前端之家

  1. 首页
  2. 问答

切换到数据集后精度不再提高

• 问答

我最近训练了一个二进制图像分类器，并最终得到了一个准确率约为97.8％的模型。我通过遵循几个官方Tensorflow指南创建了这个分类器，即：

在训练（在GTX 1080上）时，我注意到每个纪元大约需要30秒才能运行。进一步的阅读显示，将数据加载到Tensorflow训练运行中的更好方法是使用数据集。因此，我更新了代码以将图像加载到数据集中，然后通过model.fit_generator方法读取它们。

现在，当我进行培训时，我发现我的准确性和损失指标是静态的-即使学习率会随着时间而自动变化。输出看起来像这样：

loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000

鉴于我正在训练二进制分类器，其准确度为50％与猜测相同，所以我想知道我提供图像的方式或数据集大小是否存在问题

我的图像数据被这样分割：

training/
        true/  (366 images)
        false/ (354 images)

validation/
        true/  (175 images)
        false/ (885 images)

我以前使用ImageDataGenerator进行各种突变，因此增加了整体数据集。我的数据集大小有问题吗？

我正在使用的应用程序代码如下：

import math

import tensorflow as tf
import os

from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.callbacks import EarlyStopping

import helpers
import settings

AUTOTUNE = tf.data.experimental.AUTOTUNE

assert tf.test.is_built_with_cuda()
assert tf.test.is_gpu_available()

# Collect the list of training files and process their paths.
training_dataset_files = tf.data.Dataset.list_files(os.path.join(settings.TRAINING_DIRECTORY,'*','*.png'))
training_dataset_labelled = training_dataset_files.map(helpers.process_path,num_parallel_calls=AUTOTUNE)
training_dataset = helpers.prepare_for_training(training_dataset_labelled)

# Collect the validation files.
validation_dataset_files = tf.data.Dataset.list_files(os.path.join(settings.VALIDATION_DIRECTORY,'*.png'))
validation_dataset_labelled = validation_dataset_files.map(helpers.process_path,num_parallel_calls=AUTOTUNE)
validation_dataset = helpers.prepare_for_training(validation_dataset_labelled)

model = tf.keras.models.Sequential([
    # This is the first convolution
    tf.keras.layers.Conv2D(16,(3,3),activation='relu',input_shape=(settings.TARGET_IMAGE_HEIGHT,settings.TARGET_IMAGE_WIDTH,3)),tf.keras.layers.MaxPooling2D(2,2),# The second convolution
    tf.keras.layers.Conv2D(32,activation='relu'),# The third convolution
    tf.keras.layers.Conv2D(64,# The fourth convolution
    tf.keras.layers.Conv2D(64,# The fifth convolution
    tf.keras.layers.Conv2D(64,# flatten the results to feed into a DNN
    tf.keras.layers.flatten(),# 512 neuron hidden layer
    tf.keras.layers.Dense(512,# Only 1 output neuron. It will contain a value from 0-1 where 0 for 1 class ('false') and 1 for the other ('true')
    tf.keras.layers.Dense(1,activation='sigmoid')
])

model.summary()

model.compile(
    loss='binary_crossentropy',optimizer=RMSprop(lr=0.1),metrics=['acc']
)

callbacks = [
    # EarlyStopping(patience=4),tf.keras.callbacks.ReduceLROnPlateau(
        monitor='val_acc',patience=2,verbose=1,factor=0.5,min_lr=0.00001
    ),tf.keras.callbacks.ModelCheckpoint(
        # Path where to save the model
        filepath=settings.CHECKPOINT_FILE,# The two parameters below mean that we will overwrite
        # the current checkpoint if and only if
        # the `val_loss` score has improved.
        save_best_only=True,monitor='val_loss',verbose=1
    ),tf.keras.callbacks.TensorBoard(
        log_dir=settings.LOG_DIRECTORY,histogram_freq=1
    )
]

training_dataset_length = tf.data.experimental.cardinality(training_dataset_files).numpy()
steps_per_epoch = math.ceil(training_dataset_length // settings.TRAINING_BATCH_SIZE)

