pyesonekyaw commited on
Commit
3b4db59
1 Parent(s): 1289a84

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -22
README.md CHANGED
@@ -1,32 +1,34 @@
1
  ---
2
  tags:
3
  - fastai
 
 
 
4
  ---
5
 
6
- # Amazing!
 
7
 
8
- 🥳 Congratulations on hosting your fastai model on the Hugging Face Hub!
9
 
10
- # Some next steps
11
- 1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))!
12
 
13
- 2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)).
 
 
 
 
 
 
14
 
15
- 3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)!
 
 
16
 
17
- Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card.
18
-
19
-
20
- ---
21
-
22
-
23
- # Model card
24
-
25
- ## Model description
26
- More information needed
27
-
28
- ## Intended uses & limitations
29
- More information needed
30
-
31
- ## Training and evaluation data
32
- More information needed
 
1
  ---
2
  tags:
3
  - fastai
4
+ library_name: fastai
5
+ pipeline_tag: image-classification
6
+ license: openrail
7
  ---
8
 
9
+ # RecycleTree - Others Classification Model
10
+ ![Banner](https://huggingface.co/pyesonekyaw/recycletree_plastic/resolve/main/banner.png)
11
 
12
+ RecycleTree is a project from CZ3002 Advanced Software Engineering in Nanyang Technological University. It aims to enable users to have a more informed recycling experience, from finding the nearest recycling bins, to checking whether the item they wish to recycle can indeed be recycled, to learning more about recycling and contamination in general.
13
 
14
+ The whole project can be found on [GitHub](https://github.com/py-sk/RecycleTree)
 
15
 
16
+ This image classification model in particular is to classify plastic trash items into the following classes:
17
+ * Battery
18
+ * Electronic Waste
19
+ * Stationery
20
+
21
+ ## Training Data
22
+ The training dataset had 11453 images across 3 classes, with each class having roughly the same distribution of images. The images were either scraped from Google image search, or obtained by ourselves in real life.
23
 
24
+ ## Training Procedure
25
+ As the purpose of this model was to act just as a proof of concept for quick prototyping of RecycleTree, I opted to use the fast.ai library and a simple model architecture of ResNet34.
26
+ The training procedure is following the recommendations from [fast.ai](https://docs.fast.ai/)
27
 
28
+ ## Other Models
29
+ There are also other models in the RecycleTree model series:
30
+ * [Materials Classification Model](https://huggingface.co/pyesonekyaw/recycletree_materials) - Classification of images of trash into different materials
31
+ * [Paper Classification Model](https://huggingface.co/pyesonekyaw/recycletree_paper) - Classification of images of paper trash into different classes
32
+ * [Metal Classification Model](https://huggingface.co/pyesonekyaw/recycletree_metal) - Classification of images of metal trash into different classes
33
+ * [Glass Classification Model](https://huggingface.co/pyesonekyaw/recycletree_glass) - Classification of images of glass trash into different classes
34
+ * [Plastic Classification Model](https://huggingface.co/pyesonekyaw/recycletree_plastic) - Classification of images of plastic trash into different classes