当前位置：网站首页>Application of UNET in battery segmentation project

Application of UNET in battery segmentation project

2022-07-18 06:52:00 【fegggye】

Unet Network structure source code （slim Realization ）： Output result is single channel , The activation function uses leakrelu

def lrelu(x):
    return tf.maximum(x * 0.2, x)
 
activation_fn=lrelu

def upsample_and_concat(x1, x2, output_channels, in_channels):
    pool_size = 2
    deconv_filter = tf.Variable(tf.truncated_normal([pool_size, pool_size, output_channels, in_channels], stddev=0.02))
    deconv = tf.nn.conv2d_transpose(x1, deconv_filter, tf.shape(x2), strides=[1, pool_size, pool_size, 1])
 
    deconv_output = tf.concat([deconv, x2], 3)
    deconv_output.set_shape([None, None, None, output_channels * 2])
    return deconv_output

 
def UNet(inputs, reg):  # Unet
    conv1 = slim.conv2d(inputs, 32, [3, 3], rate=1, activation_fn=activation_fn, scope='g_conv1_1', weights_regularizer=reg)
    conv1 = slim.conv2d(conv1, 32, [3, 3], rate=1, activation_fn=activation_fn, scope='g_conv1_2',weights_regular
原网站

版权声明
本文为[fegggye]所创，转载请带上原文链接，感谢
https://yzsam.com/2022/199/202207151636294516.html

边栏推荐

猜你喜欢

随机推荐