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
4b2ca68
·
verified ·
1 Parent(s): 9858b75

End of training

Browse files
Files changed (4) hide show
  1. README.md +19 -15
  2. model.safetensors +1 -1
  3. runs/Aug20_07-35-52_bdedd370450b/events.out.tfevents.1724139383.bdedd370450b.897.3 +3 -0
  4. 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: 0.4835
21
- - Mean Iou: 0.4419
22
- - Mean Accuracy: 0.6869
23
- - Overall Accuracy: 0.6897
24
  - Accuracy No-label: nan
25
- - Accuracy Object1: 0.6189
26
- - Accuracy Object2: 0.7549
27
  - Iou No-label: 0.0
28
- - Iou Object1: 0.6011
29
- - Iou Object2: 0.7247
30
 
31
  ## Model description
32
 
@@ -45,9 +45,9 @@ More information needed
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
- - learning_rate: 6e-05
49
- - train_batch_size: 10
50
- - eval_batch_size: 10
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
@@ -57,9 +57,13 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy No-label | Accuracy Object1 | Accuracy Object2 | Iou No-label | Iou Object1 | Iou Object2 |
59
  |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------------:|:----------------:|:----------------:|:------------:|:-----------:|:-----------:|
60
- | 0.7477 | 2.8571 | 20 | 0.7879 | 0.4630 | 0.7491 | 0.7527 | nan | 0.6609 | 0.8373 | 0.0 | 0.6247 | 0.7643 |
61
- | 0.5719 | 5.7143 | 40 | 0.5524 | 0.4398 | 0.6865 | 0.6903 | nan | 0.5941 | 0.7788 | 0.0 | 0.5759 | 0.7436 |
62
- | 0.5369 | 8.5714 | 60 | 0.4835 | 0.4419 | 0.6869 | 0.6897 | nan | 0.6189 | 0.7549 | 0.0 | 0.6011 | 0.7247 |
 
 
 
 
63
 
64
 
65
  ### 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: 0.7816
21
+ - Mean Iou: 0.4625
22
+ - Mean Accuracy: 0.8009
23
+ - Overall Accuracy: 0.8059
24
  - Accuracy No-label: nan
25
+ - Accuracy Object1: 0.6792
26
+ - Accuracy Object2: 0.9225
27
  - Iou No-label: 0.0
28
+ - Iou Object1: 0.6389
29
+ - Iou Object2: 0.7485
30
 
31
  ## Model description
32
 
 
45
  ### Training hyperparameters
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
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy No-label | Accuracy Object1 | Accuracy Object2 | Iou No-label | Iou Object1 | Iou Object2 |
59
  |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------------:|:----------------:|:----------------:|:------------:|:-----------:|:-----------:|
60
+ | 0.9891 | 1.4286 | 20 | 1.0335 | 0.3298 | 0.6654 | 0.6772 | nan | 0.3809 | 0.9500 | 0.0 | 0.3618 | 0.6276 |
61
+ | 0.9534 | 2.8571 | 40 | 0.9094 | 0.3836 | 0.7262 | 0.7360 | nan | 0.4884 | 0.9640 | 0.0 | 0.4728 | 0.6778 |
62
+ | 0.8917 | 4.2857 | 60 | 0.8524 | 0.4227 | 0.7669 | 0.7743 | nan | 0.5876 | 0.9463 | 0.0 | 0.5603 | 0.7077 |
63
+ | 0.8488 | 5.7143 | 80 | 0.8163 | 0.4619 | 0.8056 | 0.8104 | nan | 0.6888 | 0.9223 | 0.0 | 0.6435 | 0.7422 |
64
+ | 0.8531 | 7.1429 | 100 | 0.7959 | 0.4541 | 0.7955 | 0.8008 | nan | 0.6679 | 0.9232 | 0.0 | 0.6264 | 0.7359 |
65
+ | 0.8254 | 8.5714 | 120 | 0.7843 | 0.4535 | 0.7927 | 0.7982 | nan | 0.6595 | 0.9259 | 0.0 | 0.6217 | 0.7389 |
66
+ | 0.832 | 10.0 | 140 | 0.7816 | 0.4625 | 0.8009 | 0.8059 | nan | 0.6792 | 0.9225 | 0.0 | 0.6389 | 0.7485 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57cf5e65e423044f96b71e1c57c99450df1dafaab98548c74724f3de8f4e75d9
3
  size 14885804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6268ec89fc945eb1b0947bcf910deca67ea51ba5b225b30911383d208d90e723
3
  size 14885804
runs/Aug20_07-35-52_bdedd370450b/events.out.tfevents.1724139383.bdedd370450b.897.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1512b06840c413ade5e8710045e590fdd1ead3bd03eef09fcd44f99d41638b80
3
+ size 40287
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6901954e5d1f58acd74724fff131d870172893454d3042f56e39cd60c826e08
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8254c71e043503b2a459ab8a58e560bea11cb368d66302dc0670a042a48f29b7
3
  size 5240