dongfangshenyang 2022-08-17 10:03 采纳率: 100%

已结题

为什么loss和acc陡然下降如何调整为宜？(深度学习影像分割分割二值分类 TensorFlow keras unet )

问题遇到的现象和发生背景

深度学习影像图斑分割二分类
使用框架TensorFlow keras unet
显卡P5000
初始遥感影像样本旋转了3次裁切得到训练及验证样本集验证样本随机获取

问题相关代码，请勿粘贴截图

batch_size =8
input_size=256,256,3
epochs=260
learning_rate=5e-5
train_num=10456
validation_num=1306

用于配置训练模型（优化器、目标函数、模型评估标准）

model.compile(optimizer = Adam(lr = learning_rate), loss = 'categorical_crossentropy', metrics = ['accuracy'])

运行结果及报错内容

2022-08-16 20:43:33.834002: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2022-08-16 20:43:34.821246: W tensorflow/stream_executor/gpu/redzone_allocator.cc:314] Internal: Invoking GPU asm compilation is supported on Cuda non-Windows platforms only
Relying on driver to perform ptx compilation.
Modify $PATH to customize ptxas location.
This message will be only logged once.
2022-08-16 20:43:34.871322: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
1307/1307 [ ] - 1045s 800ms/step - loss: 0.6964 - accuracy: 0.8024 - val_loss: 0.6732 - val_accuracy: 0.8048

Epoch 00001: loss improved from inf to 0.69645, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 2/260
1307/1307 [ ] - 1047s 801ms/step - loss: 0.6232 - accuracy: 0.9028 - val_loss: 0.6156 - val_accuracy: 0.8981

Epoch 00002: loss improved from 0.69645 to 0.62322, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 3/260
1307/1307 [ ] - 1024s 784ms/step - loss: 0.5814 - accuracy: 0.9059 - val_loss: 0.5668 - val_accuracy: 0.9157

Epoch 00003: loss improved from 0.62322 to 0.58136, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 4/260
1307/1307 [ ] - 960s 734ms/step - loss: 0.5437 - accuracy: 0.9053 - val_loss: 0.5916 - val_accuracy: 0.8800

Epoch 00004: loss improved from 0.58136 to 0.54374, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 5/260
1307/1307 [ ] - 960s 734ms/step - loss: 0.5069 - accuracy: 0.9104 - val_loss: 0.5355 - val_accuracy: 0.9004

Epoch 00005: loss improved from 0.54374 to 0.50688, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 6/260
1307/1307 [ ] - 959s 734ms/step - loss: 0.4756 - accuracy: 0.9103 - val_loss: 0.4023 - val_accuracy: 0.9107

Epoch 00006: loss improved from 0.50688 to 0.47559, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 7/260
1307/1307 [ ] - 960s 735ms/step - loss: 0.4449 - accuracy: 0.9140 - val_loss: 0.4558 - val_accuracy: 0.8947

Epoch 00007: loss improved from 0.47559 to 0.44491, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 8/260
1307/1307 [ ] - 960s 734ms/step - loss: 0.4195 - accuracy: 0.9141 - val_loss: 0.3656 - val_accuracy: 0.8967

Epoch 00008: loss improved from 0.44491 to 0.41947, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 9/260
1307/1307 [ ] - 960s 734ms/step - loss: 0.3982 - accuracy: 0.9130 - val_loss: 0.3337 - val_accuracy: 0.9070

Epoch 00009: loss improved from 0.41947 to 0.39823, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 10/260
1307/1307 [ ] - 960s 734ms/step - loss: 0.3777 - accuracy: 0.9132 - val_loss: 0.3189 - val_accuracy: 0.8995

Epoch 00010: loss improved from 0.39823 to 0.37770, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 11/260
1307/1307 [ ] - 960s 735ms/step - loss: 0.3639 - accuracy: 0.9138 - val_loss: 0.2769 - val_accuracy: 0.9046

