Hugging Face's logo

saad7489
/
segformer-b0-finetuned-segments-SixrayKnife8-19-2024

Image Segmentation
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Model card Files Metrics Community
saad7489 commited on
Commit
0d15554
·
verified ·
1 Parent(s): 4e94472

End of training

Browse files
Files changed (5) hide show
  1. README.md +20 -20
  2. config.json +7 -7
  3. model.safetensors +1 -1
  4. runs/Aug20_10-45-58_d98ed18656c3/events.out.tfevents.1724150776.d98ed18656c3.1590.5 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- base_model: nvidia/mit-b0
3
  license: other
 
4
  tags:
5
  - vision
6
  - image-segmentation
@@ -17,16 +17,16 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the saad7489/SixraygunTest dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5986
21
- - Mean Iou: 0.5110
22
- - Mean Accuracy: 0.8118
23
- - Overall Accuracy: 0.8081
24
- - Accuracy Object1: nan
25
- - Accuracy Object2: 0.7529
26
- - Accuracy Object3: 0.8707
27
- - Iou Object1: 0.0
28
- - Iou Object2: 0.7267
29
- - Iou Object3: 0.8065
30
 
31
  ## Model description
32
 
@@ -55,15 +55,15 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Object1 | Accuracy Object2 | Accuracy Object3 | Iou Object1 | Iou Object2 | Iou Object3 |
59
- |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:----------------:|:----------------:|:----------------:|:-----------:|:-----------:|:-----------:|
60
- | 0.7244 | 1.4286 | 20 | 0.6924 | 0.4978 | 0.8311 | 0.8263 | nan | 0.7536 | 0.9087 | 0.0 | 0.7153 | 0.7782 |
61
- | 0.7251 | 2.8571 | 40 | 0.6470 | 0.5105 | 0.8256 | 0.8213 | nan | 0.7572 | 0.8940 | 0.0 | 0.7246 | 0.8069 |
62
- | 0.6558 | 4.2857 | 60 | 0.6246 | 0.5148 | 0.8243 | 0.8210 | nan | 0.7714 | 0.8772 | 0.0 | 0.7350 | 0.8095 |
63
- | 0.6463 | 5.7143 | 80 | 0.5954 | 0.5100 | 0.8126 | 0.8098 | nan | 0.7680 | 0.8572 | 0.0 | 0.7295 | 0.8004 |
64
- | 0.63 | 7.1429 | 100 | 0.5892 | 0.5082 | 0.8073 | 0.8043 | nan | 0.7582 | 0.8564 | 0.0 | 0.7254 | 0.7991 |
65
- | 0.5935 | 8.5714 | 120 | 0.5923 | 0.5134 | 0.8155 | 0.8127 | nan | 0.7694 | 0.8616 | 0.0 | 0.7369 | 0.8031 |
66
- | 0.6137 | 10.0 | 140 | 0.5986 | 0.5110 | 0.8118 | 0.8081 | nan | 0.7529 | 0.8707 | 0.0 | 0.7267 | 0.8065 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
 
2
  license: other
3
+ base_model: nvidia/mit-b0
4
  tags:
5
  - vision
6
  - image-segmentation
 
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the saad7489/SixraygunTest dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6355
21
+ - Mean Iou: 0.5008
22
+ - Mean Accuracy: 0.7954
23
+ - Overall Accuracy: 0.7906
24
+ - Accuracy Bkg: nan
25
+ - Accuracy Knife: 0.7186
26
+ - Accuracy Gun: 0.8722
27
+ - Iou Bkg: 0.0
28
+ - Iou Knife: 0.6915
29
+ - Iou Gun: 0.8110
30
 
31
  ## Model description
32
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bkg | Accuracy Knife | Accuracy Gun | Iou Bkg | Iou Knife | Iou Gun |
59
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:--------------:|:------------:|:-------:|:---------:|:-------:|
60
+ | 0.7945 | 1.4286 | 20 | 0.7932 | 0.5023 | 0.8446 | 0.8389 | nan | 0.7531 | 0.9361 | 0.0 | 0.7186 | 0.7883 |
61
+ | 0.7385 | 2.8571 | 40 | 0.7324 | 0.5150 | 0.8445 | 0.8404 | nan | 0.7787 | 0.9103 | 0.0 | 0.7375 | 0.8074 |
62
+ | 0.7139 | 4.2857 | 60 | 0.7152 | 0.5033 | 0.8256 | 0.8200 | nan | 0.7358 | 0.9155 | 0.0 | 0.7072 | 0.8027 |
63
+ | 0.7405 | 5.7143 | 80 | 0.6747 | 0.4953 | 0.7972 | 0.7917 | nan | 0.7078 | 0.8866 | 0.0 | 0.6785 | 0.8075 |
64
+ | 0.6666 | 7.1429 | 100 | 0.6442 | 0.4937 | 0.7919 | 0.7860 | nan | 0.6964 | 0.8874 | 0.0 | 0.6723 | 0.8089 |
65
+ | 0.6357 | 8.5714 | 120 | 0.6210 | 0.4957 | 0.7874 | 0.7823 | nan | 0.7059 | 0.8688 | 0.0 | 0.6794 | 0.8076 |
66
+ | 0.6548 | 10.0 | 140 | 0.6355 | 0.5008 | 0.7954 | 0.7906 | nan | 0.7186 | 0.8722 | 0.0 | 0.6915 | 0.8110 |
67
 
68
 
69
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "saad7489/segformer-b0-finetuned-segments-SixrayKnife8-19-2024",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
@@ -28,16 +28,16 @@
28
  256
29
  ],
30
  "id2label": {
31
- "0": "object1",
32
- "1": "object2",
33
- "2": "object3"
34
  },
35
  "image_size": 224,
36
  "initializer_range": 0.02,
37
  "label2id": {
38
- "object1": 0,
39
- "object2": 1,
40
- "object3": 2
41
  },
42
  "layer_norm_eps": 1e-06,
43
  "mlp_ratios": [
 
1
  {
2
+ "_name_or_path": "nvidia/mit-b0",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
 
28
  256
29
  ],
30
  "id2label": {
31
+ "0": "bkg",
32
+ "1": "knife",
33
+ "2": "gun"
34
  },
35
  "image_size": 224,
36
  "initializer_range": 0.02,
37
  "label2id": {
38
+ "bkg": 0,
39
+ "gun": 2,
40
+ "knife": 1
41
  },
42
  "layer_norm_eps": 1e-06,
43
  "mlp_ratios": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc1c0ab0356c5db2a4702b961ffcff17a830e114be7a268698492e0de171cd0
3
  size 14885804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c9582e9f2691b11a591d0c1a78668cb414c0ab1209360c4f6df3043c67379f2
3
  size 14885804
runs/Aug20_10-45-58_d98ed18656c3/events.out.tfevents.1724150776.d98ed18656c3.1590.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fba945fb67023dae9ac3eca15f902013b9661786e81cd60dac16757cc5b89e
3
+ size 56709
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e1e7c3955d224ed1c9a7a0d31ce635711642d8bef84fdbfc5679e2d549991b
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7605a4b90149c2731772fe85546a605819b7232bccd3e35e5780e17a5a0edd8d
3
  size 5240