We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 068d5c1 commit ba7d19cCopy full SHA for ba7d19c
dl/layers/conv.md
@@ -24,8 +24,6 @@
24
25
当使用该层作为第一层时,应提供`input_shape`参数。例如`input_shape = (3,128,128)`代表128\*128的彩色RGB图像
26
27
-
28
29
## Conv2DTranspose层 {#conv2dtranspose}
30
31
---
@@ -34,8 +32,6 @@
34
32
35
33
36
37
38
39
## Conv3D层 {#conv3d}
40
41
@@ -44,3 +40,37 @@
44
45
46
42
43
+## Cropping1D层 {#cropping1d}
+
+---
47
+在时间轴(axis1)上对1D输入(即时间序列)进行裁剪
48
49
50
51
+## Cropping2D层 {#cropping2d}
52
53
54
55
+对2D输入(图像)进行裁剪,将在空域维度,即宽和高的方向上裁剪
56
57
58
59
+## Cropping3D层 {#cropping3d}
60
61
62
63
+对2D输入(图像)进行裁剪
64
65
66
67
+## UpSampling1D层 {#upsampling1d}
68
69
70
71
+在时间轴上,将每个时间步重复`length`次
72
73
74
75
76
0 commit comments