Hugging Face's logo

Vrjb
/
SegFormer_b2_2

Transformers
Safetensors
segformer
Generated from Trainer
Model card Files Community
Vrjb commited on
Commit
aa460a0
·
verified ·
1 Parent(s): 310acc3

Model save

Browse files
Files changed (3) hide show
  1. README.md +62 -78
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,48 +16,48 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [nvidia/segformer-b2-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b2-finetuned-cityscapes-1024-1024) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Accuracy Bicycle: 0.8262
20
- - Accuracy Building: 0.9449
21
- - Accuracy Bus: 0.8903
22
- - Accuracy Car: 0.9680
23
- - Accuracy Fence: 0.6775
24
- - Accuracy Motorcycle: 0.6014
25
- - Accuracy Person: 0.8587
26
- - Accuracy Pole: 0.6439
27
- - Accuracy Rider: 0.6288
28
- - Accuracy Road: 0.9858
29
- - Accuracy Sidewalk: 0.9139
30
- - Accuracy Sky: 0.9736
31
- - Accuracy Terrain: 0.7288
32
- - Accuracy Traffic light: 0.7787
33
- - Accuracy Traffic sign: 0.8035
34
- - Accuracy Train: 0.8132
35
- - Accuracy Truck: 0.8366
36
- - Accuracy Vegetation: 0.9460
37
- - Accuracy Wall: 0.6818
38
- - Iou Bicycle: 0.6671
39
- - Iou Building: 0.8977
40
- - Iou Bus: 0.8013
41
- - Iou Car: 0.9213
42
- - Iou Fence: 0.5507
43
- - Iou Motorcycle: 0.4750
44
- - Iou Person: 0.6971
45
- - Iou Pole: 0.4411
46
- - Iou Rider: 0.4634
47
- - Iou Road: 0.9780
48
- - Iou Sidewalk: 0.8245
49
- - Iou Sky: 0.9288
50
- - Iou Terrain: 0.6138
51
- - Iou Traffic light: 0.5638
52
- - Iou Traffic sign: 0.6713
53
- - Iou Train: 0.7305
54
- - Iou Truck: 0.7060
55
- - Iou Vegetation: 0.9013
56
- - Iou Wall: 0.5995
57
- - Loss: 0.5978
58
- - Mean Accuracy: 0.8159
59
- - Mean Iou: 0.7070
60
- - Overall Accuracy: 0.9460
61
 
62
  ## Model description
63
 
@@ -77,51 +77,35 @@ More information needed
77
 
78
  The following hyperparameters were used during training:
79
  - learning_rate: 0.0002
80
- - train_batch_size: 32
81
- - eval_batch_size: 32
82
  - seed: 42
83
  - gradient_accumulation_steps: 4
84
- - total_train_batch_size: 128
85
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
86
  - lr_scheduler_type: linear
87
- - lr_scheduler_warmup_steps: 500
88
  - num_epochs: 130
89
  - mixed_precision_training: Native AMP
90
 
91
  ### Training results
92
 
93