Epoch 00011: loss improved from 0.37770 to 0.36389, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 12/260
1307/1307 [ ] - 960s 735ms/step - loss: 0.3607 - accuracy: 0.9160 - val_loss: 0.3507 - val_accuracy: 0.9007

Epoch 00012: loss improved from 0.36389 to 0.36071, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 13/260
1307/1307 [ ] - 960s 734ms/step - loss: 0.3594 - accuracy: 0.9172 - val_loss: 0.2733 - val_accuracy: 0.8945

Epoch 00013: loss improved from 0.36071 to 0.35935, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 14/260
1307/1307 [ ] - 960s 734ms/step - loss: 0.3529 - accuracy: 0.9225 - val_loss: 0.2974 - val_accuracy: 0.8967

Epoch 00014: loss improved from 0.35935 to 0.35292, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 15/260
1307/1307 [ ] - 960s 735ms/step - loss: 0.3586 - accuracy: 0.9162 - val_loss: 0.2786 - val_accuracy: 0.9005

Epoch 00015: loss did not improve from 0.35292
Epoch 16/260
1307/1307 [ ] - 959s 734ms/step - loss: 0.3506 - accuracy: 0.9223 - val_loss: 0.3221 - val_accuracy: 0.9024

Epoch 00016: loss improved from 0.35292 to 0.35065, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 17/260
1307/1307 [ ] - 959s 734ms/step - loss: 0.3480 - accuracy: 0.9220 - val_loss: 0.4305 - val_accuracy: 0.8949

Epoch 00017: loss improved from 0.35065 to 0.34804, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 18/260
1307/1307 [ ] - 956s 731ms/step - loss: 0.3792 - accuracy: 0.8988 - val_loss: 0.8560 - val_accuracy: 0.1180

Epoch 00018: loss did not improve from 0.34804
Epoch 19/260
1307/1307 [ ] - 958s 733ms/step - loss: 0.3761 - accuracy: 0.8980 - val_loss: 0.7498 - val_accuracy: 0.1046

Epoch 00019: loss did not improve from 0.34804
Epoch 20/260
1307/1307 [ ] - 957s 732ms/step - loss: 0.3722 - accuracy: 0.8960 - val_loss: 0.7169 - val_accuracy: 0.1014

Epoch 00020: loss did not improve from 0.34804
Epoch 21/260
1307/1307 [ ] - 958s 733ms/step - loss: 0.3674 - accuracy: 0.8944 - val_loss: 0.6812 - val_accuracy: 0.8971

Epoch 00021: loss did not improve from 0.34804
Epoch 22/260
1307/1307 [ ] - 958s 733ms/step - loss: 0.3503 - accuracy: 0.9013 - val_loss: 0.6408 - val_accuracy: 0.8844

Epoch 00022: loss did not improve from 0.34804
Epoch 23/260
1307/1307 [ ] - 958s 733ms/step - loss: 0.0431 - accuracy: 0.1980 - val_loss: 1.1921e-07 - val_accuracy: 0.0978

Epoch 00023: loss improved from 0.34804 to 0.04306, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 24/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1007 - val_loss: 1.1921e-07 - val_accuracy: 0.1002

Epoch 00024: loss improved from 0.04306 to 0.00000, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 25/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1008 - val_loss: 1.1921e-07 - val_accuracy: 0.0957

Epoch 00025: loss improved from 0.00000 to 0.00000, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 26/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0996 - val_loss: 1.1921e-07 - val_accuracy: 0.1071

Epoch 00026: loss did not improve from 0.00000
Epoch 27/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1041 - val_loss: 1.1921e-07 - val_accuracy: 0.1075

Epoch 00027: loss did not improve from 0.00000
Epoch 28/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0996 - val_loss: 1.1921e-07 - val_accuracy: 0.0995

