shevek commited on
Commit
413345a
1 Parent(s): 90201dd

End of training

Browse files
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
@@ -18,52 +18,57 @@ 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 None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2090
22
- - Mean Iou: 0.5696
23
- - Mean Accuracy: 0.6654
24
- - Overall Accuracy: 0.9106
25
- - Accuracy Structure (dimensional): nan
26
- - Accuracy Impervious (planiform): 0.9401
27
- - Accuracy Fences: 0.0
28
- - Accuracy Water storage/tank: nan
29
- - Accuracy Pool < 100 sqft: nan
30
- - Accuracy Pool > 100 sqft: 0.9530
31
- - Accuracy Irrigated planiform: 0.8838
32
- - Accuracy Irrigated dimensional low: 0.8370
33
- - Accuracy Irrigated dimensional high: 0.9432
34
- - Accuracy Irrigated bare: 0.4234
35
- - Accuracy Irrigable planiform: 0.8112
36
- - Accuracy Irrigable dimensional low: 0.5718
37
- - Accuracy Irrigable dimensional high: 0.9410
38
- - Accuracy Irrigable bare: 0.7245
39
- - Accuracy Native planiform: nan
40
- - Accuracy Native dimensional low: 0.0
41
- - Accuracy Native dimensional high: 0.0
42
- - Accuracy Native bare: 0.9472
43
- - Accuracy Udl: nan
44
- - Accuracy Open water: 0.9967
45
- - Accuracy Artificial turf: 0.6743
46
- - Iou Structure (dimensional): 0.0
47
- - Iou Impervious (planiform): 0.8873
48
- - Iou Fences: 0.0
49
- - Iou Water storage/tank: nan
50
- - Iou Pool < 100 sqft: nan
51
- - Iou Pool > 100 sqft: 0.8999
52
- - Iou Irrigated planiform: 0.7859
53
- - Iou Irrigated dimensional low: 0.7122
54
- - Iou Irrigated dimensional high: 0.8937
55
- - Iou Irrigated bare: 0.3648
56
- - Iou Irrigable planiform: 0.7323
57
- - Iou Irrigable dimensional low: 0.4772
58
- - Iou Irrigable dimensional high: 0.8844
59
- - Iou Irrigable bare: 0.6417
60
- - Iou Native planiform: nan
61
- - Iou Native dimensional low: 0.0
62
- - Iou Native dimensional high: 0.0
63
- - Iou Native bare: 0.8356
64
- - Iou Udl: nan
65
- - Iou Open water: 0.9389
66
- - Iou Artificial turf: 0.6287
 
 
 
 
 
67
 
68
  ## Model description
69
 
@@ -90,13 +95,6 @@ The following hyperparameters were used during training:
90
  - lr_scheduler_type: linear
91
  - num_epochs: 20
92
 
93
- ### Training results
94
-
95
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Structure (dimensional) | Accuracy Impervious (planiform) | Accuracy Fences | Accuracy Water storage/tank | Accuracy Pool < 100 sqft | Accuracy Pool > 100 sqft | Accuracy Irrigated planiform | Accuracy Irrigated dimensional low | Accuracy Irrigated dimensional high | Accuracy Irrigated bare | Accuracy Irrigable planiform | Accuracy Irrigable dimensional low | Accuracy Irrigable dimensional high | Accuracy Irrigable bare | Accuracy Native planiform | Accuracy Native dimensional low | Accuracy Native dimensional high | Accuracy Native bare | Accuracy Udl | Accuracy Open water | Accuracy Artificial turf | Iou Structure (dimensional) | Iou Impervious (planiform) | Iou Fences | Iou Water storage/tank | Iou Pool < 100 sqft | Iou Pool > 100 sqft | Iou Irrigated planiform | Iou Irrigated dimensional low | Iou Irrigated dimensional high | Iou Irrigated bare | Iou Irrigable planiform | Iou Irrigable dimensional low | Iou Irrigable dimensional high | Iou Irrigable bare | Iou Native planiform | Iou Native dimensional low | Iou Native dimensional high | Iou Native bare | Iou Udl | Iou Open water | Iou Artificial turf |
96
- |:-------------:|:-------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:--------------------------------:|:-------------------------------:|:---------------:|:---------------------------:|:------------------------:|:------------------------:|:----------------------------:|:----------------------------------:|:-----------------------------------:|:-----------------------:|:----------------------------:|:----------------------------------:|:-----------------------------------:|:-----------------------:|:-------------------------:|:-------------------------------:|:--------------------------------:|:--------------------:|:------------:|:-------------------:|:------------------------:|:---------------------------:|:--------------------------:|:----------:|:----------------------:|:-------------------:|:-------------------:|:-----------------------:|:-----------------------------:|:------------------------------:|:------------------:|:-----------------------:|:-----------------------------:|:------------------------------:|:------------------:|:--------------------:|:--------------------------:|:---------------------------:|:---------------:|:-------:|:--------------:|:-------------------:|
97
- | 0.2526 | 15.3846 | 200 | 0.2090 | 0.5696 | 0.6654 | 0.9106 | nan | 0.9401 | 0.0 | nan | nan | 0.9530 | 0.8838 | 0.8370 | 0.9432 | 0.4234 | 0.8112 | 0.5718 | 0.9410 | 0.7245 | nan | 0.0 | 0.0 | 0.9472 | nan | 0.9967 | 0.6743 | 0.0 | 0.8873 | 0.0 | nan | nan | 0.8999 | 0.7859 | 0.7122 | 0.8937 | 0.3648 | 0.7323 | 0.4772 | 0.8844 | 0.6417 | nan | 0.0 | 0.0 | 0.8356 | nan | 0.9389 | 0.6287 |
98
-
99
-
100
  ### Framework versions
101
 
