0]process_show(batch_num + 1, Val_num / Batch_size, val_acc, val_loss, prefix='train:')train_sum_loss /= (Train_num // Batch_size)train_sum_acc /= (Train_num // Batch_size)val_sum_loss /= (Val_num // Batch_size)val_sum_acc /= (Val_num // Batch_size)train_losses[epoch] = train_sum_losstrain_accs[epoch] = train_sum_accval_losses[epoch] = val_sum_lossval_accs[epoch] = val_sum_accprint('average summary:\ntrain acc %.4f, loss %.4f ; val acc %.4f, loss %.4f'% (train_sum_acc, train_sum_loss, val_sum_acc, val_sum_loss))if val_sum_loss < best_loss:print('val_loss improve from %.4f to %.4f, model save to %s ! \n' % (best_loss, val_sum_loss, Model_file_paddle))best_loss = val_sum_lossbest_loss_epoch = epoch + 1fluid.io.save_inference_model(Model_file_paddle,  # 保存推理model的路径['image'],  # 推理（inference）需要 feed 的数据[predict],  # 保存推理（inference）结果的 Variablesexe)  # executor 保存 inference modelelse:print('val_loss do not improve from %.4f \n' % (best_loss))print('best loss %.4f at epoch %d \n' % (best_loss, best_loss_epoch))draw_loss_acc(train_losses, train_accs, 'train')draw_loss_acc(val_losses, val_accs, 'val')if __name__ == '__main__':pass# dataInfo_show(r'E:\_Python\01_deeplearning\03_AlexNet\data\my_imagenet',#               r'E:\_Python\01_deeplearning\03_AlexNet\data\my_imagenet.csv',#               r'E:\_Python\01_deeplearning\03_AlexNet\data\synset_words.txt')# dataset_divide(r'E:\_Python\01_deeplearning\03_AlexNet\data\my_imagenet.csv')train()