我在 Excel 中手动计算了 3x3 图像和两个 2x2 滤波器之间的卷积:
我想使用tensorflow重现相同的结果tf.nn.conv2d:
x_raw = np.array([
[2,5,3],
[3,4,2],
[4,1,1]
])
f_raw = np.array(
[[
[2,1],
[3,4]
],[
[4,1],
[1,2]
]])
f = tf.constant(f_raw, dtype=tf.float32)
x = tf.constant(x_raw, dtype=tf.float32)
filter = tf.reshape(f, [2, 2, 1, 2])
image = tf.reshape(x, [1, 3, 3, 1])
tf.nn.conv2d(image, filter, [1, 1, 1, 1], "VALID").eval()
但是我从 tensorflow 得到的输出是关闭的:
array([[[[35.,33.],[37.,25.]],[[35.,25.],[19.,15.]]]], dtype=float32)
我做错了什么?
最佳答案
要获得与 Excel 示例中相同的结果,您需要进行以下更改:
- 创建两个单独的权重
- 分别计算每个权重的卷积
代码示例:
x_raw = np.array([
[2,5,3],
[3,4,2],
[4,1,1]
])
#created two seperate weights
weight1 = np.array(
[[
[2,1],
[3,4]
]])
weight2 = np.array(
[[
[4,1],
[1,2]
]]
)
weight1 = tf.constant(weight1, dtype=tf.float32)
weight2 = tf.constant(weight2, dtype=tf.float32)
x = tf.constant(x_raw, dtype=tf.float32)
#change out_channels to 1
filter1 = tf.reshape(weight1, [2, 2, 1, 1])
filter2 = tf.reshape(weight2, [2, 2, 1, 1])
image = tf.reshape(x, [1, 3, 3, 1])
with tf.Session() as sess:
print(tf.nn.conv2d(image, filter1, [1, 1, 1, 1], "VALID").eval())
print(tf.nn.conv2d(image, filter2, [1, 1, 1, 1], "VALID").eval())
关于python - tensorflow 计算 tf.nn.conv2d,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/52923062/