Question

我使用Tensorflow，Keras和CNN架构的实现制作了图像分类器，该模型运行良好（至少对于我测试过的图像而言），准确率达到了78.87％，这是唯一的我要面对的是要使精度不低于85％。
请注意：
数据集：2个文件夹：[Train Folder ===>每个80个文件夹包含110张图像，Validation文件夹===>每个80个文件夹包含22张图像]图像大小[240-260] x [ 40-60]
以下是我用来创建，保存和测试模型的代码：

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K


# dimensions of our images.
img_width, img_height = 251, 54
#img_width, img_height = 150, 33

train_data_dir = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/test/numbers/data/train'
validation_data_dir = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/test/numbers/data/valid'
nb_train_samples = 8800 #10435
nb_validation_samples = 1763 #2051
epochs = 30 #20 # how much time you want to train your model on the data
batch_size = 32 #16

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(80)) #1
model.add(Activation('softmax')) #sigmoid

model.compile(loss='sparse_categorical_crossentropy',optimizer='rmsprop',metrics=['accuracy'])#categorical_crossentropy #binary_crossentropy

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.1,
    zoom_range=0.05,
    horizontal_flip=False)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

model.save('testX_2.h5') #first_try

最后次要续签

Epoch 30/30
275/275 [==============================] - 38s 137ms/step - loss: 0.9406 - acc: 0.7562 - val_loss: 0.1268 - val_acc: 0.9688

我如何测试模型：

from keras.models import load_model
from keras.preprocessing import image
import matplotlib.pyplot as plt
import numpy as np
import os

result = {"0":"0", "1":"0.25", "2":"0.5", "3":"0.75", "4":"1", "5":"1.25", "6":"1.5", "7":"1.75",
          "47":"2", "48":"2.25", "49":"2.5", "50":"2.75", "52":"3","53":"3.25", "54":"3.5", "55":"3.75", "56":"4", "57":"4.25", "58":"4.5",
          "59":"4.75","60":"5", "61":"5.25", "62":"5.5", "63":"5.75", "64":"6", "65":"6.25","66":"6.5", "67":"6.75", "68":"7", "69":"7.25",
          "70":"7.5", "71":"7.75", "72":"8", "73":"8.25", "74":"8.5", "75":"8.75", "76":"9", "77":"9.25", "78":"9.5", "79":"9.75", "8":"10",
          "9":"10.25", "10":"10.5", "11":"10.75", "12":"11", "13":"11.25", "14":"11.5", "15":"11.75", "16":"12","17":"12.25", "18":"12.5",
          "19":"12.75", "20":"13", "21":"13.25", "22":"13.5", "23":"13.75","24":"14", "25":"14.25", "26":"14.5", "27":"14.75", "28":"15",
          "29":"15.25", "30":"15.5", "31":"15.75", "32":"16", "33":"16.25", "34":"16.5", "35":"16.75", "36":"17", "37":"17.25", "38":"17.5",
          "39":"17.75", "40":"18", "41":"18.25", "42":"18.5", "43":"18.75", "44":"19", "45":"19.25", "46":"19.5", "51":"20"}

def load_image(img_path, show=False):

    img = image.load_img(img_path, target_size=(251, 54))

    img_tensor = image.img_to_array(img)                    # (height, width, channels)
    img_tensor = np.expand_dims(img_tensor, axis=0)         # (1, height, width, channels), add a dimension because the model expects this shape: (batch_size, height, width, channels)
    img_tensor /= 255.                                      # imshow expects values in the range [0, 1]

    if show:
        plt.imshow(img_tensor[0])                           
        plt.axis('off')
        plt.show()

    return img_tensor


if __name__ == "__main__":

    # load model
    model = load_model('C:/Users/ADEM/Desktop/msi_youssef/PFE/other_shit/testX_2.h5')

    # image path
    img_path = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/dataset/5.75/a.png'   


    # load a single image
    new_image = load_image(img_path)

    # check prediction
    #pred = model.predict(new_image)
    pred = model.predict_classes(new_image)
    #print(pred[0])
    print(result[str(pred[0])])

Answer 1

获取有关数据集的所有信息，并考虑到您的CNN模型已经具有约80％的准确性，您可以从训练该模型开始更多的时期（通常> 100时期）开始。这应该可以为您的模型带来所需的提升。

如果仅此一项不起作用，您可以实施：

转化/增强：

在输入模型之前对图像进行变换/增强。
调整模型：

更改模型层并进行超参数调整。

您可以按照此article了解更多信息。

如何提高图像分类器的准确性？

1 个答案: