Keras中的conv2d和Conv2D有什么区别？

Question

我很困惑与Conv2D和conv2d在Keras。它们之间有什么区别？我认为第一个是层，第二个是后端功能，但这是什么意思？在Conv2D中，我们发送过滤器的数量，过滤器的大小和步幅（Conv2D(64,(3,3),stride=(8,8))(input))但是在conv2d中，我们使用的conv2d(input, kernel, stride=(8,8))是内核（64、3、3），然后将过滤器的数量和大小放在一起吗？我应该在哪里输入内核？您能帮我解决这个问题吗？谢谢。

pytorch中的代码

def apply_conv(self, image, filter_type: str):

        if filter_type == 'dct':
            filters = self.dct_conv_weights
        elif filter_type == 'idct':
            filters = self.idct_conv_weights
        else:
            raise('Unknown filter_type value.')

        image_conv_channels = []
        for channel in range(image.shape[1]):
            image_yuv_ch = image[:, channel, :, :].unsqueeze_(1)
            image_conv = F.conv2d(image_yuv_ch, filters, stride=8)
            image_conv = image_conv.permute(0, 2, 3, 1)
            image_conv = image_conv.view(image_conv.shape[0], image_conv.shape[1], image_conv.shape[2], 8, 8)
            image_conv = image_conv.permute(0, 1, 3, 2, 4)
            image_conv = image_conv.contiguous().view(image_conv.shape[0],
                                                  image_conv.shape[1]*image_conv.shape[2],
                                                  image_conv.shape[3]*image_conv.shape[4])

            image_conv.unsqueeze_(1)

            # image_conv = F.conv2d()
            image_conv_channels.append(image_conv)

        image_conv_stacked = torch.cat(image_conv_channels, dim=1)

        return image_conv_stacked

Keras中更改的代码

def apply_conv(self, image, filter_type: str):

        if filter_type == 'dct':
            filters = self.dct_conv_weights
        elif filter_type == 'idct':
            filters = self.idct_conv_weights
        else:
            raise('Unknown filter_type value.')
        print(image.shape)

        image_conv_channels = []
        for channel in range(image.shape[1]):
            print(image.shape)
            print(channel)
            image_yuv_ch = K.expand_dims(image[:, channel, :, :],1)
            print( image_yuv_ch.shape)
            print(filters.shape)
            image_conv = Kr.backend.conv2d(image_yuv_ch,filters,strides=(8,8),data_format='channels_first')
           image_conv = Kr.backend.permute_dimensions(image_conv,(0, 2, 3, 1))
            image_conv = Kr.backend.reshape(image_conv,(image_conv.shape[0], image_conv.shape[1], image_conv.shape[2], 8, 8))
            image_conv =  Kr.backend.permute_dimensions(image_conv,(0, 1, 3, 2, 4))
            image_conv = Kr.backend.reshape(image_conv,(image_conv.shape[0],
                                                  image_conv.shape[1]*image_conv.shape[2],
                                                  image_conv.shape[3]*image_conv.shape[4]))

            Kr.backend.expand_dims(image_conv,1)

            # image_conv = F.conv2d()
            image_conv_channels.append(image_conv)

        image_conv_stacked = Kr.backend.concatenate(image_conv_channels, axis=1)

        return image_conv_stacked

但是当我执行代码时，它会产生以下错误：

追溯（最近一次通话）：

文件“”，第383行，位于decoded_noise = JpegCompression（）（act11）＃16中

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ keras \ engine \ base_layer.py”，行457，在调用 输出= self.call（输入，** kwargs）中

调用image_dct = self.apply_conv（noised_image，'dct'）中的文件“”，行169

文件“”，第132行，位于apply_conv image_conv = Kr.backend.conv2d（image_yuv_ch，filters，strides =（8,8），data_format ='channels_first'）

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ keras \ backend \ tensorflow_backend.py”，行3650，以conv2d data_format = tf_data_format格式）

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ ops \ nn_ops.py”，行779，卷积data_format = data_format）

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ ops \ nn_ops.py”，第839行，init filter_shape [num_spatial_dims]））

ValueError：输入通道数与过滤器的相应尺寸不匹配，1！= 8

新代码

for channel in range(image.shape[1]):
            image_yuv_ch = K.expand_dims(image[:, channel, :, :],axis=1)
            image_yuv_ch = K.permute_dimensions(image_yuv_ch, (0, 2, 3, 1))
            image_conv = tf.keras.backend.conv2d(image_yuv_ch,kernel=filters,strides=(8,8),padding='same')
            image_conv = tf.keras.backend.reshape(image_conv,(image_conv.shape[0],image_conv.shape[1], image_conv.shape[2],8,8))

