ValueError: Negative dimension size caused by subtracting 3 from 1 for 'pool1/MaxPool'

最新推荐文章于 2022-11-06 19:42:40 发布

smellycat17

最新推荐文章于 2022-11-06 19:42:40 发布

阅读量3.2k

点赞数 3

文章标签： ValueError: Negative dimension size

本文链接：https://blog.youkuaiyun.com/smellycat17/article/details/96634305

版权

在定义LetNet5网络模型时候，遇到了下述问题
此为图片通道数据格式问题

def LeNet5(w_path=None):
	input_shape = (1, img_rows, img_cols)
	img_input = Input(shape=input_shape)
	
	x = Conv2D(32, (3, 3), activation="relu", padding="same", name="conv1")	(img_input)
	x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(x)
		x = Conv2D(64, (3, 3), activation="relu", padding='same', name='conv2')(x)
	x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2')(x)
	x = Dropout(0.25)(x)
	
	x = Flatten(name='flatten')(x)
	
	x = Dense(128, activation='relu', name='fc1')(x)
	x = Dropout(0.5)(x)
	x = Dense(128, activation='relu', name='fc2')(x)
	x = Dropout(0.5)(x)
	x = Dense(10, activation='softmax', name='predictions')(x)
	
	model = Model(img_input, x, nam