vumichien commited on
Commit
53215c8
1 Parent(s): e3ce03d

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -0
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - image-segmentation
4
+ library_name: keras
5
+ ---
6
+ ## Model description
7
+ Full credits go to: [Vu Minh Chien](https://www.linkedin.com/in/vumichien/)
8
+
9
+ With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in photography, security, medical imaging, and remote sensing. The MIRNet model for low-light image enhancement, a fully-convolutional architecture that learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details
10
+ ## Dataset
11
+ The [LoL Dataset](https://drive.google.com/uc?id=1DdGIJ4PZPlF2ikl8mNM9V-PdVxVLbQi6) has been created for low-light image enhancement. It provides 485 images for training and 15 for testing. Each image pair in the dataset consists of a low-light input image and its corresponding well-exposed reference image.
12
+ ## Training procedure
13
+
14
+ ### Training hyperparameters
15
+ **Model architecture**:
16
+ - UNet with a pretrained DenseNet 201 backbone.
17
+
18
+ The following hyperparameters were used during training:
19
+ - learning_rate: 1e-04
20
+ - train_batch_size: 8
21
+ - seed: 42
22
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
23
+ - lr_scheduler_type: ReduceLROnPlateau
24
+ - num_epochs: 50
25
+
26
+ ### Training results
27
+
28
+ - The results are shown in TensorBoard.
29
+
30
+
31
+ ### View Model Demo
32
+
33
+ ![Model Demo](./demo.png)
34
+
35
+
36
+ <details>
37
+
38
+ <summary> View Model Plot </summary>
39
+
40
+ ![Model Image](./model.png)
41
+
42
+ </details>