是否有更有效的方法从数据集中提取特征，如下所示：
def extract_features(directory, sample_count):
features = np.zeros(shape=(sample_count, 6, 6, 512))
labels = np.zeros(shape=(sample_count, 6))
generator =
ImageDataGenerator(rescale=1./255).flow_from_directory(directory,
target_size=(Image_Size, Image_Size), batch_size = batch_size,
class_mode='categorical')
i = 0
print('Entering for loop...');
for inputs_batch, labels_batch in generator:
features_batch = conv_base.predict(inputs_batch)
features[i * 20 : (i + 1) * 20] = features_batch
labels[i * 20 : (i + 1) * 20] = labels_batch
i += 1
print(i);
if (i * 20) >= sample_count:
break
return features, labels
由于我的数据集的大小，这个过程花费了相当多的时间，我想知道是否有更好的方法来做到这一点？
提前致谢：）
from keras import layers
from keras import models
from keras import losses
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
from keras.applications.vgg16 import VGG16
import matplotlib.pyplot as plt
import numpy as np
Train_DIR = '/Users/eoind/food/train'
Test_DIR = '/Users/eoind/food/test'
Validation_DIR = '/Users/eoind/food/validation'
Image_Size = 200 # Size of input images to be scaled to
Train_Samples = 6000
Validation_Samples = 3000
Test_Samples = 3000
num_epochs = 30
batch_size = 20
steps_per_epoch = Train_Samples/batch_size
conv_base = VGG16(weights='imagenet', include_top=False, input_shape=
(Image_Size, Image_Size, 3))
conv_base.summary()
print('Conv_Base Summary');
def extract_features(directory, sample_count):
features = np.zeros(shape=(sample_count, 6, 6, 512))
labels = np.zeros(shape=(sample_count, 6))
generator =
ImageDataGenerator(rescale=1./255).flow_from_directory(directory,
target_size=(Image_Size, Image_Size), batch_size = batch_size,
class_mode='categorical')
i = 0
print('Entering for loop...');
for inputs_batch, labels_batch in generator:
features_batch = conv_base.predict(inputs_batch)
features[i * 20 : (i + 1) * 20] = features_batch
labels[i * 20 : (i + 1) * 20] = labels_batch
i += 1
print(i);
if (i * 20) >= sample_count:
break
return features, labels
train_features, train_labels = extract_features(Train_DIR, Train_Samples)
validation_features, validation_labels = extract_features(Validation_DIR,
Validation_Samples)
test_features, test_labels = extract_features(Test_DIR, Test_Samples)
print('Extracting Features');
train_features = np.reshape(train_features, (Train_Samples, 6 * 6 * 512))
validation_features = np.reshape(validation_features, (Validation_Samples, 6 *
6 * 512))
test_features = np.reshape(test_features, (Test_Samples, 6 * 6 * 512))
print('Reshaping Features');
model = models.Sequential()
model.add(layers.Dense(256, activation='relu', input_dim=6 * 6 * 512))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(1, activation='sigmoid'))
model.summary()
print('Model Summary');
model.compile(optimizer=optimizers.RMSprop(lr=1e-4),
loss=losses.categorical_crossentropy,
metrics=['acc'])
print('Compiling Model');
hist = model.fit(train_features, train_labels,
steps_per_epoch = steps_per_epoch,
epochs = num_epochs,
batch_size = batch_size,
verbose = 1,
validation_data = (validation_features, validation_labels))
print('Fitting Model');
train_loss=hist.history['loss']
val_loss=hist.history['val_loss']
train_acc=hist.history['acc']
val_acc=hist.history['val_acc']
xc=range(num_epochs)
fig1=plt.figure(1,figsize=(7,5))
plt.plot(xc,train_loss)
plt.plot(xc,val_loss)
plt.xlabel('Number of Epochs')
plt.ylabel('Loss')
plt.title('Training Loss Vs. Validation Loss')
plt.grid(True)
plt.legend(['Training', 'Validation'])
plt.style.use(['classic'])
fig1.savefig('loss.png')
fig2=plt.figure(2,figsize=(7,5))
plt.plot(xc,train_acc)
plt.plot(xc,val_acc)
plt.xlabel('Number of Epochs')
plt.ylabel('Accuracy')
plt.title('Training Accuracy Vs. Validation Accuracy')
plt.grid(True)
plt.legend(['Training', 'Validation'], loc='upper left')
plt.style.use(['classic'])
fig2.savefig('acc.png')
model.save('food_pretrained.h5') # Save model
Layer (type) Output Shape Param #
=================================================================
input_19 (InputLayer) (None, 200, 200, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 200, 200, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 200, 200, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 100, 100, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 100, 100, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 100, 100, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 50, 50, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 50, 50, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 50, 50, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 50, 50, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 25, 25, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 25, 25, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 25, 25, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 25, 25, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 12, 12, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 6, 6, 512) 0
=================================================================
Total params: 14,714,688
Trainable params: 14,714,688
Non-trainable params: 0
_________________________________________________________________
Conv_Base Summary
Found 6000 images belonging to 6 classes.
Entering for loop...
1
2
3
4
5
6
7
8
9
10
11
12...
答案 0 :(得分：0)
我会说不，我认为没有更有效的方式。必须进行计算，特别是在CPU上它们很慢。 您可以做的最好的事情是通过转换数据集，保存数组，然后在每次训练时加载数据集来避免重新计算。
我经历了同样的事情，直到我崩溃并买了一个GPU ......从那以后我的生活压力就小得多了。如果你买不起别的东西，我强烈建议投资，即使在1050年。您可能必须弄清楚如何处理有限的GPU内存，但它会让事情变得更顺畅。