预训练CNN中特征提取的有效方法

Question

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

由于我的数据集太大，这个过程需要相当长的时间，我想知道是否有更好的方法来完成这个过程？在

提前感谢：）

完整代码：

^{pr2}$

iPython控制台输出

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...

Answer 1

我要说不，我认为没有比这更有效的方法了。计算必须发生，尤其是在CPU上计算速度很慢。您所能做的最好的方法是通过转换数据集、保存数组，然后在每次训练时加载它们来避免重新计算。

我也经历了同样的事情，直到我崩溃，买了一个GPU。。。从那以后，我的生活就没有那么紧张了。我强烈建议你投资，如果你买不起其他东西，即使是1050。你可能要想办法处理有限的GPU内存，但它会让事情变得更顺利。在