Hugging Face's logo

saad7489
/
segformer-b0-finetuned-segments-SixrayKnife8-21-2024_saad5

Image Segmentation
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Model card Files Metrics Community
saad7489 commited on
Commit
ac8e788
•
1 Parent(s): 8e06786

End of training

Browse files
Files changed (5) hide show
  1. README.md +17 -23
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Aug21_10-26-58_098ec4303bbe/events.out.tfevents.1724236038.098ec4303bbe.2437.3 +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: 0.2923
21
- - Mean Iou: 0.8066
22
- - Mean Accuracy: 0.9078
23
- - Overall Accuracy: 0.9857
24
- - Accuracy Bkg: 0.9917
25
- - Accuracy Knife: 0.8251
26
- - Accuracy Gun: 0.9065
27
- - Iou Bkg: 0.9869
28
- - Iou Knife: 0.7133
29
- - Iou Gun: 0.7196
30
 
31
  ## Model description
32
 
@@ -45,28 +45,22 @@ More information needed
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
- - learning_rate: 6e-05
49
  - train_batch_size: 20
50
  - eval_batch_size: 20
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - num_epochs: 50
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
- | 0.8263 | 5.0 | 20 | 0.9552 | 0.5735 | 0.8760 | 0.9414 | 0.9464 | 0.8112 | 0.8703 | 0.9424 | 0.4242 | 0.3540 |
61
- | 0.6154 | 10.0 | 40 | 0.6184 | 0.6297 | 0.7711 | 0.9652 | 0.9800 | 0.6061 | 0.7272 | 0.9657 | 0.4854 | 0.4379 |
62
- | 0.5165 | 15.0 | 60 | 0.5098 | 0.6805 | 0.8233 | 0.9714 | 0.9826 | 0.7375 | 0.7498 | 0.9720 | 0.5691 | 0.5003 |
63
- | 0.4503 | 20.0 | 80 | 0.4561 | 0.7103 | 0.8818 | 0.9735 | 0.9805 | 0.7960 | 0.8690 | 0.9742 | 0.5898 | 0.5670 |
64
- | 0.4154 | 25.0 | 100 | 0.3958 | 0.7526 | 0.8997 | 0.9791 | 0.9852 | 0.8206 | 0.8934 | 0.9800 | 0.6237 | 0.6540 |
65
- | 0.3659 | 30.0 | 120 | 0.3529 | 0.7810 | 0.8969 | 0.9832 | 0.9899 | 0.7932 | 0.9076 | 0.9844 | 0.6814 | 0.6773 |
66
- | 0.3616 | 35.0 | 140 | 0.3253 | 0.7949 | 0.8937 | 0.9848 | 0.9918 | 0.8004 | 0.8889 | 0.9858 | 0.6954 | 0.7035 |
67
- | 0.3666 | 40.0 | 160 | 0.3110 | 0.8018 | 0.9085 | 0.9852 | 0.9911 | 0.8255 | 0.9087 | 0.9863 | 0.7079 | 0.7112 |
68
- | 0.3082 | 45.0 | 180 | 0.2983 | 0.8011 | 0.9037 | 0.9852 | 0.9914 | 0.8195 | 0.9002 | 0.9863 | 0.6982 | 0.7189 |
69
- | 0.3097 | 50.0 | 200 | 0.2923 | 0.8066 | 0.9078 | 0.9857 | 0.9917 | 0.8251 | 0.9065 | 0.9869 | 0.7133 | 0.7196 |
70
 
71
 
72
  ### 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: 0.2720
21
+ - Mean Iou: 0.8171
22
+ - Mean Accuracy: 0.9114
23
+ - Overall Accuracy: 0.9868
24
+ - Accuracy Bkg: 0.9925
25
+ - Accuracy Knife: 0.8345
26
+ - Accuracy Gun: 0.9072
27
+ - Iou Bkg: 0.9878
28
+ - Iou Knife: 0.7337
29
+ - Iou Gun: 0.7298
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: 20
50
  - eval_batch_size: 20
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 Knife | Accuracy Gun | Iou Bkg | Iou Knife | Iou Gun |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:--------------:|:------------:|:-------:|:---------:|:-------:|
60
+ | 0.2986 | 5.0 | 20 | 0.2833 | 0.8180 | 0.9092 | 0.9869 | 0.9928 | 0.8290 | 0.9057 | 0.9879 | 0.7362 | 0.7299 |
61
+ | 0.2801 | 10.0 | 40 | 0.2780 | 0.8141 | 0.9117 | 0.9864 | 0.9921 | 0.8366 | 0.9063 | 0.9875 | 0.7281 | 0.7268 |
62
+ | 0.2908 | 15.0 | 60 | 0.2739 | 0.8178 | 0.9075 | 0.9869 | 0.9930 | 0.8289 | 0.9005 | 0.9880 | 0.7332 | 0.7321 |
63
+ | 0.2928 | 20.0 | 80 | 0.2720 | 0.8171 | 0.9114 | 0.9868 | 0.9925 | 0.8345 | 0.9072 | 0.9878 | 0.7337 | 0.7298 |
 
 
 
 
 
 
64
 
65
 
66
  ### 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-SixrayKnife8-21-2024_saad5",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff3d30ae7fc3a9d8a9b0a212d23ced773cf51f931a29a827d949f266873629e3
3
  size 14885804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf16053b7b016dd51e4ec0a7009f864ad0105f5c0e46a302a31dd49a3dd252dc
3
  size 14885804
runs/Aug21_10-26-58_098ec4303bbe/events.out.tfevents.1724236038.098ec4303bbe.2437.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:717efe6cc1a6c23629a0e958495ad4f6c0cbd2856e870a1351d21c67df868869
3
+ size 25447
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da408ba8603bebd00ddca7c3def9cdb41973aaf2a5d488187063cdc52ed0115a
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2467dbda006b95082d2dffb05b568221beb8c32f66e9d8272f032ddce19f09
3
  size 5240