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
4113e15
·
verified ·
1 Parent(s): f23e124

End of training

Browse files
Files changed (5) hide show
  1. README.md +21 -23
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Aug20_12-16-36_2e55902cfd04/events.out.tfevents.1724156211.2e55902cfd04.1458.1 +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: 0.9038
21
- - Mean Iou: 0.4486
22
- - Mean Accuracy: 0.8693
23
- - Overall Accuracy: 0.8708
24
- - Accuracy Bkg: 0.8709
25
- - Accuracy Gun: 0.8680
26
- - Accuracy Knife: 0.8689
27
- - Iou Bkg: 0.8700
28
- - Iou Gun: 0.1670
29
- - Iou Knife: 0.3088
30
 
31
  ## Model description
32
 
@@ -46,24 +46,22 @@ More information needed
46
 
47
  The following hyperparameters were used during training:
48
  - learning_rate: 1e-05
49
- - train_batch_size: 5
50
- - eval_batch_size: 5
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - num_epochs: 10
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bkg | Accuracy Gun | Accuracy Knife | Iou Bkg | Iou Gun | Iou Knife |
59
- |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:------------:|:--------------:|:-------:|:-------:|:---------:|
60
- | 1.0919 | 1.4286 | 20 | 1.1033 | 0.1925 | 0.6509 | 0.3960 | 0.3783 | 0.8281 | 0.7462 | 0.3783 | 0.0314 | 0.1677 |
61
- | 1.0576 | 2.8571 | 40 | 1.0473 | 0.3242 | 0.7738 | 0.6681 | 0.6608 | 0.8826 | 0.7781 | 0.6607 | 0.0600 | 0.2518 |
62
- | 0.9844 | 4.2857 | 60 | 0.9913 | 0.3823 | 0.8265 | 0.7783 | 0.7750 | 0.8873 | 0.8171 | 0.7748 | 0.0928 | 0.2793 |
63
- | 0.9604 | 5.7143 | 80 | 0.9385 | 0.4206 | 0.8552 | 0.8396 | 0.8386 | 0.8813 | 0.8457 | 0.8381 | 0.1334 | 0.2902 |
64
- | 0.9418 | 7.1429 | 100 | 0.9073 | 0.4389 | 0.8651 | 0.8592 | 0.8588 | 0.8795 | 0.8570 | 0.8581 | 0.1520 | 0.3065 |
65
- | 0.9029 | 8.5714 | 120 | 0.8989 | 0.4474 | 0.8672 | 0.8683 | 0.8684 | 0.8712 | 0.8620 | 0.8677 | 0.1621 | 0.3123 |
66
- | 0.9277 | 10.0 | 140 | 0.9038 | 0.4486 | 0.8693 | 0.8708 | 0.8709 | 0.8680 | 0.8689 | 0.8700 | 0.1670 | 0.3088 |
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: 0.7107
21
+ - Mean Iou: 0.5477
22
+ - Mean Accuracy: 0.8550
23
+ - Overall Accuracy: 0.9383
24
+ - Accuracy Bkg: 0.9441
25
+ - Accuracy Gun: 0.8115
26
+ - Accuracy Knife: 0.8096
27
+ - Iou Bkg: 0.9395
28
+ - Iou Gun: 0.3214
29
+ - Iou Knife: 0.3821
30
 
31
  ## Model description
32
 
 
46
 
47
  The following hyperparameters were used during training:
48
  - learning_rate: 1e-05
49
+ - train_batch_size: 15
50
+ - eval_batch_size: 15
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
+ - num_epochs: 20
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bkg | Accuracy Gun | Accuracy Knife | Iou Bkg | Iou Gun | Iou Knife |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:------------:|:--------------:|:-------:|:-------:|:---------:|
60
+ | 0.8463 | 4.0 | 20 | 0.8083 | 0.4986 | 0.8748 | 0.9099 | 0.9123 | 0.8562 | 0.8560 | 0.9104 | 0.2327 | 0.3527 |
61
+ | 0.8068 | 8.0 | 40 | 0.7739 | 0.5197 | 0.8694 | 0.9233 | 0.9271 | 0.8402 | 0.8408 | 0.9242 | 0.2679 | 0.3670 |
62
+ | 0.7778 | 12.0 | 60 | 0.7326 | 0.5392 | 0.8611 | 0.9338 | 0.9389 | 0.8269 | 0.8176 | 0.9350 | 0.3017 | 0.3808 |
63
+ | 0.7455 | 16.0 | 80 | 0.7202 | 0.5446 | 0.8562 | 0.9369 | 0.9425 | 0.8126 | 0.8136 | 0.9381 | 0.3161 | 0.3794 |
64
+ | 0.7288 | 20.0 | 100 | 0.7107 | 0.5477 | 0.8550 | 0.9383 | 0.9441 | 0.8115 | 0.8096 | 0.9395 | 0.3214 | 0.3821 |
 
 
65
 
66
 
67
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "nvidia/mit-b0",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
 
1
  {
2
+ "_name_or_path": "saad7489/segformer-b0-finetuned-segments-SixrayKnife8-19-2024",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:385cd40593dab1216904e289f0b9dd94795bd421c3fce05ffd9afbe393c39418
3
  size 14885804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34ea7bb85838db9d5b852d0ac18e6c6f4dc94be9d883052d33ca6a80ae74f8f
3
  size 14885804
runs/Aug20_12-16-36_2e55902cfd04/events.out.tfevents.1724156211.2e55902cfd04.1458.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40748f63018283135d1edcf9ebdc75deb153c1be543d437987d0249b53ff7c5
3
+ size 30308
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0e2a8e95a5ac2b0606a8b56d365c709a44e997e5f48eb87987b83d51545d0f6
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d284516f9b43e46dabdff84a609d58c423b0f2f22b96dda0fd6a3c9cc7c68f
3
  size 5240