- | Training Loss | Epoch | Step | Accuracy Bicycle | Accuracy Building | Accuracy Bus | Accuracy Car | Accuracy Fence | Accuracy Motorcycle | Accuracy Person | Accuracy Pole | Accuracy Rider | Accuracy Road | Accuracy Sidewalk | Accuracy Sky | Accuracy Terrain | Accuracy Traffic light | Accuracy Traffic sign | Accuracy Train | Accuracy Truck | Accuracy Vegetation | Accuracy Wall | Iou Bicycle | Iou Building | Iou Bus | Iou Car | Iou Fence | Iou Motorcycle | Iou Person | Iou Pole | Iou Rider | Iou Road | Iou Sidewalk | Iou Sky | Iou Terrain | Iou Traffic light | Iou Traffic sign | Iou Train | Iou Truck | Iou Vegetation | Iou Wall | Validation Loss | Mean Accuracy | Mean Iou | Overall Accuracy |
94
- |:-------------:|:--------:|:----:|:----------------:|:-----------------:|:------------:|:------------:|:--------------:|:-------------------:|:---------------:|:-------------:|:--------------:|:-------------:|:-----------------:|:------------:|:----------------:|:----------------------:|:---------------------:|:--------------:|:--------------:|:-------------------:|:-------------:|:-----------:|:------------:|:-------:|:-------:|:---------:|:--------------:|:----------:|:--------:|:---------:|:--------:|:------------:|:-------:|:-----------:|:-----------------:|:----------------:|:---------:|:---------:|:--------------:|:--------:|:---------------:|:-------------:|:--------:|:----------------:|
95
- | 0.6763 | 4.1720 | 100 | 0.8362 | 0.9317 | 0.8807 | 0.9649 | 0.6686 | 0.6682 | 0.8485 | 0.5989 | 0.6385 | 0.9816 | 0.9065 | 0.9765 | 0.7760 | 0.7699 | 0.7853 | 0.8293 | 0.7365 | 0.9371 | 0.7217 | 0.6322 | 0.8886 | 0.7271 | 0.9108 | 0.4862 | 0.4362 | 0.6498 | 0.4079 | 0.4157 | 0.9751 | 0.8124 | 0.9175 | 0.6020 | 0.4710 | 0.6184 | 0.6716 | 0.6066 | 0.8922 | 0.5787 | 0.6208 | 0.8135 | 0.6684 | 0.9390 |
96
- | 0.649 | 8.3441 | 200 | 0.8241 | 0.9382 | 0.9060 | 0.9611 | 0.6888 | 0.6651 | 0.8443 | 0.6116 | 0.6588 | 0.9818 | 0.9075 | 0.9719 | 0.7836 | 0.7716 | 0.7959 | 0.8210 | 0.7537 | 0.9369 | 0.6542 | 0.6342 | 0.8915 | 0.7434 | 0.9142 | 0.4901 | 0.4191 | 0.6671 | 0.4114 | 0.4353 | 0.9756 | 0.8113 | 0.9235 | 0.6097 | 0.4876 | 0.6309 | 0.6678 | 0.6191 | 0.8936 | 0.5531 | 0.6129 | 0.8145 | 0.6725 | 0.9402 |
97
- | 0.6327 | 12.5161 | 300 | 0.8250 | 0.9328 | 0.9357 | 0.9609 | 0.6909 | 0.6842 | 0.8400 | 0.6175 | 0.6792 | 0.9839 | 0.9098 | 0.9798 | 0.7755 | 0.7802 | 0.8031 | 0.7399 | 0.7759 | 0.9384 | 0.7078 | 0.6332 | 0.8920 | 0.7468 | 0.9143 | 0.4882 | 0.4235 | 0.6669 | 0.4175 | 0.4400 | 0.9770 | 0.8202 | 0.9188 | 0.6148 | 0.4975 | 0.6342 | 0.6823 | 0.5800 | 0.8952 | 0.5790 | 0.6065 | 0.8190 | 0.6748 | 0.9410 |
98
