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
2ad68cd
·
verified ·
1 Parent(s): 01add4d

End of training

Browse files
Files changed (4) hide show
  1. README.md +16 -16
  2. model.safetensors +1 -1
  3. runs/Aug20_08-09-24_ab49fae2aabc/events.out.tfevents.1724141385.ab49fae2aabc.366.1 +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: 0.8400
21
- - Mean Iou: 0.5119
22
- - Mean Accuracy: 0.8558
23
- - Overall Accuracy: 0.8558
24
  - Accuracy Object1: nan
25
- - Accuracy Object2: 0.8556
26
- - Accuracy Object3: 0.8561
27
  - Iou Object1: 0.0
28
- - Iou Object2: 0.7670
29
- - Iou Object3: 0.7687
30
 
31
  ## Model description
32
 
@@ -57,13 +57,13 @@ The following hyperparameters were used during training:
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
- | 1.0078 | 1.4286 | 20 | 1.0664 | 0.3704 | 0.7172 | 0.7115 | nan | 0.6051 | 0.8292 | 0.0 | 0.5243 | 0.5870 |
61
- | 0.9646 | 2.8571 | 40 | 0.9611 | 0.4414 | 0.7944 | 0.7925 | nan | 0.7559 | 0.8330 | 0.0 | 0.6574 | 0.6668 |
62
- | 0.9287 | 4.2857 | 60 | 0.8994 | 0.4776 | 0.8308 | 0.8297 | nan | 0.8085 | 0.8532 | 0.0 | 0.7157 | 0.7172 |
63
- | 0.873 | 5.7143 | 80 | 0.8656 | 0.4944 | 0.8451 | 0.8440 | nan | 0.8231 | 0.8671 | 0.0 | 0.7390 | 0.7442 |
64
- | 0.8578 | 7.1429 | 100 | 0.8394 | 0.5069 | 0.8534 | 0.8532 | nan | 0.8493 | 0.8575 | 0.0 | 0.7602 | 0.7605 |
65
- | 0.8201 | 8.5714 | 120 | 0.8329 | 0.5102 | 0.8545 | 0.8546 | nan | 0.8558 | 0.8531 | 0.0 | 0.7648 | 0.7657 |
66
- | 0.8415 | 10.0 | 140 | 0.8400 | 0.5119 | 0.8558 | 0.8558 | nan | 0.8556 | 0.8561 | 0.0 | 0.7670 | 0.7687 |
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: 0.8755
21
+ - Mean Iou: 0.5092
22
+ - Mean Accuracy: 0.8594
23
+ - Overall Accuracy: 0.8549
24
  - Accuracy Object1: nan
25
+ - Accuracy Object2: 0.7708
26
+ - Accuracy Object3: 0.9479
27
  - Iou Object1: 0.0
28
+ - Iou Object2: 0.7432
29
+ - Iou Object3: 0.7844
30
 
31
  ## Model description
32
 
 
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
+ | 1.0985 | 1.4286 | 20 | 1.0886 | 0.2471 | 0.5995 | 0.5802 | nan | 0.2163 | 0.9827 | 0.0 | 0.2130 | 0.5284 |
61
+ | 1.051 | 2.8571 | 40 | 1.0140 | 0.3757 | 0.7369 | 0.7259 | nan | 0.5196 | 0.9542 | 0.0 | 0.4990 | 0.6280 |
62
+ | 1.0047 | 4.2857 | 60 | 0.9555 | 0.4411 | 0.8033 | 0.7952 | nan | 0.6423 | 0.9643 | 0.0 | 0.6235 | 0.6997 |
63
+ | 0.9207 | 5.7143 | 80 | 0.9049 | 0.4783 | 0.8356 | 0.8295 | nan | 0.7139 | 0.9574 | 0.0 | 0.6907 | 0.7441 |
64
+ | 0.9117 | 7.1429 | 100 | 0.8798 | 0.4988 | 0.8516 | 0.8466 | nan | 0.7523 | 0.9508 | 0.0 | 0.7257 | 0.7707 |
65
+ | 0.8705 | 8.5714 | 120 | 0.8692 | 0.5038 | 0.8543 | 0.8496 | nan | 0.7608 | 0.9478 | 0.0 | 0.7332 | 0.7783 |
66
+ | 0.8738 | 10.0 | 140 | 0.8755 | 0.5092 | 0.8594 | 0.8549 | nan | 0.7708 | 0.9479 | 0.0 | 0.7432 | 0.7844 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90d4854c1cb8bb76f7bc6459551de7b6149e87b98e157df4d9d25bc609cce230
3
  size 14885804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae27ebb5af204998ea646ba84e6ebc55c042e9cc9ee967bf4c8f13b83ca2e86
3
  size 14885804
runs/Aug20_08-09-24_ab49fae2aabc/events.out.tfevents.1724141385.ab49fae2aabc.366.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e01220a5eafd6ecd7393737eebe88c9a5b29ce13e7bde88b5367b7085e524b
3
+ size 40271
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fbd09b5d0674dc1ee38313e5bfb410a3ac02bab8cdf19d4ef1d63c014fdb50b
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f5ede119ab1c0c8f666d94a217b6e4ebad6652aca1b10d92ee4e1d30a8274c
3
  size 5240