繁体   English   中英

X_train 和 y_train 匹配吗? 卷积神经网络——无分割字符识别

[英]Do X_train and y_train match? Convolutional Neural Network - Segmentation free character recognition

我正在尝试训练一个卷积神经网络来识别图像上的字符。 一张图像包含 7 个字符(0-9、AZ、空格 => 字符的 37 种可能性)。 总共有 646 张图片。 这些图像是 X_train 数据。

X_train.shape
(646, 600, 1200, 1)

我还有一个包含图像所有标签的数据表。 我对这些标签进行了单热编码以获得 arrays。

y_train.shape
(646, 7, 37)

646是图像的数量,所以是行维度。 7是label的长度,列维度。 37是可能的字符数,深度维度。

我希望我的卷积神经网络能够自动识别图像上的字符,而无需像本文作者那样对字符进行任何分割或空间规范: https://ieeexplore.ieee.org/abstract/document/8078501

我现在想知道 X_train 和 y_train 是否适合我的神经网络? 也许我必须重塑 X_train 或 y_train 的维度,因为当我运行这段代码时:

from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), input_shape = (600, 1200, 1), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(64, activation = "relu"))
model.add(Dense(7, activation = "relu"))
model.add(Dense(37, activation = "softmax"))

model.compile(optimizer="rmsprop", loss="categorical_crossentropy", metrics=["accuracy"])

model.fit(X_train, y_train, batch_size = 32, epochs = 10, shuffle = True)

我收到以下错误:

ValueError: Error when checking target: expected dense_3 to have 2 dimensions, but got array with shape (646, 7, 37)

谢谢大家的建议!

我重新定义了 .networks 以匹配 y output 形状,我可以对表演说些什么

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), input_shape = (600, 1200, 1), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Lambda(lambda x: tf.expand_dims(x,1)))
model.add(Dense(64, activation = "relu"))
model.add(Dense(7, activation = "relu"))
model.add(Permute((2, 1)))
model.add(Dense(37, activation = "softmax"))

摘要:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_6 (Conv2D)            (None, 598, 1198, 32)     320       
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 299, 599, 32)      0         
_________________________________________________________________
dropout_6 (Dropout)          (None, 299, 599, 32)      0         
_________________________________________________________________
flatten_5 (Flatten)          (None, 5731232)           0         
_________________________________________________________________
lambda_3 (Lambda)            (None, 1, 5731232)        0         
_________________________________________________________________
dense_15 (Dense)             (None, 1, 64)             366798912 
_________________________________________________________________
dense_16 (Dense)             (None, 1, 7)              455       
_________________________________________________________________
permute (Permute)            (None, 7, 1)              0         
_________________________________________________________________
dense_17 (Dense)             (None, 7, 37)             74        
=================================================================

暂无
暂无

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM