add model trained on low-resolution data (#1)
Browse files- add model trained on low-resolution data (7d51bc656ebcfd2ea548a12c351d9a00b9c64693)
- nn_architecture.txt +19 -0
- trained_model.pth +3 -0
- transformation +0 -0
nn_architecture.txt
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FullyCNN(
|
2 |
+
(0): Conv2d(2, 128, kernel_size=(5, 5), stride=(1, 1))
|
3 |
+
(1): ReLU()
|
4 |
+
(2): Conv2d(128, 64, kernel_size=(5, 5), stride=(1, 1))
|
5 |
+
(3): ReLU()
|
6 |
+
(4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1))
|
7 |
+
(5): ReLU()
|
8 |
+
(6): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
|
9 |
+
(7): ReLU()
|
10 |
+
(8): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
|
11 |
+
(9): ReLU()
|
12 |
+
(10): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
|
13 |
+
(11): ReLU()
|
14 |
+
(12): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1))
|
15 |
+
(13): ReLU()
|
16 |
+
(14): Conv2d(32, 4, kernel_size=(3, 3), stride=(1, 1))
|
17 |
+
(final_transformation): SoftPlusTransform(Parameter containing:
|
18 |
+
tensor(0.1000, requires_grad=True))
|
19 |
+
)
|
trained_model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3c8f9bda445fc500382294a56e481d1300cfc57a912cb4006b5e31ab81bd957
|
3 |
+
size 1077412
|
transformation
ADDED
Binary file (916 Bytes). View file
|
|