validation_dataset_length = tf.data.experimental.cardinality(validation_dataset_files).numpy()
validation_steps = math.ceil(validation_dataset_length // settings.VALIDATION_BATCH_SIZE)

history = model.fit_generator(
    training_dataset,steps_per_epoch=steps_per_epoch,epochs=20000,validation_data=validation_dataset,validation_steps=validation_steps,callbacks=callbacks,)

model.save(settings.FULL_MODEL_FILE)

helpers.py如下所示：

import tensorflow as tf
import settings

AUTOTUNE = tf.data.experimental.AUTOTUNE


def process_path(file_path):
    parts = tf.strings.split(file_path,'\\')
    label = parts[-2] == settings.CLASS_NAMES

    # Read the file and decode the image
    img = tf.io.read_file(file_path)
    img = tf.image.decode_png(img,channels=3)
    img = tf.image.convert_image_dtype(img,tf.float32)
    img = tf.image.resize(img,[settings.TARGET_IMAGE_HEIGHT,settings.TARGET_IMAGE_WIDTH])
    return img,label


def prepare_for_training(ds,cache=True,shuffle_buffer_size=10000):
    if cache:
        if isinstance(cache,str):
            ds = ds.cache(cache)
        else:
            ds = ds.cache()

    ds = ds.shuffle(buffer_size=shuffle_buffer_size)

    ds = ds.repeat()
    ds = ds.batch(settings.TRAINING_BATCH_SIZE)
    ds = ds.prefetch(buffer_size=AUTOTUNE)

    return ds

更大的应用程序输出片段如下：

21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00207: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 247ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 208/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00208: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 248ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 209/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00209: val_loss did not improve from 7.71247
22/22 [==============================] - 6s 251ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 210/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00210: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 242ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 211/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00211: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 246ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 212/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00212: val_loss did not improve from 7.71247
22/22 [==============================] - 6s 252ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 213/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00213: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 242ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 214/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00214: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 241ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 215/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00215: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 247ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 216/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00216: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 248ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 217/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00217: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 249ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 218/20000
21/22 [===========================>..] - eta: 0s - loss: 7.7125 - acc: 0.5000
Epoch 00218: val_loss did not improve from 7.71247
22/22 [==============================] - 5s 244ms/step - loss: 7.7125 - acc: 0.5000 - val_loss: 7.7125 - val_acc: 0.5000
Epoch 219/20000
19/22 [========================>.....] - eta: 0s - loss: 7.7125 - acc: 0.5000
gundamblade 回答：切换到数据集后精度不再提高

您必须检查一些内容。

  • 再尝试几次，您可能不喜欢'relu'激活（如果一层变为全零，则将永远卡住）。
  • 从数据集中获取一个x,y对，并验证y在0和1之间（因为您使用的是“ Sigmoid”）。

这两个是最麻烦和可能的事情。

稍后，如果通道数相同，您可能想检查数据集中的x是否在您之前训练的范围内（不是很重要，但可能会改变一点性能）。

对于relus，有诸如this one之类的解决方案。

,

首先删除所有图像增强。 然后，在包含扩展数据集之后，在较小的数据集上对模型进行过度拟合。 另请注意： 训练/         真实/（366张图像）         false /（354张图片）

验证/         真实/（175张图像）         假/（885图像） 您的验证数据集看起来太复杂了，我想尝试在训练数据集中添加更多百分比的图像。

,

当代码运行良好时，应突出显示与代码相比所做的更改。

我希望process_path函数能够保持安静，并且不会出现任何错误（图像解码，通道管理，标签生成）。

因此，如果修改仅与Dataset API有关，则可以通过检查生成的示例开始：

batch = next(iter(training_dataset))
tf.print("Image: ",batch[0][0])
tf.print("Label: ",batch[1][0])

其他似乎很奇怪的东西：

  • 大小为10000的随机播放缓冲区对于您的+700张图片来说似乎很大
  • 您确定自己的steps_per_epoch值吗？数据集基数并不总是很准确。
deep-learningkerasmachine-learningtensorflow
本文链接：https://www.f2er.com/3148573.html

大家都在问