我正在尝试配置一个网络,用于像车牌这样的顺序数据的字符识别。现在我想使用深度自动车牌识别系统(链接:http://www.ee.iisc.ac.in/people/faculty/soma.biswas/Papers/jain_icgvip2016_alpr.pdf)中的表3所示的体系结构。
作者提出的架构是这样的:

第一层非常常见,但我遇到的问题是架构的顶部(红色框架中的部分)。他们提到了11个并行层,我真的不确定如何在Python中实现这一点。我编写了这个架构的代码,但它似乎并不适合我。
model = Sequential()
model.add(Conv2D(64, kernel_size=(5, 5), input_shape = (32, 96, 3), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(128, kernel_size=(3, 3), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(256, kernel_size=(3, 3), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1024, activation = "relu"))
model.add(Dense(11*37, activation="Softmax"))
model.add(keras.layers.Reshape((11, 37)))有人能帮帮忙吗?我如何对顶部进行编码,才能获得与作者相同的体系结构?
发布于 2020-07-07 01:59:26
下面的代码可以构建如图所示的架构。
import tensorflow as tf
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import Conv2D, Flatten, MaxPooling2D, Dense, Input, Reshape, Concatenate, Dropout
def create_model(input_shape = (32, 96, 1)):
input_img = Input(shape=input_shape)
'''
Add the ST Layer here.
'''
model = Conv2D(64, kernel_size=(5, 5), input_shape = input_shape, activation = "relu")(input_img)
model = MaxPooling2D(pool_size=(2, 2))(model)
model = Dropout(0.25)(model)
model = Conv2D(128, kernel_size=(3, 3), input_shape = input_shape, activation = "relu")(model)
model = MaxPooling2D(pool_size=(2, 2))(model)
model = Dropout(0.25)(model)
model = Conv2D(256, kernel_size=(3, 3), input_shape = input_shape, activation = "relu")(model)
model = MaxPooling2D(pool_size=(2, 2))(model)
model = Dropout(0.25)(model)
model = Flatten()(model)
backbone = Dense(1024, activation="relu")(model)
branches = []
for i in range(11):
branches.append(backbone)
branches[i] = Dense(37, activation = "softmax", name="branch_"+str(i))(branches[i])
output = Concatenate(axis=1)(branches)
output = Reshape((11, 37))(output)
model = Model(input_img, output)
return model

发布于 2020-07-06 21:06:46
据我所知,您的实现几乎是正确的。作者以完全连接层的输出为输入训练了11个单独的分类器。在这里,你可以把“并行”理解为“独立”。
但是,您不能在完全连接的层之后立即应用Softmax激活。由于所有分类器都是独立的,我们希望每个分类器都为每个可能的字符输出一个概率。换句话说,我们希望每个分类器的输出之和为1。因此,正确的实现应该是:
...
model.add(Dense(1024, activation = "relu"))
# Feeding every neuron with the previous layer's output
model.add(Dense(11*37))
model.add(keras.layers.Reshape((11, 37)))
model.add(keras.activations.softmax(x, axis=1))https://stackoverflow.com/questions/62695857
复制相似问题