zarqankhn commited on
Commit
f978d83
·
verified ·
1 Parent(s): 557735b

Add YAML metadata front matter to model card

Browse files
Files changed (1) hide show
  1. README.md +44 -0
README.md CHANGED
@@ -1,3 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # QuickDraw 345 Doodle Classifier — TFLite
2
 
3
  A doodle recognition model trained on all **345 categories** from Google's [Quick Draw Dataset](https://quickdraw.withgoogle.com/data), exported as TFLite for **Flutter on-device offline inference**.
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - image-classification
7
+ - tflite
8
+ - flutter
9
+ - quickdraw
10
+ - doodle-recognition
11
+ - on-device-inference
12
+ - se-resnet
13
+ datasets:
14
+ - google/quickdraw
15
+ metrics:
16
+ - accuracy
17
+ library_name: tflite
18
+ pipeline_tag: image-classification
19
+ model-index:
20
+ - name: quickdraw-345-se-resnet
21
+ results:
22
+ - task:
23
+ type: image-classification
24
+ name: Image Classification
25
+ dataset:
26
+ name: Google Quick Draw
27
+ type: google/quickdraw
28
+ metrics:
29
+ - type: accuracy
30
+ value: 0.7619
31
+ name: Top-1 Accuracy
32
+ - type: accuracy
33
+ value: 0.8951
34
+ name: Top-3 Accuracy
35
+ - type: accuracy
36
+ value: 0.9226
37
+ name: Top-5 Accuracy
38
+ - type: accuracy
39
+ value: 0.9455
40
+ name: Top-10 Accuracy
41
+ - type: accuracy
42
+ value: 0.7640
43
+ name: TFLite Float16 Accuracy
44
+ ---
45
  # QuickDraw 345 Doodle Classifier — TFLite
46
 
47
  A doodle recognition model trained on all **345 categories** from Google's [Quick Draw Dataset](https://quickdraw.withgoogle.com/data), exported as TFLite for **Flutter on-device offline inference**.