- | 0.6321 | 16.6882 | 400 | 0.8473 | 0.9333 | 0.9042 | 0.9597 | 0.6878 | 0.6749 | 0.8289 | 0.6306 | 0.6738 | 0.9840 | 0.9194 | 0.9750 | 0.7271 | 0.7847 | 0.7854 | 0.8171 | 0.8296 | 0.9367 | 0.7383 | 0.6360 | 0.8931 | 0.7894 | 0.9161 | 0.4811 | 0.4574 | 0.6752 | 0.4139 | 0.4474 | 0.9766 | 0.8173 | 0.9243 | 0.6003 | 0.5042 | 0.6356 | 0.6679 | 0.6483 | 0.8944 | 0.5733 | 0.6049 | 0.8230 | 0.6817 | 0.9411 |
99
- | 0.6219 | 20.8602 | 500 | 0.8085 | 0.9301 | 0.9266 | 0.9593 | 0.7064 | 0.6943 | 0.8425 | 0.6387 | 0.7025 | 0.9832 | 0.9199 | 0.9780 | 0.7778 | 0.7839 | 0.8100 | 0.8120 | 0.7471 | 0.9386 | 0.7158 | 0.6482 | 0.8910 | 0.7310 | 0.9151 | 0.5059 | 0.4182 | 0.6754 | 0.4164 | 0.4467 | 0.9765 | 0.8162 | 0.9207 | 0.6187 | 0.5148 | 0.6485 | 0.7533 | 0.6318 | 0.8958 | 0.5640 | 0.6012 | 0.8250 | 0.6836 | 0.9411 |
100
- | 0.1572 | 25.0 | 600 | 0.8167 | 0.9384 | 0.8867 | 0.9602 | 0.6745 | 0.6673 | 0.8645 | 0.6280 | 0.6791 | 0.9844 | 0.9125 | 0.9778 | 0.7342 | 0.7659 | 0.7921 | 0.8300 | 0.8411 | 0.9431 | 0.6924 | 0.6612 | 0.8947 | 0.7886 | 0.9151 | 0.5092 | 0.4830 | 0.6717 | 0.4254 | 0.4626 | 0.9770 | 0.8187 | 0.9233 | 0.6089 | 0.5399 | 0.6485 | 0.7090 | 0.6634 | 0.8981 | 0.5849 | 0.6016 | 0.8205 | 0.6938 | 0.9431 |
101
- | 0.613 | 29.1720 | 700 | 0.8183 | 0.9368 | 0.9089 | 0.9620 | 0.7040 | 0.6935 | 0.8512 | 0.6348 | 0.7416 | 0.9839 | 0.9135 | 0.9756 | 0.7501 | 0.8059 | 0.7921 | 0.8327 | 0.8974 | 0.9414 | 0.7066 | 0.6473 | 0.8953 | 0.8132 | 0.9176 | 0.5289 | 0.4490 | 0.6741 | 0.4251 | 0.4382 | 0.9772 | 0.8228 | 0.9279 | 0.6057 | 0.5201 | 0.6563 | 0.7073 | 0.6844 | 0.8977 | 0.5853 | 0.5985 | 0.8342 | 0.6933 | 0.9432 |
102
- | 0.6154 | 33.3441 | 800 | 0.8270 | 0.9393 | 0.8993 | 0.9667 | 0.7066 | 0.6561 | 0.8642 | 0.6180 | 0.6853 | 0.9831 | 0.9264 | 0.9763 | 0.7192 | 0.7746 | 0.7913 | 0.7972 | 0.8290 | 0.9402 | 0.7187 | 0.6545 | 0.8968 | 0.8111 | 0.9195 | 0.5315 | 0.4827 | 0.6750 | 0.4280 | 0.4560 | 0.9767 | 0.8168 | 0.9279 | 0.5997 | 0.5442 | 0.6618 | 0.7143 | 0.7031 | 0.8974 | 0.5736 | 0.5988 | 0.8220 | 0.6985 | 0.9437 |
103
- | 0.5967 | 37.5161 | 900 | 0.8368 | 0.9410 | 0.9186 | 0.9659 | 0.6942 | 0.6912 | 0.8592 | 0.6302 | 0.6752 | 0.9848 | 0.9150 | 0.9766 | 0.7284 | 0.8032 | 0.8060 | 0.7736 | 0.8285 | 0.9429 | 0.7013 | 0.6568 | 0.8973 | 0.8036 | 0.9189 | 0.5218 | 0.4588 | 0.6856 | 0.4320 | 0.4652 | 0.9777 | 0.8257 | 0.9283 | 0.6038 | 0.5385 | 0.6666 | 0.7255 | 0.6933 | 0.9000 | 0.5961 | 0.5974 | 0.8249 | 0.6998 | 0.9447 |
104
