rrighart commited on
Commit
bf54b06
1 Parent(s): 99b1d03
Files changed (1) hide show
  1. README.md +21 -11
README.md CHANGED
@@ -1,4 +1,15 @@
1
 
 
 
 
 
 
 
 
 
 
 
 
2
  # Color tags
3
 
4
  ## An App classifying images on different colors
@@ -7,26 +18,25 @@ App: https://huggingface.co/spaces/rrighart/color-tags
7
 
8
  Color tags are very useful for finding pictures on the web, such as in e-commerce applications.
9
  This App provides color tags for uploaded image files.
10
- The underlying model was trained using a basic Convolutional Neural Network and an EfficientNet, with the latter giving slightly better results [[1]](https://www.kaggle.com/code/rrighart/the-prediction-of-color-tags/data) .
11
 
12
- For training and validation, the Vehicles Color Recognition (VCoR) dataset was used, which has 15 colors classes [[2]](https://www.kaggle.com/datasets/landrykezebou/vcor-vehicle-color-recognition-dataset). A separate unseen testset has overall accuracy of 84%.
13
- One goal of this project is to see if the model can generalizes to other kind of products and objects. For this purpose tested some images from the Fashion Product Images data [[3]](https://www.kaggle.com/datasets/paramaggarwal/fashion-product-images-small) which shows promising results.
14
 
15
  ## Contact
16
 
17
- Ruthger Righart (PhD)
18
-
19
- Data scientist in machine learning and computer vision
20
-
21
  Email: rrighart@googlemail.com
22
-
23
  Web: https://www.rrighart.com
24
 
25
  ## References
26
 
27
- 1. The prediction of color tags, Kaggle Notebook R. Righart.
28
- 2. Vehicle color recognition dataset (VCoR).
29
- 3. Fashion Product Images.
 
 
30
 
31
 
32
 
1
 
2
+
3
+ ---
4
+ title: color tags
5
+ colorFrom: gray
6
+ colorTo: purple
7
+ sdk: gradio
8
+ sdk_version: 3.1.4
9
+ app_file: app.py
10
+ pinned: false
11
+ ---
12
+
13
  # Color tags
14
 
15
  ## An App classifying images on different colors
18
 
19
  Color tags are very useful for finding pictures on the web, such as in e-commerce applications.
20
  This App provides color tags for uploaded image files.
21
+ The underlying model was trained using a basic Convolutional Neural Network and an EfficientNet, with the latter giving slightly better results [1](https://www.kaggle.com/code/rrighart/the-prediction-of-color-tags/data) .
22
 
23
+ For training and validation, the Vehicles Color Recognition (VCoR) dataset was used, which has 15 colors classes [2](https://www.kaggle.com/datasets/landrykezebou/vcor-vehicle-color-recognition-dataset). A separate unseen testset has overall accuracy of 84%
24
+ One goal of this project was to see if the model can generalizes to other kind of products and objects. For this purpose I have used Fashion Product Images [3](https://www.kaggle.com/datasets/paramaggarwal/fashion-product-images-small) and several test images show promising results.
25
 
26
  ## Contact
27
 
28
+ Ruthger Righart
29
+ Self-employed data scientist in machine learning and computer vision
 
 
30
  Email: rrighart@googlemail.com
 
31
  Web: https://www.rrighart.com
32
 
33
  ## References
34
 
35
+ 1. https://www.kaggle.com/code/rrighart/the-prediction-of-color-tags/data .
36
+
37
+ 2. https://www.kaggle.com/datasets/landrykezebou/vcor-vehicle-color-recognition-dataset
38
+
39
+ 3. https://www.kaggle.com/datasets/paramaggarwal/fashion-product-images-small
40
 
41
 
42