错误：

追溯（最近一次通话）：

文件“”，第263行，位于decoded_noise = JpegCompression（）（act11）＃16中

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ keras \ engine \ base_layer.py”，行457，在调用 输出= self.call（输入，** kwargs）中

呼叫image_dct = self.apply_conv（noised_image，'dct'）中的文件“”，行166

文件“”，行128，位于apply_conv image_conv = tf.keras.backend.reshape（image_conv，（image_conv.shape [0]，image_conv.shape [1]，image_conv.shape [2]，8,8））

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ keras \ backend.py”，第2281行，重塑形式返回array_ops.reshape（x，shape）

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ ops \ gen_array_ops.py”，行6482，重塑为“ Reshape”，张量=张量，shape =形状，名称=名称）

_apply_op_helper中的文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ framework \ op_def_library.py”行513引发错误

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ framework \ op_def_library.py”，行510，在_apply_op_helper preferred_dtype = default_dtype中）

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ framework \ ops.py”，行1146，在internal_convert_to_tensor中ret = conversion_func（value，dtype = dtype，name = name，as_ref = as_ref）

_constant_tensor_conversion_function中的文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ framework \ constant_op.py”第229行返回常量（v，dtype = dtype，name = name）

文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ framework \ constant_op.py”，第208行，常量值，dtype = dtype，shape = shape，verify_shape = verify_shape））

make_tensor_proto“受支持的类型”中的文件“ D：\ software \ Anaconda3 \ envs \ py36 \ lib \ site-packages \ tensorflow \ python \ framework \ tensor_util.py”，行531。％（类型（值），值）

TypeError：无法将类型的对象转换为Tensor。内容：（Dimension（None），Dimension（4），Dimension（4），8，8）。考虑将元素强制转换为受支持的类型。

Answer 1

Tensorflow和Keras现在正在使用channel_last约定。因此，首先您应将通道暗淡置换为最后一个使用K.permute_dimension。您可以在colab.research.google.com中尝试使用此代码来弄清楚自己。

第一个问题：

• conv2d是执行2D卷积文档的功能
• keras.layers.Conv2D() will return an instance of class Conv2D which perform convolution function. See more here

# The second 
import keras
conv_layer = keras.layers.Conv2D(filters=64, kernel_size=8, strides=(4, 4), padding='same')

Basically, they differ from the way to define and the way to use. K.conv2d is used inside keras.layers.Conv2D when conv_layer apply convolution on some input x such as conv_layer.

The example below may help you to understand it easier the difference between say_hello and SayHello.

def say_hello(word, name):
    print(word, name)


class SayHello():

    def __init__(self, word='Hello'):
        self.word = word
        pass

    def __call__(self, name):
        say_hello(self.word, name)


say_hello('Hello', 'Nadia') #Hello Nadia

sayhello = SayHello(word='Hello') # you will get an instance `sayhello` from class SayHello

sayhello('Nadia') # Hello Nadia

Second question:

• kernel here is a tensor of shape (kernel_size, kernel_size, in_channels, out_channels)
• If you want to get the image_conv of shape (8, 8, 64) then the strides=(4,4).

import tensorflow as tf
import tensorflow.keras.backend as K

image = tf.random_normal((10,3, 32, 32))
print(image.shape) # shape=(10, 3, 32, 32)

channel = 1
image_yuv_ch = K.expand_dims(image[:, channel,:,:], axis=1) # shape=(10, 1, 32, 32)
image_yuv_ch = K.permute_dimensions(image_yuv_ch, (0, 2, 3, 1)) # shape=(10, 32, 32, 1)

# The first K.conv2d
in_channels = 1
out_channels = 64 # same as filters
kernel = tf.random_normal((8, 8, in_channels, out_channels)) # shape=(8, 8, 1, 64)

image_conv = tf.keras.backend.conv2d(image_yuv_ch, kernel=kernel, strides=(4, 4), padding='same')
print(image_conv.shape) #shape=(10, 8, 8, 64)


# The second 
import keras
conv_layer = keras.layers.Conv2D(filters=64, kernel_size=8, strides=(4, 4), padding='same')
image_conv = conv_layer(image_yuv_ch)
print(image_conv.shape) #shape=(10, 8, 8, 64)