解决keras,val_categorical_accuracy:,0.0000e+00问题_训练过程中准确率一直是0

keras

0.0000e+00

143 浏览量更新于2023-03-16 评论 2 收藏 46KB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源评论

资源推荐

解决解决keras,val_categorical_accuracy:,0.0000e+00问题问题

主要介绍了解决keras,val_categorical_accuracy:,0.0000e+00问题，具有很好的参考价值，希望对大家有所帮

助。一起跟随小编过来看看吧

问题描述：问题描述：

在利用神经网络进行分类和识别的时候，使用了keras这个封装层次比较高的框架，backend使用的是tensorflow-cpu。

在交叉验证的时候，出现 val_categorical_accuracy: 0.0000e+00的问题。

问题分析：问题分析：

首先，弄清楚，训练集、验证集、测试集的区别，验证集是从训练集中提前拿出一部分的数据集。在keras中，一般都是使用

这种方式来指定验证集占训练集和的总大小。

validation_split=0.2

比如，经典的数据集MNIST，共有60000个训练集，就会

Train on 48000 samples, validate on 12000 samples

我自己学习使用的数据集比较小

训练数据集样本数： 498 ,标签个数 498

Train on 398 samples, validate on 100 samples

基本上符合4：1（0.2）的分配

出现 val_categorical_accuracy: 0.0000e+00的问题，我这边的原因主要是，样本本身是有规律的，导致分配的验证集的标签

可能在训练集中可能就没有。

（PS：我实际看了下，498个样本共10个标签，后100个验证集占据了基本上后面3个标签（实际上，这三个标签占了103个

样本），也就是前面的训练集基本上就没有后面的标签，整体占据前面7个标签）

问题解决：问题解决：

把最初始的训练集打乱，当然，标签也要跟着移动。

index = [i for i in range(len(x_train))]

np.random.shuffle(index)

x_train = x_train[index]

y_train = y_train[index]

model.fit(x_train, y_train, batch_size=32, epochs=10, validation_split=0.2, verbose=1)

同样的问题表现，可能有不同的原因，解决方法也不尽相同，这里只是和大家分享我自己的问题解决过程。

补充知识：补充知识：keras中自定义验证集的性能评估中自定义验证集的性能评估

如下所示：

def AUC(y_true,y_pred):

not_y_pred=np.logical_not(y_pred)

y_int1=y_true*y_pred

y_int0=np.logical_not(y_true)*not_y_pred

TP=np.sum(y_pred*y_int1)

FP=np.sum(y_pred)-TP

TN=np.sum(not_y_pred*y_int0)

FN=np.sum(not_y_pred)-TN

TPR=np.float(TP)/(TP+FN)

FPR=np.float(FP)/(FP+TN)

return((1+TPR-FPR)/2)

以上这篇解决keras,val_categorical_accuracy:,0.0000e+00问题就是小编分享给大家的全部内容了，希望能给大家一个参考，

也希望大家多多支持我们。

本内容试读结束，登录后可阅读更多

下载后可阅读完整内容，剩余0页未读，立即下载

#将分类标签变为onehot编码 #Keras采用独热编码输出 num_class = 10 y_train = keras.utils.to_categorical(y_train, num_class) y_test = keras.utils.to_categorical(y_test, num_class) print(y_train[0]) 查看结果： y_train[0]： ,该样本对应数字是： y_test[0]: ,该样本对应数字是：

y_train = keras.utils.to_categorical(y_train, num_classes) y_test = keras.utils.to_categorical(y_test, num_classes) # 输出转换后的标签 print("y_train[0]:", y_train[0]) print("y_test[0]:", y_test[0]) ...

from keras_frcnn import metrics as metrics_fn ImportError: cannot import name 'metrics' from 'keras_frcnn' (D:\程序\Keras-Faster-RCNN-master-master\keras_frcnn\init.py)

为此，你可以尝试使用`keras_frcnn.metrics`代替`from keras_frcnn import metrics as metrics_fn`，并修改`class_acc`和`mean_overlapping_bboxes`为`keras_frcnn.metrics.class_acc`和`keras_frcnn.metrics.mean_...

