我正在使用 tensorflow 构建卷积神经网络。给定形状 (none, 16, 16, 4, 192) 的张量,我想执行转置卷积,得到形状 (none, 32, 32, 7, 192)。
过滤器大小为 [2,2,4,192,192] 和步长为 [2,2,1,1,1] 会产生我想要的输出形状吗?
最佳答案
是的,你几乎是对的。
一个小的更正是 tf.nn.conv3d_transpose
需要 NCDHW
或 NDHWC
输入格式(您的似乎是 NHWDC
),滤波器形状预计为[深度、高度、宽度、output_channels、in_channels]
。这会影响 filter
和 stride
中的维度顺序:
# 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
哪些输出:
(?, 16, 16, 4, 192)
(?, 4, 16, 16, 192)
(?, 7, 32, 32, 192)
(?, 32, 32, 7, 192)
关于python - 转置卷积(反卷积)算法,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/46735034/