- | 0.6113 | 43.3441 | 1000 | 0.8114 | 0.9435 | 0.9162 | 0.9682 | 0.6887 | 0.6922 | 0.8528 | 0.6319 | 0.6959 | 0.9840 | 0.9185 | 0.9747 | 0.7511 | 0.7938 | 0.8076 | 0.8179 | 0.8431 | 0.9453 | 0.6844 | 0.6675 | 0.8979 | 0.8282 | 0.9209 | 0.5519 | 0.4788 | 0.6895 | 0.4343 | 0.4795 | 0.9775 | 0.8251 | 0.9280 | 0.6232 | 0.5477 | 0.6681 | 0.7208 | 0.7055 | 0.9006 | 0.5850 | 0.5974 | 0.8274 | 0.7068 | 0.9456 |
105
- | 0.6155 | 47.5161 | 1100 | 0.8193 | 0.9404 | 0.9000 | 0.9650 | 0.7242 | 0.6926 | 0.8622 | 0.6371 | 0.6744 | 0.9848 | 0.9096 | 0.9761 | 0.7650 | 0.7841 | 0.8067 | 0.8327 | 0.8597 | 0.9443 | 0.6867 | 0.6607 | 0.8975 | 0.8213 | 0.9193 | 0.5429 | 0.4796 | 0.6891 | 0.4329 | 0.4818 | 0.9773 | 0.8235 | 0.9258 | 0.6255 | 0.5465 | 0.6665 | 0.7301 | 0.6962 | 0.9004 | 0.5856 | 0.5966 | 0.8297 | 0.7054 | 0.9450 |
106
- | 0.605 | 51.6882 | 1200 | 0.8356 | 0.9416 | 0.9192 | 0.9682 | 0.6789 | 0.6754 | 0.8590 | 0.6360 | 0.6497 | 0.9847 | 0.9171 | 0.9766 | 0.7311 | 0.7955 | 0.8059 | 0.7841 | 0.8372 | 0.9442 | 0.6923 | 0.6606 | 0.8975 | 0.7930 | 0.9183 | 0.5300 | 0.4747 | 0.6877 | 0.4345 | 0.4726 | 0.9781 | 0.8287 | 0.9260 | 0.6068 | 0.5421 | 0.6693 | 0.7221 | 0.7117 | 0.9004 | 0.5852 | 0.5966 | 0.8227 | 0.7021 | 0.9452 |
107
- | 0.5865 | 55.8602 | 1300 | 0.8238 | 0.9405 | 0.9057 | 0.9670 | 0.7083 | 0.6673 | 0.8572 | 0.6398 | 0.6839 | 0.9851 | 0.9173 | 0.9761 | 0.7360 | 0.7990 | 0.8095 | 0.8257 | 0.8463 | 0.9440 | 0.6720 | 0.6586 | 0.8972 | 0.8166 | 0.9214 | 0.5501 | 0.4759 | 0.6857 | 0.4334 | 0.4690 | 0.9780 | 0.8251 | 0.9261 | 0.6123 | 0.5400 | 0.6711 | 0.7240 | 0.7229 | 0.9003 | 0.5816 | 0.5966 | 0.8266 | 0.7047 | 0.9452 |
108
- | 0.1505 | 60.0 | 1400 | 0.8310 | 0.9406 | 0.9175 | 0.9665 | 0.6897 | 0.6671 | 0.8492 | 0.6415 | 0.6798 | 0.9855 | 0.9173 | 0.9753 | 0.7203 | 0.7981 | 0.8107 | 0.8027 | 0.8389 | 0.9476 | 0.6767 | 0.6618 | 0.8987 | 0.8084 | 0.9201 | 0.5429 | 0.4889 | 0.6904 | 0.4342 | 0.4703 | 0.9783 | 0.8265 | 0.9282 | 0.6085 | 0.5468 | 0.6719 | 0.7289 | 0.7062 | 0.9007 | 0.5901 | 0.5973 | 0.8240 | 0.7054 | 0.9456 |
109
- | 0.6019 | 64.1720 | 1500 | 0.8321 | 0.9432 | 0.9117 | 0.9682 | 0.6942 | 0.6693 | 0.8522 | 0.6313 | 0.6682 | 0.9847 | 0.9200 | 0.9761 | 0.7374 | 0.8045 | 0.8070 | 0.8258 | 0.8397 | 0.9451 | 0.6770 | 0.6637 | 0.8988 | 0.8152 | 0.9206 | 0.5487 | 0.4857 | 0.6911 | 0.4349 | 0.4724 | 0.9781 | 0.8265 | 0.9269 | 0.6131 | 0.5470 | 0.6708 | 0.7441 | 0.7183 | 0.9011 | 0.5854 | 0.5965 | 0.8257 | 0.7075 | 0.9458 |
110
