我正在尝试使用2实现多类语义分割模型 类(人,车)。这是我对unet体系结构的修改实现。我的输出通道数为3(3类-人,汽车,背景)。如何获得像素明智的分类? 这是我的地面真理面具的两个例子。
我正在为每个对象类使用1个通道。
def conv_block(tensor, nfilters, size=3, padding='same', initializer="he_normal"):
x = Conv2D(filters=nfilters, kernel_size=(size, size), padding=padding, kernel_initializer=initializer)(tensor)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(filters=nfilters, kernel_size=(size, size), padding=padding, kernel_initializer=initializer)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
return x
def deconv_block(tensor, residual, nfilters, size=3, padding='same', strides=(2, 2)):
y = Conv2DTranspose(nfilters, kernel_size=(size, size), strides=strides, padding=padding)(tensor)
y = concatenate([y, residual], axis=3)
y = conv_block(y, nfilters)
return y
def Unet(img_height, img_width, nclasses=3, filters=64):
input_layer = Input(shape=(img_height, img_width, 3), name='image_input')
conv1 = conv_block(input_layer, nfilters=filters)
conv1_out = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = conv_block(conv1_out, nfilters=filters*2)
conv2_out = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = conv_block(conv2_out, nfilters=filters*4)
conv3_out = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = conv_block(conv3_out, nfilters=filters*8)
conv4_out = MaxPooling2D(pool_size=(2, 2))(conv4)
conv4_out = Dropout(0.5)(conv4_out)
conv5 = conv_block(conv4_out, nfilters=filters*16)
conv5 = Dropout(0.5)(conv5)
deconv6 = deconv_block(conv5, residual=conv4, nfilters=filters*8)
deconv6 = Dropout(0.5)(deconv6)
deconv7 = deconv_block(deconv6, residual=conv3, nfilters=filters*4)
deconv7 = Dropout(0.5)(deconv7)
deconv8 = deconv_block(deconv7, residual=conv2, nfilters=filters*2)
deconv9 = deconv_block(deconv8, residual=conv1, nfilters=filters)
output_layer = Conv2D(filters=nclasses, kernel_size=(1, 1))(deconv9)
output_layer = BatchNormalization()(output_layer)
output_layer = Reshape((img_height*img_width, nclasses), input_shape=(img_height, img_width, nclasses))(output_layer)
output_layer = Activation('softmax')(output_layer)
model = Model(inputs=input_layer, outputs=output_layer, name='Unet')
return model
答案 0 :(得分:1)
您快完成了,现在使用以下方法反向传播网络错误:
loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=output_layer, labels=labels))
tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)
您不必将基本事实转换为一次性格式,sparse_softmax会为您加点。