帮我把下面这个代码从TensorFlow改成pytorch import tensorflow as tf import os import numpy as np import matplotlib.pyplot as plt os.environ["CUDA_VISIBLE_DEVICES"] = "0" base_dir = 'E:/direction/datasetsall/' train_dir = os.path.join(base_dir, 'train_img/') validation_dir = os.path.join(base_dir, 'val_img/') train_cats_dir = os.path.join(train_dir, 'down') train_dogs_dir = os.path.join(train_dir, 'up') validation_cats_dir = os.path.join(validation_dir, 'down') validation_dogs_dir = os.path.join(validation_dir, 'up') batch_size = 64 epochs = 50 IMG_HEIGHT = 128 IMG_WIDTH = 128 num_cats_tr = len(os.listdir(train_cats_dir)) num_dogs_tr = len(os.listdir(train_dogs_dir)) num_cats_val = len(os.listdir(validation_cats_dir)) num_dogs_val = len(os.listdir(validation_dogs_dir)) total_train = num_cats_tr + num_dogs_tr total_val = num_cats_val + num_dogs_val train_image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1. / 255) validation_image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1. / 255) train_data_gen = train_image_generator.flow_from_directory(batch_size=batch_size, directory=train_dir, shuffle=True, target_size=(IMG_HEIGHT, IMG_WIDTH), class_mode='categorical') val_data_gen = validation_image_generator.flow_from_directory(batch_size=batch_size, directory=validation_dir, target_size=(IMG_HEIGHT, IMG_WIDTH), class_mode='categorical') sample_training_images, _ = next(train_data_gen) model = tf.keras.models.Sequential([ tf.keras.layers.Conv2D(16, 3, padding='same', activation='relu', input_shape=(IMG_HEIGHT, IMG_WIDTH, 3)), tf.keras.layers.MaxPooling2D(), tf.keras.layers.Conv2D(32, 3, padding='same', activation='relu'), tf.keras.layers.MaxPooling2D(), tf.keras.layers.Conv2D(64, 3, padding='same', activation='relu'), tf.keras.layers.MaxPooling2D(), tf.keras.layers.Flatten(), tf.keras.layers.Dense(256, activation='relu'), tf.keras.layers.Dense(2, activation='softmax') ]) model.compile(optimizer='adam', loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), metrics=['accuracy']) model.summary() history = model.fit_generator( train_data_gen, steps_per_epoch=total_train // batch_size, epochs=epochs, validation_data=val_data_gen, validation_steps=total_val // batch_size ) # 可视化训练结果 acc = history.history['accuracy'] val_acc = history.history['val_accuracy'] loss = history.history['loss'] val_loss = history.history['val_loss'] epochs_range = range(epochs) model.save("./model/timo_classification_128_maxPool2D_dense256.h5")

import torch import os import numpy as np import matplotlib.pyplot as plt os.environ["CUDA_VISIBLE_DEVICES"] = "0" base_dir = 'E:/direction/datasetsall/' train_dir = os.path.join(base_dir, 'train_img/...

network_output = tf.keras.utils.to_categorical(network_output) AttributeError: 'function' object has no attribute 'utils'

这个错误通常发生在您尝试使用`tf.keras.utils`模块的函数时，但是该模块未正确导入或已被其他模块覆盖。您可以尝试以下解决方案： 1. 确保您已正确导入`tensorflow.keras.utils...希望这些解决方案能帮助您解决问题！