- | 0.6082 | 68.3441 | 1600 | 0.8249 | 0.9428 | 0.9110 | 0.9683 | 0.6844 | 0.6680 | 0.8569 | 0.6339 | 0.6637 | 0.9853 | 0.9182 | 0.9755 | 0.7302 | 0.7945 | 0.8067 | 0.8150 | 0.8432 | 0.9462 | 0.6799 | 0.6649 | 0.8985 | 0.8145 | 0.9209 | 0.5444 | 0.4907 | 0.6910 | 0.4349 | 0.4700 | 0.9783 | 0.8273 | 0.9274 | 0.6142 | 0.5526 | 0.6707 | 0.7383 | 0.7218 | 0.9011 | 0.5894 | 0.5969 | 0.8236 | 0.7079 | 0.9459 |
111
- | 0.6057 | 73.7742 | 1700 | 0.8342 | 0.9444 | 0.9132 | 0.9674 | 0.6959 | 0.6581 | 0.8547 | 0.6279 | 0.6629 | 0.9849 | 0.9208 | 0.9768 | 0.7394 | 0.7859 | 0.8000 | 0.8019 | 0.8525 | 0.9454 | 0.6808 | 0.6667 | 0.8992 | 0.8112 | 0.9208 | 0.5568 | 0.4826 | 0.6950 | 0.4368 | 0.4680 | 0.9783 | 0.8273 | 0.9278 | 0.6107 | 0.5552 | 0.6754 | 0.7357 | 0.7128 | 0.9014 | 0.5878 | 0.5966 | 0.8235 | 0.7079 | 0.9462 |
112
- | 0.5902 | 77.9462 | 1800 | 0.8231 | 0.9412 | 0.9140 | 0.9655 | 0.6859 | 0.6790 | 0.8644 | 0.6439 | 0.6521 | 0.9834 | 0.9214 | 0.9756 | 0.7299 | 0.7915 | 0.8075 | 0.8062 | 0.8496 | 0.9474 | 0.7073 | 0.6659 | 0.8986 | 0.8144 | 0.9200 | 0.5493 | 0.4959 | 0.6882 | 0.4345 | 0.4651 | 0.9776 | 0.8249 | 0.9275 | 0.6154 | 0.5535 | 0.6679 | 0.7355 | 0.7024 | 0.9009 | 0.6018 | 0.5963 | 0.8257 | 0.7073 | 0.9455 |
113
- | 0.5844 | 82.0860 | 1900 | 0.8153 | 0.9418 | 0.9073 | 0.9678 | 0.6821 | 0.6820 | 0.8621 | 0.6425 | 0.6528 | 0.9857 | 0.9170 | 0.9758 | 0.7316 | 0.8014 | 0.8038 | 0.8135 | 0.8386 | 0.9450 | 0.6829 | 0.6661 | 0.8974 | 0.8120 | 0.9207 | 0.5475 | 0.4830 | 0.6899 | 0.4329 | 0.4729 | 0.9783 | 0.8269 | 0.9257 | 0.6150 | 0.5492 | 0.6721 | 0.7398 | 0.7211 | 0.9006 | 0.5936 | 0.5974 | 0.8236 | 0.7076 | 0.9456 |
114
- | 0.6002 | 86.2581 | 2000 | 0.8202 | 0.9421 | 0.9062 | 0.9692 | 0.6877 | 0.6950 | 0.8645 | 0.6349 | 0.6645 | 0.9855 | 0.9173 | 0.9768 | 0.7449 | 0.7940 | 0.8092 | 0.8238 | 0.8284 | 0.9454 | 0.6975 | 0.6660 | 0.8985 | 0.8120 | 0.9207 | 0.5581 | 0.4865 | 0.6906 | 0.4365 | 0.4789 | 0.9784 | 0.8280 | 0.9280 | 0.6188 | 0.5531 | 0.6724 | 0.7333 | 0.7155 | 0.9007 | 0.5964 | 0.5963 | 0.8267 | 0.7091 | 0.9461 |
115
- | 0.5994 | 90.4301 | 2100 | 0.8275 | 0.9426 | 0.8978 | 0.9679 | 0.6835 | 0.6745 | 0.8577 | 0.6385 | 0.6705 | 0.9854 | 0.9175 | 0.9758 | 0.7307 | 0.7930 | 0.8066 | 0.8256 | 0.8419 | 0.9471 | 0.6835 | 0.6654 | 0.8985 | 0.8111 | 0.9209 | 0.5453 | 0.4970 | 0.6913 | 0.4371 | 0.4766 | 0.9785 | 0.8288 | 0.9270 | 0.6188 | 0.5546 | 0.6725 | 0.7412 | 0.7208 | 0.9011 | 0.5929 | 0.5969 | 0.8246 | 0.7094 | 0.9461 |
116
