Hugging Face's logo

ZeeeWP
/
segformer-b0-finetuned-segments-satellite-terrain

Image Segmentation
Transformers
Safetensors
segformer
vision
Generated from Trainer
Model card Files Community
ZeeeWP commited on
Commit
f950831
·
verified ·
1 Parent(s): a80c9fe

End of training

Browse files
Files changed (3) hide show
  1. README.md +19 -19
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- base_model: nvidia/mit-b0
3
  library_name: transformers
4
  license: other
 
5
  tags:
6
  - vision
7
  - image-segmentation
@@ -18,25 +18,25 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ZeeeWP/terrain_map dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.5864
22
- - Mean Iou: 0.2321
23
- - Mean Accuracy: 0.3696
24
- - Overall Accuracy: 0.5634
25
  - Accuracy Unlabeled: nan
26
- - Accuracy Sand: 0.7791
27
- - Accuracy Cliff: 0.7374
28
- - Accuracy Bedrock flat: 0.6510
29
- - Accuracy Bedrock lowhill: 0.0354
30
  - Accuracy Bedrock highhill: 0.0
31
- - Accuracy Gravel low hill: 0.3842
32
  - Accuracy Gravel high hill: 0.0
33
  - Iou Unlabeled: 0.0
34
- - Iou Sand: 0.6893
35
- - Iou Cliff: 0.4361
36
- - Iou Bedrock flat: 0.4508
37
- - Iou Bedrock lowhill: 0.0337
38
  - Iou Bedrock highhill: 0.0
39
- - Iou Gravel low hill: 0.2469
40
  - Iou Gravel high hill: 0.0
41
 
42
  ## Model description
@@ -68,10 +68,10 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Sand | Accuracy Cliff | Accuracy Bedrock flat | Accuracy Bedrock lowhill | Accuracy Bedrock highhill | Accuracy Gravel low hill | Accuracy Gravel high hill | Iou Unlabeled | Iou Sand | Iou Cliff | Iou Bedrock flat | Iou Bedrock lowhill | Iou Bedrock highhill | Iou Gravel low hill | Iou Gravel high hill |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:--------------:|:---------------------:|:------------------------:|:-------------------------:|:------------------------:|:-------------------------:|:-------------:|:--------:|:---------:|:----------------:|:-------------------:|:--------------------:|:-------------------:|:--------------------:|
71
- | 1.8112 | 2.5 | 20 | 1.9952 | 0.1801 | 0.3131 | 0.4952 | nan | 0.5584 | 0.8000 | 0.5986 | 0.0492 | 0.0055 | 0.1607 | 0.0192 | 0.0 | 0.4056 | 0.4166 | 0.4358 | 0.0456 | 0.0018 | 0.1338 | 0.0019 |
72
- | 1.6328 | 5.0 | 40 | 1.7866 | 0.2145 | 0.3514 | 0.5421 | nan | 0.7209 | 0.8280 | 0.6081 | 0.0391 | 0.0 | 0.2636 | 0.0 | 0.0 | 0.6272 | 0.4126 | 0.4458 | 0.0376 | 0.0 | 0.1931 | 0.0 |
73
- | 1.5004 | 7.5 | 60 | 1.6383 | 0.2316 | 0.3695 | 0.5571 | nan | 0.7734 | 0.7044 | 0.6298 | 0.0443 | 0.0 | 0.4344 | 0.0 | 0.0 | 0.6825 | 0.4346 | 0.4371 | 0.0411 | 0.0 | 0.2576 | 0.0 |
74
- | 1.5562 | 10.0 | 80 | 1.5864 | 0.2321 | 0.3696 | 0.5634 | nan | 0.7791 | 0.7374 | 0.6510 | 0.0354 | 0.0 | 0.3842 | 0.0 | 0.0 | 0.6893 | 0.4361 | 0.4508 | 0.0337 | 0.0 | 0.2469 | 0.0 |
75
 