import numpy as np import matplotlib.pyplot as plt from keras.layers import Dense,LSTM,Dropout from keras.models import Sequential # 加载数据 X = np.load("X_od.npy") Y = np.load("Y_od.npy") # 数据归一化 max = np.max(X) X = X / max Y = Y / max # 划分训练集、验证集、测试集 train_x = X[:1000] train_y = Y[:1000] val_x = X[1000:1150] val_y = Y[1000:1150] test_x = X[1150:] test_y = Y # 构建LSTM模型 model = Sequential() model.add(LSTM(units=109, input_shape=(5,109),return_sequences=True)) model.add(Dropout(0.2)) model.add(Dense(units=1, activation='linear')) # 原为Dense(units=109) model.summary() # 编译模型 model.compile(optimizer='adam', loss='mse') # 训练模型 history = model.fit(train_x, train_y, epochs=50, batch_size=32, validation_data=(val_x, val_y), verbose=1, shuffle=False) # 评估模型 test_loss = model.evaluate(test_x, test_y) print('Test loss:', test_loss) # 模型预测 train_predict = model.predict(train_x) val_predict = model.predict(val_x) test_predict = model.predict(test_x) # 预测结果可视化 plt.figure(figsize=(20, 8)) plt.plot(train_y[-100:], label='true') plt.plot(train_predict[-100:], label='predict') plt.legend() plt.title('Training set') plt.show() plt.figure(figsize=(20, 8)) plt.plot(val_y[-50:], label='true') plt.plot(val_predict[-50:], label='predict') plt.legend() plt.title('Validation set') plt.show() plt.figure(figsize=(20, 8)) plt.plot(test_y[:50], label='true') plt.plot(test_predict[:50], label='predict') plt.legend() plt.title('Test set') plt.show()如何修改这一代码的数据维度让其可以正常运行

根据代码，输入数据的shape应该为(样本数, 时间步长, 特征数)，...val_x = val_x.reshape(val_x.shape[0], 5, 109) test_x = test_x.reshape(test_x.shape[0], 5, 109) ``` 这样就可以将数据reshape成正确的shape了。

from keras.preprocessing.text import Tokenizer from keras.preprocessing.sequence import pad_sequences from keras.utils import to_categorical import numpy as np MAX_SEQUENCE_LEN = 1000 # 文档限制长度 MAX_WORDS_NUM = 20000 # 词典的个数 VAL_SPLIT_RATIO = 0.2 # 验证集的比例 tokenizer = Tokenizer(num_words=MAX_WORDS_NUM) tokenizer.fit_on_texts(texts) sequences = tokenizer.texts_to_sequences(texts) word_index = tokenizer.word_index print(len(word_index)) # all token found # print(word_index.get('新闻')) # get word index dict_swaped = lambda _dict: {val:key for (key, val) in _dict.items()} word_dict = dict_swaped(word_index) # swap key-value data = pad_sequences(sequences, maxlen=MAX_SEQUENCE_LEN) labels_categorical = to_categorical(np.asarray(labels)) print('Shape of data tensor:', data.shape) print('Shape of label tensor:', labels_categorical.shape) indices = np.arange(data.shape[0]) np.random.shuffle(indices) data = data[indices] labels_categorical = labels_categorical[indices] # split data by ratio val_samples_num = int(VAL_SPLIT_RATIO * data.shape[0]) x_train = data[:-val_samples_num] y_train = labels_categorical[:-val_samples_num] x_val = data[-val_samples_num:] y_val = labels_categorical[-val_samples_num:]

这段代码使用了Keras库中的Tokenizer和pad_sequences方法对文本进行预处理，将文本转化为数字序列，并进行了填充，确保所有文本序列的长度相同。同时也使用了to_categorical方法对标签进行独热编码。最后，将数据集...