- | 0.5897 | 94.6022 | 2200 | 0.8219 | 0.9433 | 0.9060 | 0.9684 | 0.6841 | 0.6610 | 0.8635 | 0.6373 | 0.6571 | 0.9851 | 0.9207 | 0.9757 | 0.7376 | 0.7946 | 0.8039 | 0.8242 | 0.8316 | 0.9463 | 0.6824 | 0.6689 | 0.8985 | 0.8115 | 0.9215 | 0.5489 | 0.5015 | 0.6920 | 0.4370 | 0.4758 | 0.9784 | 0.8288 | 0.9271 | 0.6179 | 0.5531 | 0.6746 | 0.7421 | 0.7263 | 0.9014 | 0.5893 | 0.5967 | 0.8234 | 0.7102 | 0.9462 |
117
- | 0.5943 | 98.7742 | 2300 | 0.8253 | 0.9436 | 0.9044 | 0.9685 | 0.6821 | 0.6711 | 0.8623 | 0.6365 | 0.6539 | 0.9858 | 0.9187 | 0.9759 | 0.7307 | 0.7947 | 0.8060 | 0.8184 | 0.8382 | 0.9462 | 0.6811 | 0.6688 | 0.8986 | 0.8117 | 0.9213 | 0.5501 | 0.4981 | 0.6926 | 0.4377 | 0.4736 | 0.9787 | 0.8300 | 0.9273 | 0.6166 | 0.5542 | 0.6746 | 0.7438 | 0.7260 | 0.9013 | 0.5891 | 0.5966 | 0.8233 | 0.7102 | 0.9463 |
118
- | 0.5988 | 104.1720 | 2400 | 0.8235 | 0.9455 | 0.9132 | 0.9686 | 0.7072 | 0.6616 | 0.8569 | 0.6359 | 0.6259 | 0.9844 | 0.9149 | 0.9762 | 0.7296 | 0.7874 | 0.8040 | 0.8115 | 0.8439 | 0.9436 | 0.6705 | 0.6658 | 0.8978 | 0.8018 | 0.9198 | 0.5381 | 0.4730 | 0.6947 | 0.4371 | 0.4691 | 0.9778 | 0.8258 | 0.9280 | 0.6127 | 0.5548 | 0.6725 | 0.7327 | 0.7294 | 0.9007 | 0.5843 | 0.5971 | 0.8213 | 0.7061 | 0.9456 |
119
- | 0.5968 | 108.3441 | 2500 | 0.8442 | 0.9408 | 0.8922 | 0.9685 | 0.6813 | 0.6150 | 0.8498 | 0.6433 | 0.6675 | 0.9858 | 0.9152 | 0.9759 | 0.7361 | 0.8084 | 0.8026 | 0.8403 | 0.8400 | 0.9454 | 0.6961 | 0.6576 | 0.8988 | 0.7935 | 0.9201 | 0.5453 | 0.4663 | 0.6905 | 0.4376 | 0.4554 | 0.9782 | 0.8258 | 0.9286 | 0.6197 | 0.5384 | 0.6735 | 0.7347 | 0.7153 | 0.9003 | 0.5934 | 0.5964 | 0.8236 | 0.7038 | 0.9456 |
120
- | 0.5934 | 112.5161 | 2600 | 0.8267 | 0.9417 | 0.8930 | 0.9663 | 0.6780 | 0.6904 | 0.8500 | 0.6529 | 0.6629 | 0.9851 | 0.9182 | 0.9732 | 0.7291 | 0.8029 | 0.8066 | 0.8414 | 0.8154 | 0.9461 | 0.6904 | 0.6634 | 0.8978 | 0.7907 | 0.9195 | 0.5427 | 0.4832 | 0.6929 | 0.4339 | 0.4602 | 0.9780 | 0.8276 | 0.9293 | 0.6219 | 0.5494 | 0.6734 | 0.7479 | 0.6764 | 0.9008 | 0.5980 | 0.5964 | 0.8247 | 0.7046 | 0.9455 |
121
- | 0.5893 | 116.6882 | 2700 | 0.8316 | 0.9460 | 0.8689 | 0.9678 | 0.7088 | 0.6357 | 0.8551 | 0.6420 | 0.6625 | 0.9858 | 0.9202 | 0.9758 | 0.7252 | 0.7788 | 0.7964 | 0.7989 | 0.8307 | 0.9442 | 0.6789 | 0.6651 | 0.9008 | 0.7851 | 0.9216 | 0.5594 | 0.4902 | 0.6928 | 0.4404 | 0.4711 | 0.9785 | 0.8254 | 0.9280 | 0.6207 | 0.5652 | 0.6744 | 0.7374 | 0.7051 | 0.9013 | 0.5985 | 0.5967 | 0.8186 | 0.7085 | 0.9465 |
122
