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

Question

我正在尝试训练用于图像字符识别的卷积神经网络。一张图片包含 7 个字符（0-9、AZ、空格 => 37 个字符的可能性）。总共有 646 张图像。这些图像是 X_train 数据。

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

我还有一个包含所有图像标签的数据表。我对这些标签进行了一次热编码以获取数组。

y_train.shape
(646, 7, 37)

646是图像的数量，所以是行维度。7是标签的长度，列的尺寸。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，而无需像本文中的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)

感谢您的所有建议！

标签： pythonarraystensorflowneural-networkconv-neural-network

Answer 1

我重新定义了网络以匹配 y 输出形状，我可以对性能说任何话

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        
=================================================================