tokenizer = Tokenizer(num_words=max_words) tokenizer.fit_on_texts(data['text']) sequences = tokenizer.texts_to_sequences(data['text']) word_index = tokenizer.word_index print('Found %s unique tokens.' % len(word_index)) data = pad_sequences(sequences,maxlen=maxlen) labels = np.array(data[:,:1]) print('Shape of data tensor:',data.shape) print('Shape of label tensor',labels.shape) indices = np.arange(data.shape[0]) np.random.shuffle(indices) data = data[indices] labels = labels[indices] x_train = data[:traing_samples] y_train = data[:traing_samples] x_val = data[traing_samples:traing_samples+validation_samples] y_val = data[traing_samples:traing_samples+validation_samples] model = Sequential() model.add(Embedding(max_words,100,input_length=maxlen)) model.add(Flatten()) model.add(Dense(32,activation='relu')) model.add(Dense(10000,activation='sigmoid')) model.summary() model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc']) history = model.fit(x_train,y_train, epochs=1, batch_size=128, validation_data=[x_val,y_val]) import matplotlib.pyplot as plt acc = history.history['acc'] val_acc = history.history['val_acc'] loss = history.history['loss'] val_loss = history.history['val_loss'] epoachs = range(1,len(acc) + 1) plt.plot(epoachs,acc,'bo',label='Training acc') plt.plot(epoachs,val_acc,'b',label = 'Validation acc') plt.title('Training and validation accuracy') plt.legend() plt.figure() plt.plot(epoachs,loss,'bo',label='Training loss') plt.plot(epoachs,val_loss,'b',label = 'Validation loss') plt.title('Training and validation loss') plt.legend() plt.show() max_len = 10000 x_train = keras.preprocessing.sequence.pad_sequences(x_train, maxlen=max_len) x_test = data[10000:,0:] x_test = keras.preprocessing.sequence.pad_sequences(x_test, maxlen=max_len) # 将标签转换为独热编码 y_train = np.eye(2)[y_train] y_test = data[10000:,:1] y_test = np.eye(2)[y_test]

这段代码中存在几个问题： 1. `labels` 的赋值有误。应该是 `labels = np.array(data[:, 1:])`，因为标签是从第二列开始的。 2. `validation_data` 的格式有误。应该是 `validation_data=(x_val, y_val)`，而不是 ...

train_y=tf.keras.utils.to_categorical(train_y) test_y=tf.keras.utils.to_categorical(test_y)

这段代码使用了Keras中的to_categorical函数，将训练集和测试集的标签进行了One-hot编码，以便于在训练神经网络时使用。在机器学习中，分类任务通常需要将类别标签转换为数字表示，以便于进行模型训练和评估。而...

def test_mobilenet(): train_ds, val_ds, class_names = data_load("D:/AI/dataset/dataset", 224, 224, 4) print(class_names) model = tf.keras.models.load_model("models/mobilenet_245_epoch30.h5") model.summary() loss, accuracy = model.evaluate(val_ds) print('Mobilenet test accuracy :', accuracy)这段代码什么意思，里面的参数是什么意思，详细介绍参数的意思

5. `loss, accuracy = model.evaluate(val_ds)`：使用验证集 `val_ds` 来评估模型的损失和准确率。函数 `evaluate()` 返回两个值，分别是损失和准确率。 6. `print('Mobilenet test accuracy :', accuracy)`：打印...

ImportError: cannot import name 'to_categorical' from 'keras.utils' (d:\py\Anaconda3\envs\tf2.6\lib\site-packages\keras\utils\init.py)

这个错误是因为在keras.utils中找不到to_categorical函数。这个函数在新版本的Keras中已经被移除了。如果你使用的是较新的Keras版本，你可以尝试使用tensorflow.keras.utils中的to_categorical函数。你可以按照...

用python基于fer2013表情数据库实现人脸表情识别，给出代码和运行结果

28273/28273 [==============================] - 13s 449us/step - loss: 0.9844 - accuracy: 0.6451 - val_loss: 1.1117 - val_accuracy: 0.5942 Test loss: 1.0938747529090038 Test accuracy: 0....

利用keras进行MNIST模型的训练和预测并且保存json格式导出model的h6文件

469/469 [==============================] - 6s 13ms/step - loss: 0.2478 - accuracy: 0.9252 - val_loss: 0.1024 - val_accuracy: 0.9677 Epoch 2/10 469/469 [==============================] - 6s 13ms/step -...

