Hugging Face's logo

johanhag
/
segformer-b0-winter

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Model card Files
xet
Metrics Community
johanhag commited on
Commit
9e1949f
·
1 Parent(s): 322fc0a

End of training

Browse files
Files changed (3) hide show
  1. README.md +26 -26
  2. model.safetensors +1 -1
  3. runs/Dec14_23-39-28_285780465a18/events.out.tfevents.1702597749.285780465a18.1092.3 +3 -0
README.md CHANGED
@@ -17,24 +17,24 @@ 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 johanhag/winter-test dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2476
21
- - Mean Iou: 0.6950
22
- - Mean Accuracy: 0.7560
23
- - Overall Accuracy: 0.9613
24
- - Accuracy Unlabeled: 0.0
25
  - Accuracy Object: nan
26
- - Accuracy Road: 0.9763
27
- - Accuracy Side walk: 0.9003
28
- - Accuracy Car: 0.9338
29
  - Accuracy Pedestrian: nan
30
- - Accuracy Other: 0.9695
31
- - Iou Unlabeled: 0.0
32
  - Iou Object: nan
33
- - Iou Road: 0.9165
34
- - Iou Side walk: 0.8125
35
- - Iou Car: 0.7846
36
  - Iou Pedestrian: nan
37
- - Iou Other: 0.9616
38
 
39
  ## Model description
40
 
@@ -65,18 +65,18 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Object | Accuracy Road | Accuracy Side walk | Accuracy Car | Accuracy Pedestrian | Accuracy Other | Iou Unlabeled | Iou Object | Iou Road | Iou Side walk | Iou Car | Iou Pedestrian | Iou Other |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:---------------:|:-------------:|:------------------:|:------------:|:-------------------:|:--------------:|:-------------:|:----------:|:--------:|:-------------:|:-------:|:--------------:|:---------:|
68
- | 0.6662 | 4.0 | 20 | 0.5318 | 0.6442 | 0.7488 | 0.9389 | 0.0 | nan | 0.9603 | 0.8801 | 0.9621 | nan | 0.9417 | 0.0 | nan | 0.8608 | 0.7657 | 0.6557 | nan | 0.9389 |
69
- | 0.4806 | 8.0 | 40 | 0.4783 | 0.6699 | 0.7602 | 0.9512 | 0.0 | nan | 0.9652 | 0.9322 | 0.9533 | nan | 0.9501 | 0.0 | nan | 0.8969 | 0.8188 | 0.6865 | nan | 0.9471 |
70
- | 0.4185 | 12.0 | 60 | 0.4170 | 0.6697 | 0.7592 | 0.9480 | 0.0 | nan | 0.9725 | 0.9327 | 0.9479 | nan | 0.9431 | 0.0 | nan | 0.8930 | 0.8040 | 0.7117 | nan | 0.9400 |
71
- | 0.3673 | 16.0 | 80 | 0.3781 | 0.6843 | 0.7673 | 0.9588 | 0.0 | nan | 0.9645 | 0.9514 | 0.9622 | nan | 0.9582 | 0.0 | nan | 0.9231 | 0.8371 | 0.7065 | nan | 0.9549 |
72
- | 0.4814 | 20.0 | 100 | 0.3583 | 0.6687 | 0.7504 | 0.9495 | 0.0 | nan | 0.9754 | 0.8796 | 0.9426 | nan | 0.9546 | 0.0 | nan | 0.8838 | 0.7781 | 0.7312 | nan | 0.9505 |
73
- | 0.3182 | 24.0 | 120 | 0.3222 | 0.6816 | 0.7537 | 0.9570 | 0.0 | nan | 0.9728 | 0.8986 | 0.9328 | nan | 0.9643 | 0.0 | nan | 0.9094 | 0.8066 | 0.7351 | nan | 0.9569 |
74
- | 0.2363 | 28.0 | 140 | 0.3001 | 0.6879 | 0.7575 | 0.9586 | 0.0 | nan | 0.9741 | 0.9156 | 0.9345 | nan | 0.9631 | 0.0 | nan | 0.9154 | 0.8165 | 0.7515 | nan | 0.9562 |
75
- | 0.2559 | 32.0 | 160 | 0.2878 | 0.6884 | 0.7562 | 0.9591 | 0.0 | nan | 0.9749 | 0.9068 | 0.9338 | nan | 0.9653 | 0.0 | nan | 0.9160 | 0.8108 | 0.7569 | nan | 0.9581 |
76
- | 0.2343 | 36.0 | 180 | 0.2731 | 0.6924 | 0.7545 | 0.9600 | 0.0 | nan | 0.9768 | 0.9010 | 0.9272 | nan | 0.9676 | 0.0 | nan | 0.9143 | 0.8088 | 0.7791 | nan | 0.9597 |
77
- | 0.3806 | 40.0 | 200 | 0.2668 | 0.6911 | 0.7555 | 0.9601 | 0.0 | nan | 0.9743 | 0.8984 | 0.9363 | nan | 0.9686 | 0.0 | nan | 0.9145 | 0.8109 | 0.7698 | nan | 0.9604 |
78
- | 0.3517 | 44.0 | 220 | 0.2591 | 0.6917 | 0.7565 | 0.9605 | 0.0 | nan | 0.9747 | 0.8958 | 0.9431 | nan | 0.9691 | 0.0 | nan | 0.9144 | 0.8119 | 0.7707 | nan | 0.9612 |
79
- | 0.2259 | 48.0 | 240 | 0.2476 | 0.6950 | 0.7560 | 0.9613 | 0.0 | nan | 0.9763 | 0.9003 | 0.9338 | nan | 0.9695 | 0.0 | nan | 0.9165 | 0.8125 | 0.7846 | nan | 0.9616 |
80
 
