我在val_acc=0.97良好且使用model.fit_generator的图像上训练了CNN网络模型。
这是最后一个纪元的输出，证明了较高的验证准确性：
199/200 [============================>.] - ETA: 1s - loss: 0.1563 - acc: 0.9563
200/200 [==============================] - 306s 2s/step - loss: 0.1556 - acc: 0.9565 - val_loss: 0.1402 - val_acc: 0.9691
Epoch 00005: val_acc improved from 0.96701 to 0.96907, saving model to /home/sergorl/cars/color_weights.hdf5
但是，当我使用训练期间使用的相同验证数据集，但仅测试一张图像时，对于验证集中的每张图像，我总是得到错误的预测标签，并且预测概率看起来像是均匀分布。 / p>
我阅读了以下链接： Wrong prediction on images
Why is Keras training well but returning wrong predictions?
Keras Val_acc is good but prediction for same data is poor
但是我找不到解决方案！
from keras.models import Sequential,Model,load_model
from keras.optimizers import SGD
from keras.layers import BatchNormalization, Lambda, Input, Dense, Convolution2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, Dropout, Flatten, merge, Reshape, Activation
from keras.layers.merge import Concatenate
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint
import os
import cv2
import numpy as np
class CarColorNet:
def __init__(self, numClasses=6, imageWidth=256, imageHeight=256):
self.classes = {}
self.numClasses = numClasses
self.imageWidth = imageWidth
self.imageHeight = imageHeight
input_image = Input(shape=(self.imageWidth, self.imageHeight, 3))
# ------------------------------------ TOP BRANCH ------------------------------------
# first top convolution layer
top_conv1 = Convolution2D(filters=48, kernel_size=(11, 11), strides=(4, 4),
input_shape=(self.imageWidth, self.imageHeight, 3), activation='relu')(input_image)
top_conv1 = BatchNormalization()(top_conv1)
top_conv1 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(top_conv1)
# second top convolution layer
# split feature map by half
top_top_conv2 = Lambda(lambda x: x[:, :, :, :24])(top_conv1)
top_bot_conv2 = Lambda(lambda x: x[:, :, :, 24:])(top_conv1)
top_top_conv2 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(top_top_conv2)
top_top_conv2 = BatchNormalization()(top_top_conv2)
top_top_conv2 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(top_top_conv2)
top_bot_conv2 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(top_bot_conv2)
top_bot_conv2 = BatchNormalization()(top_bot_conv2)
top_bot_conv2 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(top_bot_conv2)
# third top convolution layer
# concat 2 feature map
top_conv3 = Concatenate()([top_top_conv2, top_bot_conv2])
top_conv3 = Convolution2D(filters=192, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(top_conv3)
# fourth top convolution layer
# split feature map by half
top_top_conv4 = Lambda(lambda x: x[:, :, :, :96])(top_conv3)
top_bot_conv4 = Lambda(lambda x: x[:, :, :, 96:])(top_conv3)
top_top_conv4 = Convolution2D(filters=96, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(top_top_conv4)
top_bot_conv4 = Convolution2D(filters=96, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(top_bot_conv4)
# fifth top convolution layer
top_top_conv5 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(top_top_conv4)
top_top_conv5 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(top_top_conv5)
top_bot_conv5 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(top_bot_conv4)
top_bot_conv5 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(top_bot_conv5)
# ------------------------------------ TOP BOTTOM ------------------------------------
# first bottom convolution layer
bottom_conv1 = Convolution2D(filters=48, kernel_size=(11, 11), strides=(4, 4),
input_shape=(224, 224, 3), activation='relu')(input_image)
bottom_conv1 = BatchNormalization()(bottom_conv1)
bottom_conv1 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(bottom_conv1)
# second bottom convolution layer
# split feature map by half
bottom_top_conv2 = Lambda(lambda x: x[:, :, :, :24])(bottom_conv1)
bottom_bot_conv2 = Lambda(lambda x: x[:, :, :, 24:])(bottom_conv1)
bottom_top_conv2 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(bottom_top_conv2)
bottom_top_conv2 = BatchNormalization()(bottom_top_conv2)
bottom_top_conv2 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(bottom_top_conv2)
bottom_bot_conv2 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(bottom_bot_conv2)
bottom_bot_conv2 = BatchNormalization()(bottom_bot_conv2)
bottom_bot_conv2 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(bottom_bot_conv2)
# third bottom convolution layer
# concat 2 feature map
bottom_conv3 = Concatenate()([bottom_top_conv2, bottom_bot_conv2])
bottom_conv3 = Convolution2D(filters=192, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(bottom_conv3)
# fourth bottom convolution layer
# split feature map by half
bottom_top_conv4 = Lambda(lambda x: x[:, :, :, :96])(bottom_conv3)
bottom_bot_conv4 = Lambda(lambda x: x[:, :, :, 96:])(bottom_conv3)
bottom_top_conv4 = Convolution2D(filters=96, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(bottom_top_conv4)
bottom_bot_conv4 = Convolution2D(filters=96, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(bottom_bot_conv4)
# fifth bottom convolution layer
bottom_top_conv5 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(bottom_top_conv4)
