K00B404 commited on
Commit
0273cf7
1 Parent(s): 7e91180

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -34
README.md CHANGED
@@ -1,40 +1,8 @@
1
- ---
2
- tags:
3
- - unet
4
- - pix2pix
5
- - pytorch
6
- library_name: pytorch
7
- license: wtfpl
8
- datasets:
9
- - K00B404/pix2pix_flux_set
10
- language:
11
- - en
12
- pipeline_tag: image-to-image
13
- ---
14
-
15
  # Pix2Pix UNet Model
16
 
17
- ## Model Description
18
- Custom UNet model for Pix2Pix image translation.
19
  - **Image Size:** 256
20
  - **Model Type:** small_UNet (256)
21
-
22
- ## Usage
23
-
24
- ```python
25
- import torch
26
- from small_256_model import UNet as small_UNet
27
- from big_1024_model import UNet as big_UNet
28
- big = True
29
- # Load the model
30
- name='big_model_weights.pth' if big else 'small_model_weights.pth'
31
- checkpoint = torch.load(name)
32
- model = big_UNet() if checkpoint['model_config']['big'] else small_UNet()
33
- model.load_state_dict(checkpoint['model_state_dict'])
34
- model.eval()
35
-
36
- Model Architecture
37
-
38
  UNet(
39
  (encoder): Sequential(
40
  (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
@@ -52,4 +20,4 @@ UNet(
52
  (4): ConvTranspose2d(64, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
53
  (5): Tanh()
54
  )
55
- )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # Pix2Pix UNet Model
2
 
 
 
3
  - **Image Size:** 256
4
  - **Model Type:** small_UNet (256)
5
+ ## Model Architecture
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  UNet(
7
  (encoder): Sequential(
8
  (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
 
20
  (4): ConvTranspose2d(64, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
21
  (5): Tanh()
22
  )
23
+ )