import tensorflow as tf from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPool2D, Dropoutfrom tensorflow.keras import Model# 在GPU上运算时，因为cuDNN库本身也有自己的随机数生成器，所以即使tf设置了seed，也不会每次得到相同的结果tf.random.set_seed(100)mnist = tf.keras.datasets.mnist(X_train, y_train), (X_test, y_test) = mnist.load_data()X_train, X_test = X_train/255.0, X_test/255.0# 将特征数据集从(N,32,32)转变成(N,32,32,1),因为Conv2D需要(NHWC)四阶张量结构X_train = X_train[..., tf.newaxis] X_test = X_test[..., tf.newaxis]batch_size = 64# 手动生成mini_batch数据集train_ds = tf.data.Dataset.from_tensor_slices((X_train, y_train)).shuffle(10000).batch(batch_size)test_ds = tf.data.Dataset.from_tensor_slices((X_test, y_test)).batch(batch_size)class Deep_CNN_Model(Model): def init(self): super(Deep_CNN_Model, self).init() self.conv1 = Conv2D(32, 5, activation='relu') self.pool1 = MaxPool2D() self.conv2 = Conv2D(64, 5, activation='relu') self.pool2 = MaxPool2D() self.flatten = Flatten() self.d1 = Dense(128, activation='relu') self.dropout = Dropout(0.2) self.d2 = Dense(10, activation='softmax') def call(self, X): # 无需在此处增加training参数状态。只需要在调用Model.call时，传递training参数即可 X = self.conv1(X) X = self.pool1(X) X = self.conv2(X) X = self.pool2(X) X = self.flatten(X) X = self.d1(X) X = self.dropout(X) # 无需在此处设置training状态。只需要在调用Model.call时，传递training参数即可 return self.d2(X)model = Deep_CNN_Model()loss_object = tf.keras.losses.SparseCategoricalCrossentropy()optimizer = tf.keras.optimizers.Adam()train_loss = tf.keras.metrics.Mean(name='train_loss')train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')test_loss = tf.keras.metrics.Mean(name='test_loss')test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')# TODO：定义单批次的训练和预测操作@tf.functiondef train_step(images, labels): ...... @tf.functiondef test_step(images, labels): ...... # TODO：执行完整的训练过程EPOCHS = 10for epoch in range(EPOCHS)补全代码

train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy') test_loss = tf.keras.metrics.Mean(name='test_loss') test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='...

通过TensorFlow框架搭建GRU模型实现对IMDB数据集的分析。（付代码及结果截图）

157/157 [==============================] - 13s 78ms/step - loss: 0.5663 - accuracy: 0.6967 - val_loss: 0.3933 - val_accuracy: 0.8392 Epoch 2/10 157/157 [==============================] - 12s 75ms/step...

双向预训练语言模型ELMo，给出python代码及运行结果

125/125 [==============================] - 9s 71ms/step - loss: 0.6018 - accuracy: 0.6840 - val_loss: 0.5233 - val_accuracy: 0.7280 Epoch 2/10 125/125 [==============================] - 4s 31ms/step -...

import numpy as np import tensorflow as tf from tensorflow import keras import matplotlib.pyplot as plt ## Let us define a plt function for simplicity def plt_loss(x,training_metric,testing_metric,ax,colors = ['b']): ax.plot(x,training_metric,'b',label = 'Train') ax.plot(x,testing_metric,'k',label = 'Test') ax.set_xlabel('Epochs') ax.set_ylabel('Accuarcy')# ax.set_ylabel('Categorical Crossentropy Loss') plt.legend() plt.grid() plt.show() tf.keras.utils.set_random_seed(1) ## We import the Minist Dataset using Keras.datasets (train_data, train_labels), (test_data, test_labels) = keras.datasets.mnist.load_data() ## We first vectorize the image (28*28) into a vector （784） train_data = train_data.reshape(train_data.shape[0],train_data.shape[1]train_data.shape[2]) # 60000784 test_data = test_data.reshape(test_data.shape[0],test_data.shape[1]test_data.shape[2]) # 10000784 ## We next change label number to a 10 dimensional vector, e.g., 1->[0,1,0,0,0,0,0,0,0,0] train_labels = keras.utils.to_categorical(train_labels,10) test_labels = keras.utils.to_categorical(test_labels,10) ## start to build a MLP model N_batch_size = 5000 N_epochs = 100 lr = 0.01 ## we build a three layer model, 784 -> 64 -> 10 MLP_4 = keras.models.Sequential([ keras.layers.Dense(128, input_shape=(784,),activation='relu'), keras.layers.Dense(64,activation='relu'), keras.layers.Dense(10,activation='softmax') ]) MLP_4.compile( optimizer=keras.optimizers.Adam(lr), loss= 'categorical_crossentropy', metrics = ['accuracy'] ) History = MLP_4.fit(train_data[:10000],train_labels[:10000], batch_size = N_batch_size, epochs = N_epochs,validation_data=(test_data,test_labels), shuffle=False) train_acc = History.history['accuracy'] test_acc = History.history['val_accuracy']在该模型的每一层（包括输出层）都分别加入L1，L2正则项训练，分别汇报测试数据准确率