76
 
77
  ### Framework versions
 
1
  ---
 
2
  library_name: transformers
3
  license: other
4
+ base_model: nvidia/mit-b0
5
  tags:
6
  - vision
7
  - image-segmentation
 
18
 
19
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ZeeeWP/terrain_map dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.6101
22
+ - Mean Iou: 0.1907
23
+ - Mean Accuracy: 0.3530
24
+ - Overall Accuracy: 0.4780
25
  - Accuracy Unlabeled: nan
26
+ - Accuracy Sand: 0.5878
27
+ - Accuracy Cliff: 0.7663
28
+ - Accuracy Bedrock flat: 0.7396
29
+ - Accuracy Bedrock lowhill: 0.0135
30
  - Accuracy Bedrock highhill: 0.0
31
+ - Accuracy Gravel low hill: 0.3636
32
  - Accuracy Gravel high hill: 0.0
33
  - Iou Unlabeled: 0.0
34
+ - Iou Sand: 0.4409
35
+ - Iou Cliff: 0.4125
36
+ - Iou Bedrock flat: 0.3709
37
+ - Iou Bedrock lowhill: 0.0132
38
  - Iou Bedrock highhill: 0.0
39
+ - Iou Gravel low hill: 0.2884
40
  - Iou Gravel high hill: 0.0
41
 
42
  ## Model description
 
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Sand | Accuracy Cliff | Accuracy Bedrock flat | Accuracy Bedrock lowhill | Accuracy Bedrock highhill | Accuracy Gravel low hill | Accuracy Gravel high hill | Iou Unlabeled | Iou Sand | Iou Cliff | Iou Bedrock flat | Iou Bedrock lowhill | Iou Bedrock highhill | Iou Gravel low hill | Iou Gravel high hill |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:--------------:|:---------------------:|:------------------------:|:-------------------------:|:------------------------:|:-------------------------:|:-------------:|:--------:|:---------:|:----------------:|:-------------------:|:--------------------:|:-------------------:|:--------------------:|
71
+ | 1.8047 | 2.5 | 20 | 1.9790 | 0.1684 | 0.3173 | 0.4408 | nan | 0.4519 | 0.8376 | 0.5959 | 0.0301 | 0.0 | 0.3053 | 0.0 | 0.0 | 0.3641 | 0.3607 | 0.3496 | 0.0296 | 0.0 | 0.2429 | 0.0 |
72
+ | 1.5102 | 5.0 | 40 | 1.7599 | 0.1694 | 0.3192 | 0.4582 | nan | 0.3901 | 0.8340 | 0.6609 | 0.0192 | 0.0 | 0.3305 | 0.0 | 0.0 | 0.3239 | 0.3799 | 0.3675 | 0.0189 | 0.0 | 0.2649 | 0.0 |
73
+ | 1.4458 | 7.5 | 60 | 1.6088 | 0.1873 | 0.3457 | 0.4639 | nan | 0.5881 | 0.7480 | 0.7632 | 0.0081 | 0.0 | 0.3122 | 0.0 | 0.0 | 0.4691 | 0.4114 | 0.3544 | 0.0080 | 0.0 | 0.2555 | 0.0 |
74
+ | 1.568 | 10.0 | 80 | 1.6101 | 0.1907 | 0.3530 | 0.4780 | nan | 0.5878 | 0.7663 | 0.7396 | 0.0135 | 0.0 | 0.3636 | 0.0 | 0.0 | 0.4409 | 0.4125 | 0.3709 | 0.0132 | 0.0 | 0.2884 | 0.0 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:616e4e4284794b8ee5b86b54b87e68e15f8497a1c8e456819a0f22f5e2785580
3
  size 14890952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256d453d173f276790336950ceec7311ab85a08afac262af88b2f6e732c918e8
3
  size 14890952
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e091ee813ad71c2b1f3bcd8846db964aa8127fa321d5f3ce0237741d3fae47b
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9c25f69430fb6bc35811c16bc63d3c8e3d643790fae01961d89896e9cf67c3
3
  size 5240