Hugging Face's logo

eleninaneversmiles
/
segformer-b0-finetuned-segments-sidewalk-2

Image Segmentation
Transformers
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
eleninaneversmiles commited on
Commit
3ebdad6
·
verified ·
1 Parent(s): 19a5214

End of training

Browse files
Files changed (3) hide show
  1. README.md +30 -22
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  license: other
 
3
  tags:
4
  - vision
5
  - image-segmentation
6
  - generated_from_trainer
7
- base_model: nvidia/mit-b0
8
  model-index:
9
  - name: segformer-b0-finetuned-segments-sidewalk-2
10
  results: []
@@ -17,12 +17,7 @@ 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 eleninaneversmiles/wheels dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.7657
21
- - Mean Iou: 1.0
22
- - Mean Accuracy: 1.0
23
- - Overall Accuracy: 1.0
24
- - Accuracy 1: nan
25
- - Iou 1: nan
26
 
27
  ## Model description
28
 
@@ -47,24 +42,37 @@ The following hyperparameters were used during training:
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 50
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy 1 | Iou 1 |
55
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:----------:|:-----:|
56
- | 3.1438 | 4.0 | 20 | 3.5905 | 0.4999 | 0.9998 | 0.9998 | nan | nan |
57
- | 2.7237 | 8.0 | 40 | 3.0580 | 1.0 | 1.0 | 1.0 | nan | nan |
58
- | 2.5161 | 12.0 | 60 | 2.7052 | 1.0 | 1.0 | 1.0 | nan | nan |
59
- | 2.2549 | 16.0 | 80 | 2.5135 | 1.0 | 1.0 | 1.0 | nan | nan |
60
- | 2.2175 | 20.0 | 100 | 2.3205 | 1.0 | 1.0 | 1.0 | nan | nan |
61
- | 1.848 | 24.0 | 120 | 2.1632 | 1.0 | 1.0 | 1.0 | nan | nan |
62
- | 1.747 | 28.0 | 140 | 1.9624 | 1.0 | 1.0 | 1.0 | nan | nan |
63
- | 1.7869 | 32.0 | 160 | 1.8811 | 1.0 | 1.0 | 1.0 | nan | nan |
64
- | 1.6521 | 36.0 | 180 | 1.8269 | 1.0 | 1.0 | 1.0 | nan | nan |
65
- | 1.5971 | 40.0 | 200 | 1.7873 | 1.0 | 1.0 | 1.0 | nan | nan |
66
- | 1.5828 | 44.0 | 220 | 1.7885 | 1.0 | 1.0 | 1.0 | nan | nan |
67
- | 1.5443 | 48.0 | 240 | 1.7657 | 1.0 | 1.0 | 1.0 | nan | nan |
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
 
1
  ---
2
  license: other
3
+ base_model: nvidia/mit-b0
4
  tags:
5
  - vision
6
  - image-segmentation
7
  - generated_from_trainer
 
8
  model-index:
9
  - name: segformer-b0-finetuned-segments-sidewalk-2
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the eleninaneversmiles/wheels dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4143
 
 
 
 
 
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 100
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.2256 | 4.0 | 20 | 2.3584 |
52
+ | 2.1286 | 8.0 | 40 | 1.9811 |
53
+ | 1.7382 | 12.0 | 60 | 1.8292 |
54
+ | 1.5859 | 16.0 | 80 | 1.7057 |
55
+ | 1.3773 | 20.0 | 100 | 1.4923 |
56
+ | 1.2484 | 24.0 | 120 | 1.3850 |
57
+ | 1.1516 | 28.0 | 140 | 1.3239 |
58
+ | 1.2039 | 32.0 | 160 | 1.1738 |
59
+ | 0.9099 | 36.0 | 180 | 0.9805 |
60
+ | 0.8456 | 40.0 | 200 | 0.9142 |
61
+ | 0.7384 | 44.0 | 220 | 0.8445 |
62
+ | 0.67 | 48.0 | 240 | 0.7545 |
63
+ | 0.6088 | 52.0 | 260 | 0.6968 |
64
+ | 0.5561 | 56.0 | 280 | 0.6064 |
65
+ | 0.6686 | 60.0 | 300 | 0.5775 |
66
+ | 0.4748 | 64.0 | 320 | 0.5647 |
67
+ | 0.4435 | 68.0 | 340 | 0.5248 |
68
+ | 0.415 | 72.0 | 360 | 0.4950 |
69
+ | 0.3937 | 76.0 | 380 | 0.4786 |
70
+ | 0.3665 | 80.0 | 400 | 0.4568 |
71
+ | 0.3561 | 84.0 | 420 | 0.4325 |
72
+ | 0.3256 | 88.0 | 440 | 0.4257 |
73
+ | 0.336 | 92.0 | 460 | 0.4163 |
74
+ | 0.4353 | 96.0 | 480 | 0.4241 |
75
+ | 0.4326 | 100.0 | 500 | 0.4143 |
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4fbfaa2bf8f0a8dab5ab8c8e05c895fa927586b03b3210ac1aed3dbbca92393
3
  size 14931044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de73af9eb45c7ce3582609ccaa19d5e43a8d45053cdaddc402230a3f7b5d2136
3
  size 14931044
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3100b0eb30a0afc8bbbeee219450a8cbabc7d5da2df9696e243e39c3af29fd62
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33b77ebc271e412632ff2f34c985c5ca6c117a495fa3417caf09db2727c13838
3
  size 5176