bottom_top_conv5 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(bottom_top_conv5)
bottom_bot_conv5 = Convolution2D(filters=64, kernel_size=(3, 3), strides=(1, 1), activation='relu',
padding='same')(bottom_bot_conv4)
bottom_bot_conv5 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(bottom_bot_conv5)
# ---------------------------------- CONCATENATE TOP AND BOTTOM BRANCH ------------------------------------
conv_output = Concatenate()([top_top_conv5, top_bot_conv5, bottom_top_conv5, bottom_bot_conv5])
# Flatten
flatten = Flatten()(conv_output)
# Fully-connected layer
FC_1 = Dense(units=4096, activation='relu')(flatten)
FC_1 = Dropout(0.6)(FC_1)
FC_2 = Dense(units=4096, activation='relu')(FC_1)
FC_2 = Dropout(0.6)(FC_2)
output = Dense(units=self.numClasses, activation='softmax')(FC_2)
self.model = Model(inputs=input_image, outputs=output)
sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)
# sgd = SGD(lr=0.01, momentum=0.9, decay=0.0005, nesterov=True)
self.model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])
def train(self,
pathToTrainSet,
pathToValidSet,
pathToSaveModel,
epochs=7,
batchSize=32,
stepsPerEpoch=200,
validationSteps=1000):
fileOfWeights = 'color_weights.hdf5'
checkpoint = ModelCheckpoint(os.path.join(pathToSaveModel, fileOfWeights),
monitor='val_acc', verbose=1,
save_best_only=True, mode='max')
checkpoint2 = ModelCheckpoint(os.path.join(pathToSaveModel, fileOfWeights),
monitor='val_loss', verbose=1,
save_best_only=True, mode='max')
trainDataGen = ImageDataGenerator(rescale=1.0/255, shear_range=0.2,
zoom_range=0.3, horizontal_flip=True)
validDataGen = ImageDataGenerator(rescale=1.0/255)
trainSet = trainDataGen.flow_from_directory(
pathToTrainSet,
target_size=(self.imageWidth, self.imageHeight),
batch_size=batchSize,
class_mode='categorical'
)
self.classes = {v: k for k, v in trainSet.class_indices.items()}
np.save(os.path.join(pathToSaveModel, 'class_index.npy'), self.classes)
validSet = validDataGen.flow_from_directory(
pathToValidSet,
target_size=(self.imageWidth, self.imageHeight),
batch_size=batchSize,
class_mode='categorical'
)
self.model.fit_generator(
trainSet,
steps_per_epoch=stepsPerEpoch,
epochs=epochs,
validation_data=validSet,
validation_steps=validationSteps//batchSize,
callbacks=[checkpoint, checkpoint2])
print('============================ Saving is here ============================')
self.model.save(os.path.join(pathToSaveModel, 'car_color_net.h5'))
@staticmethod
def load(pathToModel, pathToClassIndexes):
model = load_model(pathToModel)
layers = model.layers
inputShape, outputShape = layers[0].input_shape, layers[-1].output_shape,
imageWidth, imageHeight = inputShape[1], inputShape[2]
numClasses = outputShape[1]
net = CarColorNet(numClasses, imageWidth, imageHeight)
net.classes = np.load(os.path.join(pathToClassIndexes, 'class_index.npy')).item()
return net
def predictOneImage(self, pathToImage):
frame = cv2.imread(pathToImage)
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame = cv2.resize(frame, (self.imageWidth, self.imageHeight))
frame = np.expand_dims(frame, axis=0)
# cv2.imshow("boxed", frame[0, :, :, :])
# cv2.waitKey(0)
frame = np.asarray(frame, dtype='float32')
img = frame/255
probs = self.model.predict(img)
ind = probs.argmax(axis=-1)[0]
return self.classes[ind]
if __name__ == '__main__':
pathToTrainSet = '/home/sergorl/cars/train'
pathToValidSet = '/home/sergorl/cars/valid'
pathToSaveModel = '/home/sergorl/cars'
## Train net
# net = CarColorNet(numClasses=6)
# net.train(pathToTrainSet, pathToValidSet, pathToSaveModel)
# Test on all images from validSet
net = CarColorNet.load(os.path.join(pathToSaveModel, 'car_color_net.h5'), pathToSaveModel)
count, countTrueLabels = 0, 0
for dirpath, _dirnames, filenames in os.walk(pathToValidSet):
trueLabel = dirpath.split('/')[-1]
for file in filenames:
label = net.predictOneImage(os.path.join(dirpath, file))
print(trueLabel, label)
if label == trueLabel:
countTrueLabels += 1
count += 1
print('rate is {0:.2f}'.format(float(countTrueLabels) / float(count) * 100))
如果我的val_acc=0.97不错，我会期望（或几乎）相同的结果，测试验证集中的每个图像。但是总是有错误的预测！
培训结束后，我立即上网了，发现学习很好：
if __name__ == '__main__':
pathToTrainSet = '/home/sergorl/cars/train'
pathToValidSet = '/home/sergorl/cars/valid'
pathToSaveModel = '/home/sergorl/cars'
# Train net
net = CarColorNet(numClasses=6)
net.train(pathToTrainSet, pathToValidSet, pathToSaveModel)
# Test on all images from validSet
count, countTrueLabels = 0, 0
for dirpath, _dirnames, filenames in os.walk(pathToValidSet):
trueLabel = dirpath.split('/')[-1]
for file in filenames:
label = net.predictOneImage(os.path.join(dirpath, file))
print(trueLabel, label)
if label == trueLabel:
countTrueLabels += 1
count += 1
print('rate is {0:.2f}'.format(float(countTrueLabels) / float(count) * 100))
所以看来问题出在model.save内部，并且看来保存不起作用！我在git上发现了许多相关问题，例如：
https://github.com/keras-team/keras/issues/4875
https://github.com/keras-team/keras/issues/4904
但是我不知道如何使用Python 3.7.3和keras 2.0.0
答案 0 :(得分：0)
您能否分享有关该问题的更多信息，例如获得的输出是什么？从代码中，我可以看到您正在训练6个类，并使用分类交叉熵，因此理想情况下，您应该得到一个包含6个值的数组，每个值的bw为0和1，并且该数组中最高值的索引应该为输出。