Epoch 00028: loss did not improve from 0.00000
Epoch 29/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0992 - val_loss: 1.1921e-07 - val_accuracy: 0.0937

Epoch 00029: loss did not improve from 0.00000
Epoch 30/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0985 - val_loss: 1.1921e-07 - val_accuracy: 0.1015

Epoch 00030: loss did not improve from 0.00000
Epoch 31/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1025 - val_loss: 1.1921e-07 - val_accuracy: 0.0973

Epoch 00031: loss did not improve from 0.00000
Epoch 32/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0972 - val_loss: 1.1921e-07 - val_accuracy: 0.1082

Epoch 00032: loss did not improve from 0.00000
Epoch 33/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0989 - val_loss: 1.1921e-07 - val_accuracy: 0.0937

Epoch 00033: loss did not improve from 0.00000
Epoch 34/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0995 - val_loss: 1.1921e-07 - val_accuracy: 0.0986

Epoch 00034: loss did not improve from 0.00000
Epoch 35/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0995 - val_loss: 1.1921e-07 - val_accuracy: 0.1008

Epoch 00035: loss improved from 0.00000 to 0.00000, saving model to F:\Data\QQCT2025\RSICPRJ\model\model.hdf5
Epoch 36/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1017 - val_loss: 1.1921e-07 - val_accuracy: 0.0910

Epoch 00036: loss did not improve from 0.00000
Epoch 37/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1003 - val_loss: 1.1921e-07 - val_accuracy: 0.0993

Epoch 00037: loss did not improve from 0.00000
Epoch 38/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1041 - val_loss: 1.1921e-07 - val_accuracy: 0.0965

Epoch 00038: loss did not improve from 0.00000
Epoch 39/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1024 - val_loss: 1.1921e-07 - val_accuracy: 0.0895

Epoch 00039: loss did not improve from 0.00000
Epoch 40/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.0992 - val_loss: 1.1921e-07 - val_accuracy: 0.0962

Epoch 00040: loss did not improve from 0.00000
Epoch 41/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1041 - val_loss: 1.1921e-07 - val_accuracy: 0.0978

Epoch 00041: loss did not improve from 0.00000
Epoch 42/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1008 - val_loss: 1.1921e-07 - val_accuracy: 0.0985

Epoch 00042: loss did not improve from 0.00000
Epoch 43/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1034 - val_loss: 1.1921e-07 - val_accuracy: 0.1030

Epoch 00043: loss did not improve from 0.00000
Epoch 44/260
1307/1307 [ ] - 958s 733ms/step - loss: 1.1921e-07 - accuracy: 0.1032 - val_loss: 1.1921e-07 - val_accuracy: 0.1070

Epoch 00044: loss did not improve from 0.00000
Epoch 45/260
653/1307 [=>] - ETA: 1:17:37 - loss: 1.1921e-07 - accuracy: 0.1055

我的解答思路和尝试过的方法

深度学习半路出家初次开展这么多样本的训练
昨天开始训练时就出现过acc较低的情况开始几轮0.1的acc 重启了几次把lr从2e-5调整为5e-5
训练acc前几轮达到0.8左右之后继续训练
今天发现在18轮出现loss和acc陡然下降之后 acc维持在0.1左右才训练至45轮

我想要达到的结果

请问loss和acc陡然下降是什么原因？
怎样调整或检查排除才能让loss 和acc正常曲线拟合至最佳状态？
就遥感影像地类要素分类来说基础样本旋转3次得到10000左右训练样本是否可用或还有哪些增强方式可用？

写回答
好问题 0 提建议
追加酬金
关注问题
分享
邀请回答
编辑收藏删除
收藏举报

9条回答默认最新

herosunly Python领域优质创作者 2022-08-17 12:56

关注

数据增强使用CutMix和Cutout，其中CutMix就是将一部分区域cut掉但不填充0像素而是随机填充训练集中的其他数据的区域像素值，分类结果按一定的比例分配；Cutout:随机的将样本中的部分区域cut掉，并且填充0像素值，分类的结果不变
激活函数可尝试使用swish或者mish
训练trick可使用学习率预热+学习率余弦衰减，建议先试预热，然后试两者合起来。
学习率预热的代码为：