test_acc = History.history['val_accuracy'] print("MLP model with L1 and L2 regularization, test accuracy: ", test_acc[-1]) ``` 在该模型的每一层都加入L1和L2正则化项训练，并且L1和L2正则化项的系数都...

实验名称使用循环神经网络实现影评数据的分类实验目的熟悉循环神经网络在文本分析和分类上的应用实验要求 1.从keras的数据集中加载影评数据，注意需要填充（截断）数据，并转成数组的形式。 2.构建一个神经网络模型，要求使用词嵌入和循环层，并使用划分好的训练集数据训练模型，使用划分好的测试集的数据验证模型，训练迭代20次。 3.获取训练过程中的训练精度、验证精度，并使用matplotlib来绘制精度变化曲线，要求模型的验证精度达到85%以上（注意不是训练精度）。 4.写实验报告，将实验代码和绘制精度变化曲线截图粘贴到实验报告中。实验数据数据来源是keras自带的影评数据集：(imdb)。实验步骤 1.加载数据，并将读取到的数据转换成深度学习所需的格式 2.构建深度学习模型 3.训练模型 4.获取历史精度数据，绘制精度变化折线图

20000/20000 [==============================] - 48s 2ms/step - loss: 0.3085 - accuracy: 0.8806 - val_loss: 0.3294 - val_accuracy: 0.8662 Epoch 4/20 20000/20000 [==============================] - 48s ...

weixin_38593738

粉丝: 0
资源: 925

会员权益专享

解决keras,val_categorical_accuracy:,0.0000e+00问题

评论0

会员权益专享

最新资源

解决keras,val_categorical_accuracy:,0.0000e+00问题

评论0

解决keras GAN训练是loss不发生变化,accuracy一直为0.5的问题

inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5

利用CNN,LSTM,CNN-LSTM,TextCNN,Bi-LSTM和传统的机器学习算法进行情感分析.zip

from keras_frcnn import metrics as metrics_fn ImportError: cannot import name 'metrics' from 'keras_frcnn' (D:\程序\Keras-Faster-RCNN-master-master\keras_frcnn\__init__.py)

network_output = tf.keras.utils.to_categorical(network_output) AttributeError: 'function' object has no attribute 'utils'

train_y=tf.keras.utils.to_categorical(train_y) test_y=tf.keras.utils.to_categorical(test_y)

ImportError: cannot import name 'to_categorical' from 'keras.utils' (d:\py\Anaconda3\envs\tf2.6\lib\site-packages\keras\utils\__init__.py)

用python基于fer2013表情数据库实现人脸表情识别，给出代码和运行结果

利用keras进行MNIST模型的训练和预测并且保存json格式导出model的h6文件

通过TensorFlow框架搭建GRU模型实现对IMDB数据集的分析。（付代码及结果截图）

双向预训练语言模型ELMo，给出python代码及运行结果

会员权益专享

最新资源

from keras_frcnn import metrics as metrics_fn ImportError: cannot import name 'metrics' from 'keras_frcnn' (D:\程序\Keras-Faster-RCNN-master-master\keras_frcnn\init.py)

ImportError: cannot import name 'to_categorical' from 'keras.utils' (d:\py\Anaconda3\envs\tf2.6\lib\site-packages\keras\utils\init.py)