获取Keras模型中间层输出

使用Keras可以比较方便地搭建一些深度学习网络，获取中间层输出可以帮助理解它是如何运行的。这里使用一个小型的Keras网络，对Caltech101数据集进行图像分类，并获取中间层输出结果，以及手工计算卷积层的输出结果。

修正：表示当前是训练模式还是测试模式的参数K.learning_phase()文中表述和使用有误，在该函数说明中可以看到：

The learning phase flag is a bool tensor (0 = test, 1 = train)，所以0是测试模式，1是训练模式，部分网络结构下两者有差别。

 

我使用的版本：

1.      WIN7系统

2.      Python 2.7.10.2

3.      Keras 2.0.8

4.      Theano 0.9.0

5.      numpy 1.13.1

6.      h5py 2.5.0

7.      OpenCV 2.4.13

在ubuntu中也可运行，需要修改文件路径，并且如果在ubuntu中使用的后端是tensorflow，后面的kernel不需要翻转。我的Keras设置中总是："image_data_format": "channels_last"。

参考资料：

1.      http://keras-cn.readthedocs.io/en/latest/for_beginners/FAQ/#intermediate_layer

2.      cs231n_2017_lecture5

 

从文件夹中提取图像数据的方式：

函数：

def eachFile(filepath):                 #将目录内的文件名放入列表中
    pathDir =  os.listdir(filepath)
    out = []
    for allDir in pathDir:
        child = allDir.decode('gbk')    # .decode('gbk')是解决中文显示乱码问题
        out.append(child)
    return out
def get_data(data_name,train_left=0.0,train_right=0.7,train_all=0.7,resize=True,data_format=None,t=''):   #从文件夹中获取图像数据
    file_name = os.path.join(pic_dir_out,data_name+t+'_'+str(train_left)+'_'+str(train_right)+'_'+str(Width)+"X"+str(Height)+".h5")   
    print file_name
    if os.path.exists(file_name):           #判断之前是否有存到文件中
        f = h5py.File(file_name,'r')
        if t=='train':
            X_train = f['X_train'][:]
            y_train = f['y_train'][:]
            f.close()
            return (X_train, y_train)
        elif t=='test':
            X_test = f['X_test'][:]
            y_test = f['y_test'][:]
            f.close()
            return (X_test, y_test)  
        else:
            return
    data_format = conv_utils.normalize_data_format(data_format)
    pic_dir_set = eachFile(pic_dir_data)
    X_train = []
    y_train = []
    X_test = []
    y_test = []
    label = 0
    for pic_dir in pic_dir_set:
        print pic_dir_data+pic_dir
        if not os.path.isdir(os.path.join(pic_dir_data,pic_dir)):
            continue    
        pic_set = eachFile(os.path.join(pic_dir_data,pic_dir))
        pic_index = 0
        train_count = int(len(pic_set)*train_all)
        train_l = int(len(pic_set)*train_left)
        train_r = int(len(pic_set)*train_right)
        for pic_name in pic_set:
            if not os.path.isfile(os.path.join(pic_dir_data,pic_dir,pic_name)):
                continue            
            img = cv2.imread(os.path.join(pic_dir_data,pic_dir,pic_name))
            if img is None:
                continue
            if (resize):
                img = cv2.resize(img,(Width,Height))
            if (data_format == 'channels_last'):
                img = img.reshape(-1,Width,Height,3)
            elif (data_format == 'channels_first'):
                img = img.reshape(-1,Width,Height,3)
                img = img.transpose(0, 3, 1, 2)
            if (pic_index < train_count):
                if t=='train':
                    if (pic_index >= train_l and pic_index < train_r):
                        X_train.append(img)
                        y_train.append(label)          
            else:
                if t=='test':
                    X_test.append(img)
                    y_test.append(label)
            pic_index += 1
        if len(pic_set) <> 0:        
            label += 1
     
    f = h5py.File(file_name,'w')
    if t=='train':
        X_train = np.concatenate(X_train,axis=0)     
        y_train = np.array(y_train)      
        f.create_dataset('X_train', data = X_train)
        f.create_dataset('y_train', data = y_train)
        f.close()
        return (X_train, y_train)
    elif t=='test':
        X_test = np.concatenate(X_tes