# 在10个epoch学习率从5e-8逐渐提升为5e-7
from tensorflow.keras.callbacks import LearningRateScheduler

lr_schedule = [10]

def schedule(epoch_idx):
    if epoch_idx  < lr_schedule[0]:
        return 5e-7 / 10 * (epoch_idx+1)
   
    return 5e-7

scheduler = LearningRateScheduler(schedule=schedule)

model.fit(X_train, X_train_label,
                  validation_data=(X_val, X_val_label),
                  epochs=100, batch_size=64,
                  shuffle=True,
                  callbacks=[scheduler] #回调代码

两者合起来的代码为：

from tensorflow.keras.callbacks import LearningRateScheduler

lr_schedule = [10]

def schedule(epoch_idx):
    if epoch_idx < lr_schedule[0]:
        return 5e-7 / 10 * (epoch_idx+1)
    else:
        t = (epoch_idx - 10) * math.pi / 100 
        return  1/2 * (1 + math.cos(t)) * 0.1

scheduler = LearningRateScheduler(schedule=schedule)

本回答被题主选为最佳回答 , 对您是否有帮助呢?

编辑记录

查看更多回答(8条)

报告相同问题？

关注问题

为什么loss和acc陡然下降如何调整为宜？(深度学习 影像分割 分割二值分类 TensorFlow keras unet ) tensorflow 分类深度学习
2022-08-17 10:03

回答 9 已采纳数据增强使用CutMix和Cutout，其中CutMix就是将一部分区域cut掉但不填充0像素而是随机填充训练集中的其他数据的区域像素值，分类结果按一定的比例分配；Cutout:随机的将样本中的部分区
keras训练二分类模型acc一直0.5 loss一直是0.69怎么办? tensorflow 人工智能深度学习
2021-03-18 16:11

回答 2 已采纳帮你改了下代码，路径你自己再改改，验证集acc能跑到0.8以上了。 import os import tensorflow as tf from tensorflow.keras import S
请问tensorflow中的tf.keras.models.Model和tf.keras.Model有什么区别啊？ keras tensorflow 深度学习
2022-10-27 20:21

回答 2 已采纳没有看过源码，但是我的使用经验告诉我这两个是一样的，很有可能是同一个代码封装了两个入口。
使用 TensorFlow 进行图像分割的深度学习
2024-04-28 14:31

小白学视觉的博客点击上方“小白学视觉”，选择加"星标"或“置顶”...TensorFlow 是一个开源框架，用于构建和训练机器学习模型，在我们的例子中是图像分割模型。Tensorflow 提供执行图像分割任务所需的工具和预训练模型。图像分割...
使用Keras编写的LSTM，训练时出现loss: nan - val_loss: nan，该如何调整？ keras lstm 有问必答深度学习
2022-05-03 18:40

回答 2 已采纳原数据第一列是时间形式的20220503这种，在读数据之后进行下面操作，你的数据是简单的1 2 34这种，数据可能在处理过程丢失或者变成nan了，你可以一步步看看每次处理后当前的数据现在是什么格式 d
keras 二分类预测结果几乎全是一个值 keras python 有问必答深度学习
2021-06-18 20:41

回答 2 已采纳应该是这个吧，你训练之后得到的模型是H，prediction = H.predict(img)
module 'tensorflow.keras.layers' has no attribute 'Normalization keras tensorflow 深度学习
2022-08-09 16:15

