1na37 commited on
Commit
cddc6a8
·
verified ·
1 Parent(s): b2744f8

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +58 -0
  2. config.json +18 -0
  3. pytorch_model.pth +3 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: id
3
+ tags:
4
+ - image-classification
5
+ - resnet18
6
+ - pytorch
7
+ - computer-vision
8
+ license: mit
9
+ datasets:
10
+ - sumn2u/garbage-classification-v2
11
+ metrics:
12
+ - accuracy
13
+ ---
14
+
15
+ # Garbage Classification
16
+
17
+ Model ini adalah versi **ResNet18** yang di-fine-tune menggunakan dataset **Garbage Classification v2** dari Kaggle. Model ini mencapai hasil berikut pada dataset evaluasi (25% split):
18
+
19
+ - **Loss:** 0.0020
20
+ - **Accuracy:** 0.9364
21
+
22
+ ## Model description
23
+ Model klasifikasi gambar untuk membedakan jenis-jenis sampah guna mendukung sistem pemilahan otomatis. Menggunakan arsitektur ResNet18 dengan teknik Transfer Learning.
24
+
25
+ ## Intended uses & limitations
26
+ Digunakan untuk mengidentifikasi material tunggal dalam gambar. Limitasi mencakup kesulitan pada latar belakang yang ramai atau objek yang bertumpuk.
27
+
28
+ ## Training and evaluation data
29
+ Dataset menggunakan 12,260 gambar yang dibagi menjadi 75% Training (9,195 gambar) dan 25% Testing (3,065 gambar).
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+ The following hyperparameters were used during training:
35
+ - **learning_rate:** 0.0001
36
+ - **train_batch_size:** 32
37
+ - **eval_batch_size:** 32
38
+ - **optimizer:** Adam with weight_decay=1e-4
39
+ - **lr_scheduler_type:** StepLR (step=5, gamma=0.5)
40
+ - **num_epochs:** 15
41
+
42
+ ### Training results
43
+ | Epoch | Training Loss | Train Accuracy |
44
+ |-------|---------------|----------------|
45
+ | 1 | 0.5585 | 82.53% |
46
+ | 3 | 0.0790 | 97.77% |
47
+ | 6 | 0.0121 | 99.85% |
48
+ | 9 | 0.0043 | 99.98% |
49
+ | 12 | 0.0029 | 99.99% |
50
+ | 15 | 0.0020 | 100.00% |
51
+
52
+ ## Framework versions
53
+ - **Pytorch:** 2.10.0+cu128
54
+ - **Torchvision:** 0.25.0+cu128
55
+ - **Python:** 3.12.12
56
+
57
+ ## Author
58
+ **Ina Alyani**
config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "resnet18",
3
+ "num_classes": 10,
4
+ "class_names": [
5
+ "battery",
6
+ "biological",
7
+ "cardboard",
8
+ "clothes",
9
+ "glass",
10
+ "metal",
11
+ "paper",
12
+ "plastic",
13
+ "shoes",
14
+ "trash"
15
+ ],
16
+ "task": "image-classification",
17
+ "dataset": "Garbage Classification v2 (Kaggle)"
18
+ }
pytorch_model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765111768eda435650b42fbaf0d62ae5f0efeaca0e90329e5a3b7cd2b16b188b
3
+ size 44806987