102
  - Transformers 4.44.2
 
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 None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - eval_loss: 0.2053
22
+ - eval_mean_iou: 0.5448
23
+ - eval_mean_accuracy: 0.6296
24
+ - eval_overall_accuracy: 0.9130
25
+ - eval_accuracy_Structure (dimensional): nan
26
+ - eval_accuracy_Impervious (planiform): 0.9578
27
+ - eval_accuracy_Fences: 0.3758
28
+ - eval_accuracy_Water Storage/Tank: nan
29
+ - eval_accuracy_Pool < 100 sqft: 0.0
30
+ - eval_accuracy_Pool > 100 sqft: 0.8208
31
+ - eval_accuracy_Irrigated Planiform: 0.8708
32
+ - eval_accuracy_Irrigated Dimensional Low: 0.6817
33
+ - eval_accuracy_Irrigated Dimensional High: 0.9472
34
+ - eval_accuracy_Irrigated Bare: 0.4827
35
+ - eval_accuracy_Irrigable Planiform: 0.6668
36
+ - eval_accuracy_Irrigable Dimensional Low: 0.6013
37
+ - eval_accuracy_Irrigable Dimensional High: 0.7902
38
+ - eval_accuracy_Irrigable Bare: 0.5657
39
+ - eval_accuracy_Native Planiform: 0.9093
40
+ - eval_accuracy_Native Dimensional Low: 0.0
41
+ - eval_accuracy_Native Dimensional High: 0.0961
42
+ - eval_accuracy_Native Bare: 0.9332
43
+ - eval_accuracy_UDL: nan
44
+ - eval_accuracy_Open Water: 0.6613
45
+ - eval_accuracy_Artificial Turf: 0.9720
46
+ - eval_iou_Structure (dimensional): 0.0
47
+ - eval_iou_Impervious (planiform): 0.8964
48
+ - eval_iou_Fences: 0.3104
49
+ - eval_iou_Water Storage/Tank: nan
50
+ - eval_iou_Pool < 100 sqft: 0.0
51
+ - eval_iou_Pool > 100 sqft: 0.8199
52
+ - eval_iou_Irrigated Planiform: 0.7563
53
+ - eval_iou_Irrigated Dimensional Low: 0.5480
54
+ - eval_iou_Irrigated Dimensional High: 0.8920
55
+ - eval_iou_Irrigated Bare: 0.4053
56
+ - eval_iou_Irrigable Planiform: 0.6007
57
+ - eval_iou_Irrigable Dimensional Low: 0.5083
58
+ - eval_iou_Irrigable Dimensional High: 0.7595
59
+ - eval_iou_Irrigable Bare: 0.5106
60
+ - eval_iou_Native Planiform: 0.8678
61
+ - eval_iou_Native Dimensional Low: 0.0
62
+ - eval_iou_Native Dimensional High: 0.0961
63
+ - eval_iou_Native Bare: 0.8293
64
+ - eval_iou_UDL: nan
65
+ - eval_iou_Open Water: 0.5929
66
+ - eval_iou_Artificial Turf: 0.9584
67
+ - eval_runtime: 6.2852
68
+ - eval_samples_per_second: 15.91
69
+ - eval_steps_per_second: 1.114
70
+ - epoch: 10.8
71
+ - step: 270
72
 
73
  ## Model description
74
 
 
95
  - lr_scheduler_type: linear
96
  - num_epochs: 20
97
 
 
 
 
 
 
 
 
98
  ### Framework versions
99
 
100
  - Transformers 4.44.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:966bc27861556dca41a240e5b46e08af0fbcfa714fed79154dfe1f30f1d262be
3
  size 14904316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f98d60c3c6f09a52ffd3ef21d8320ab46239473ff5513719ef27e069c1d73fa
3
  size 14904316
runs/Nov01_04-02-32_51022d54530c/events.out.tfevents.1730433766.51022d54530c.3311.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fe6c348d964db28d6d3cd19c60d098f82fe02315ad9e38cf62f8c6dcf84c75
3
+ size 181613
runs/Nov01_04-02-32_51022d54530c/events.out.tfevents.1730434680.51022d54530c.3311.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a004f01afb7d99606c36524f6528a08e9dc91b7d5e5d7726f35ffca690916ae
3
+ size 181614
runs/Nov01_04-02-32_51022d54530c/events.out.tfevents.1730435591.51022d54530c.3311.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0587f6abf6268b58859ace47e3add812de03538d4ccc6c027ca2b1893082864
3
+ size 181614
runs/Nov01_04-02-32_51022d54530c/events.out.tfevents.1730436508.51022d54530c.3311.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce32ae787b5a67364cb011544fdbc7322587a18223c37b385af12981f10aeb9
3
+ size 181614
runs/Nov01_04-02-32_51022d54530c/events.out.tfevents.1730437427.51022d54530c.3311.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acad9807c9579c5e49eb1cfaa6924191cc7fe7079f0de5943c41d2c63ff2f690
3
+ size 181614
runs/Nov01_04-02-32_51022d54530c/events.out.tfevents.1730438343.51022d54530c.3311.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae8c6e7462de2692d16f7ac5f44d6e31065e94949ae1ca3c5c419606b117962
3
+ size 100833
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:111be75dc6ba8460362e7a690b6a03ccbc86433d1ac1958ff8a30b3b9bdd49f8
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556703b3c60fdcc89df3236908d7f0d824c1752fed0dc42bb8f8088bce32d05c
3
  size 5240