我正在使用tensorflow来构建卷积神经网络 . 给定形状的张量(无,16,16,4,192)我想执行转置卷积,导致形状(无,32,32,7,192) .
Would a filter size of [2,2,4,192,192] and stride of [2,2,1,1,1] produce the output shape that I want?
是的,你几乎是对的 .
一个小的修正是 tf.nn.conv3d_transpose 期望 NCDHW 或 NDHWC 输入格式(你的似乎是 NHWDC ),滤镜形状应该是 [depth, height, width, output_channels, in_channels] . 这会影响 filter 和 stride 中的维度顺序:
tf.nn.conv3d_transpose
NCDHW
NDHWC
NHWDC
[depth, height, width, output_channels, in_channels]
filter
stride
# Original format: NHWDC. original = tf.placeholder(dtype=tf.float32, shape=[None, 16, 16, 4, 192]) print original.shape # Convert to NDHWC format. input = tf.reshape(original, shape=[-1, 4, 16, 16, 192]) print input.shape # input shape: [batch, depth, height, width, in_channels]. # filter shape: [depth, height, width, output_channels, in_channels]. # output shape: [batch, depth, height, width, output_channels]. filter = tf.get_variable('filter', shape=[4, 2, 2, 192, 192], dtype=tf.float32) conv = tf.nn.conv3d_transpose(input, filter=filter, output_shape=[-1, 7, 32, 32, 192], strides=[1, 1, 2, 2, 1], padding='SAME') print conv.shape final = tf.reshape(conv, shape=[-1, 32, 32, 7, 192]) print final.shape
哪个输出:
(?, 16, 16, 4, 192) (?, 4, 16, 16, 192) (?, 7, 32, 32, 192) (?, 32, 32, 7, 192)
1 回答
是的,你几乎是对的 .
一个小的修正是
tf.nn.conv3d_transpose
期望NCDHW
或NDHWC
输入格式(你的似乎是NHWDC
),滤镜形状应该是[depth, height, width, output_channels, in_channels]
. 这会影响filter
和stride
中的维度顺序:哪个输出: