joonhaim commited on
Commit
88b9f23
·
verified ·
1 Parent(s): 1fa36d2

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -0
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: pytorch
4
+ tags:
5
+ - computer-vision
6
+ - image-classification
7
+ - efficientnet
8
+ - surgical-tools
9
+ - surgical-instruments
10
+ - binary-classification
11
+ datasets:
12
+ - joonhaim/hinged-state-classifier-crops
13
+ ---
14
+
15
+ # hinged-state-classifier-efficientnet-b0
16
+
17
+ EfficientNet-B0 image classification model for surgical instrument state recognition.
18
+
19
+ ## Task
20
+ Binary classification of hinged surgical instrument state:
21
+ - closed
22
+ - open
23
+
24
+ ## Model details
25
+ - Architecture: EfficientNet-B0
26
+ - Framework: PyTorch
27
+ - Checkpoint: `best.pt`
28
+ - Input image size: 224 × 224
29
+
30
+ ## Dataset
31
+ Trained on:
32
+ - `joonhaim/hinged-state-classifier-crops`
33
+
34
+ ## Notes
35
+ This is a custom PyTorch checkpoint for classifying the state of hinged surgical instruments from cropped images.
36
+
37
+ The class order must match the order used during training.