回答 2 已采纳你是tensorflow哪个版本？keras哪个版本？不说版本很难查问题。可以试下把Normalization改为normalization试下可以试下把tensorflow.keras.layers
深度学习-Tensorflow2.2-图像处理{10}-UNET图像语义分割模型-24
2020-12-03 12:53

gemoumou的博客 UNET图像语义分割模型简介
tensorflow2.x 深度学习 使用相同梯度进行梯度下降的两个相同神经网络，得到的结果却不同 tensorflow 深度学习神经网络
2021-03-12 00:07

回答 2 已采纳在上面给的代码的第164行处插入 optimizer = optimizers.Adam(lr=1e-4) 重新初始化optimizer，这样两个模型训练后的测试结果就一样了，望采纳
tensorflow.keras打开SGD的问题，如何解决？ keras python tensorflow 有问必答
2022-03-19 21:27

回答 3 已采纳是不是安装的模块版本不对
使用keras进行分类问题时，验证集loss,accuracy 显示0.0000e+00，但是最后画图像时能显示出验证曲线 keras 深度学习
2018-12-10 06:32

回答 4 已采纳没看到你history输出的代码，感觉曲线图是可信的，而你输出val_loss的时候输出错了。
Keras实现Unet语义分割医学细胞图像并训练自己的数据集
2021-11-02 17:30

冬暇的博客文章目录Keras实现Unet语义分割医学细胞图像并训练自己的数据集一、Unet网络模型二、代码运行三、制作自己的数据集进行训练并测试标注 # 前言本文实现keras下的Unet语义分割模型并且用自己制作的数据集进行训练...
tensorflow keras调用模型显示进度条 keras python tensorflow
2023-01-05 17:22

回答 2 已采纳看看函数原型，有没有一个参数可以去掉进度条显示的，按常理应该会有。tensorflow.keras，就有一个参数verbose=0
【人工智能Ⅱ】实验4：Unet眼底血管图像分割
2024-03-29 08:41

MorleyOlsen的博客根据预测结果可以分析得到：在训练迭代次数较高的情况下，模型能够完全完成对眼球图像进行分割，所有眼球中的血管基本保持一个较高的能见度。根据预测结果可以分析得到：在训练迭代次数较低的情况下，模型并不能很好...
Unet分割医学图像全记录/结果全白解决办法/多分类Dice loss
2020-05-05 17:08

W思涵的博客这里写自定义目录标题Unet实现过程中遇到的bug1.Found 0 images belonging to 0 classes在服务器上指定GPU运行文件功能快捷键合理的创建标题，有助于目录的生成如何改变文本的样式插入链接与图片如何插入一段漂亮的...
没有解决我的问题, 去提问

问题事件

关注

码龄粉丝数原力等级 --

被采纳

被点赞

采纳率
系统已结题 8月28日
关注

码龄粉丝数原力等级 --

被采纳

被点赞

采纳率
已采纳回答 8月20日
关注

码龄粉丝数原力等级 --

被采纳

被点赞

采纳率
赞助了问题酬金40元 8月17日
关注

码龄粉丝数原力等级 --

被采纳

被点赞

采纳率
赞助了问题酬金60元 8月17日
展开全部

悬赏问题

¥200 csgo2的viewmatrix值是否还有别的获取方式
¥15 Stable Diffusion，用Ebsynth utility在视频选帧图重绘，第一步报错，蒙版和帧图没法生成，怎么处理啊
¥15 请把下列每一行代码完整地读懂并注释出来
¥15 pycharm运行main文件，显示没有conda环境
¥15 寻找公式识别开发，自动识别整页文档、图像公式的软件
¥15 为什么eclipse不能再下载了？
¥15 编辑cmake lists 明明写了project项目名，但是还是报错怎么回事
¥15 关于#计算机视觉#的问题：求一份高质量桥梁多病害数据集
¥15 特定网页无法访问，已排除网页问题
¥50 如何将脑的图像投影到颅骨上

为什么loss和acc陡然下降 如何调整为宜？(深度学习 影像分割 分割 二值分类 TensorFlow keras unet )