[英]tensorflow compute tf.nn.conv2d
我已經在 Excel 中手動計算了 3x3 圖像和兩個 2x2 過濾器之間的卷積:
我想使用 tensorflow tf.nn.conv2d:
重現相同的結果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()
但是我從 tensorflow 得到的輸出是關閉的:
數組([[[[35.,33.],[37.,25.]],[[35.,25.],[19.,15.]]]], dtype=float32)
我做錯了什么?
要獲得與 excel 示例相同的結果,您需要進行以下更改:
代碼示例:
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())
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.