81
 
82
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the johanhag/winter-test dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1441
21
+ - Mean Iou: 0.8861
22
+ - Mean Accuracy: 0.9456
23
+ - Overall Accuracy: 0.9660
24
+ - Accuracy Unlabeled: nan
25
  - Accuracy Object: nan
26
+ - Accuracy Road: 0.9769
27
+ - Accuracy Side walk: 0.8930
28
+ - Accuracy Car: 0.9347
29
  - Accuracy Pedestrian: nan
30
+ - Accuracy Other: 0.9779
31
+ - Iou Unlabeled: nan
32
  - Iou Object: nan
33
+ - Iou Road: 0.9197
34
+ - Iou Side walk: 0.8250
35
+ - Iou Car: 0.8319
36
  - Iou Pedestrian: nan
37
+ - Iou Other: 0.9678
38
 
39
  ## Model description
40
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Object | Accuracy Road | Accuracy Side walk | Accuracy Car | Accuracy Pedestrian | Accuracy Other | Iou Unlabeled | Iou Object | Iou Road | Iou Side walk | Iou Car | Iou Pedestrian | Iou Other |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:---------------:|:-------------:|:------------------:|:------------:|:-------------------:|:--------------:|:-------------:|:----------:|:--------:|:-------------:|:-------:|:--------------:|:---------:|
68
+ | 0.2207 | 4.0 | 20 | 0.2300 | 0.8576 | 0.9439 | 0.9583 | nan | nan | 0.9738 | 0.8767 | 0.9564 | nan | 0.9686 | nan | nan | 0.9018 | 0.8000 | 0.7670 | nan | 0.9617 |
69
+ | 0.1792 | 8.0 | 40 | 0.2126 | 0.8696 | 0.9457 | 0.9614 | nan | nan | 0.9768 | 0.8911 | 0.9444 | nan | 0.9706 | nan | nan | 0.9106 | 0.8122 | 0.7924 | nan | 0.9633 |
70
+ | 0.1527 | 12.0 | 60 | 0.1869 | 0.8769 | 0.9470 | 0.9634 | nan | nan | 0.9776 | 0.9023 | 0.9364 | nan | 0.9718 | nan | nan | 0.9180 | 0.8165 | 0.8085 | nan | 0.9647 |
71
+ | 0.1329 | 16.0 | 80 | 0.1787 | 0.8783 | 0.9429 | 0.9634 | nan | nan | 0.9772 | 0.8880 | 0.9314 | nan | 0.9749 | nan | nan | 0.9126 | 0.8117 | 0.8229 | nan | 0.9661 |
72
+ | 0.1746 | 20.0 | 100 | 0.1651 | 0.8864 | 0.9511 | 0.9668 | nan | nan | 0.9771 | 0.9126 | 0.9395 | nan | 0.9751 | nan | nan | 0.9258 | 0.8369 | 0.8157 | nan | 0.9671 |
73
+ | 0.1218 | 24.0 | 120 | 0.1652 | 0.8798 | 0.9444 | 0.9643 | nan | nan | 0.9791 | 0.8858 | 0.9370 | nan | 0.9757 | nan | nan | 0.9140 | 0.8156 | 0.8224 | nan | 0.9673 |
74
+ | 0.0816 | 28.0 | 140 | 0.1473 | 0.8921 | 0.9521 | 0.9684 | nan | nan | 0.9723 | 0.9199 | 0.9383 | nan | 0.9780 | nan | nan | 0.9299 | 0.8478 | 0.8231 | nan | 0.9676 |
75
+ | 0.0893 | 32.0 | 160 | 0.1490 | 0.8892 | 0.9502 | 0.9672 | nan | nan | 0.9749 | 0.9140 | 0.9354 | nan | 0.9766 | nan | nan | 0.9260 | 0.8384 | 0.825 | nan | 0.9673 |
76
+ | 0.0849 | 36.0 | 180 | 0.1517 | 0.8861 | 0.9476 | 0.9660 | nan | nan | 0.9791 | 0.8987 | 0.9367 | nan | 0.9760 | nan | nan | 0.9205 | 0.8258 | 0.8308 | nan | 0.9674 |
77
+ | 0.1625 | 40.0 | 200 | 0.1519 | 0.8843 | 0.9468 | 0.9654 | nan | nan | 0.9777 | 0.8938 | 0.9394 | nan | 0.9763 | nan | nan | 0.9176 | 0.8235 | 0.8289 | nan | 0.9673 |
78
+ | 0.1396 | 44.0 | 220 | 0.1500 | 0.8850 | 0.9476 | 0.9655 | nan | nan | 0.9791 | 0.8949 | 0.9408 | nan | 0.9757 | nan | nan | 0.9187 | 0.8223 | 0.8317 | nan | 0.9674 |
79
+ | 0.0931 | 48.0 | 240 | 0.1441 | 0.8861 | 0.9456 | 0.9660 | nan | nan | 0.9769 | 0.8930 | 0.9347 | nan | 0.9779 | nan | nan | 0.9197 | 0.8250 | 0.8319 | nan | 0.9678 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a9de4a4f3cf58ec52aa8166572b2a8ca37fb5724b782086b606595c565ac963
3
  size 14889924
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e24a34cbf16098f8284526972ab3bc691ae8a3797c0c2388e350fbbbee801f0
3
  size 14889924
runs/Dec14_23-39-28_285780465a18/events.out.tfevents.1702597749.285780465a18.1092.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8006fa420098eb245c8ad471d135323d42ef285d2a41e0576b85c890a33099
3
+ size 58911