- | 0.598 | 120.8602 | 2800 | 0.8248 | 0.9426 | 0.8877 | 0.9702 | 0.6858 | 0.6403 | 0.8694 | 0.6413 | 0.6432 | 0.9849 | 0.9174 | 0.9749 | 0.7394 | 0.8017 | 0.8145 | 0.8240 | 0.8345 | 0.9460 | 0.6913 | 0.6687 | 0.8988 | 0.7999 | 0.9203 | 0.5387 | 0.5032 | 0.6932 | 0.4434 | 0.4683 | 0.9782 | 0.8276 | 0.9283 | 0.6096 | 0.5563 | 0.6685 | 0.7417 | 0.7233 | 0.9015 | 0.6029 | 0.5962 | 0.8228 | 0.7091 | 0.9461 |
123
- | 0.1497 | 125.0 | 2900 | 0.8211 | 0.9433 | 0.8712 | 0.9675 | 0.6773 | 0.6297 | 0.8645 | 0.6431 | 0.6212 | 0.9839 | 0.9250 | 0.9740 | 0.7376 | 0.7925 | 0.8022 | 0.8372 | 0.8380 | 0.9479 | 0.6826 | 0.6688 | 0.8983 | 0.8017 | 0.9207 | 0.5458 | 0.4906 | 0.6925 | 0.4414 | 0.4662 | 0.9779 | 0.8277 | 0.9288 | 0.6221 | 0.5526 | 0.6740 | 0.7356 | 0.7041 | 0.9011 | 0.5898 | 0.5974 | 0.8189 | 0.7074 | 0.9460 |
124
- | 0.5912 | 129.1720 | 3000 | 0.8262 | 0.9449 | 0.8903 | 0.9680 | 0.6775 | 0.6014 | 0.8587 | 0.6439 | 0.6288 | 0.9858 | 0.9139 | 0.9736 | 0.7288 | 0.7787 | 0.8035 | 0.8132 | 0.8366 | 0.9460 | 0.6818 | 0.6671 | 0.8977 | 0.8013 | 0.9213 | 0.5507 | 0.4750 | 0.6971 | 0.4411 | 0.4634 | 0.9780 | 0.8245 | 0.9288 | 0.6138 | 0.5638 | 0.6713 | 0.7305 | 0.7060 | 0.9013 | 0.5995 | 0.5978 | 0.8159 | 0.7070 | 0.9460 |
125
 
126
 
127
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [nvidia/segformer-b2-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b2-finetuned-cityscapes-1024-1024) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5687
20
+ - Mean Iou: 0.7141
21
+ - Mean Accuracy: 0.8338
22
+ - Overall Accuracy: 0.9518
23
+ - Accuracy Road: 0.9861
24
+ - Accuracy Sidewalk: 0.9403
25
+ - Accuracy Building: 0.9549
26
+ - Accuracy Wall: 0.7046
27
+ - Accuracy Fence: 0.7106
28
+ - Accuracy Pole: 0.6880
29
+ - Accuracy Traffic light: 0.8719
30
+ - Accuracy Traffic sign: 0.8349
31
+ - Accuracy Vegetation: 0.9442
32
+ - Accuracy Terrain: 0.6876
33
+ - Accuracy Sky: 0.9817
34
+ - Accuracy Person: 0.8778
35
+ - Accuracy Rider: 0.5796
36
+ - Accuracy Car: 0.9746
37
+ - Accuracy Truck: 0.7663
38
+ - Accuracy Bus: 0.9041
39
+ - Accuracy Train: 0.7933
40
+ - Accuracy Motorcycle: 0.7614
41
+ - Accuracy Bicycle: 0.8798
42
+ - Iou Road: 0.9809
43
+ - Iou Sidewalk: 0.8418
44
+ - Iou Building: 0.9125
45
+ - Iou Wall: 0.5459
46
+ - Iou Fence: 0.5277
47
+ - Iou Pole: 0.5466
48
+ - Iou Traffic light: 0.6398
49
+ - Iou Traffic sign: 0.7499
50
+ - Iou Vegetation: 0.9115
51
+ - Iou Terrain: 0.5282
52
+ - Iou Sky: 0.9396
53
+ - Iou Person: 0.7568
54
+ - Iou Rider: 0.4521
55
+ - Iou Car: 0.9319
56
+ - Iou Truck: 0.6160
57
+ - Iou Bus: 0.7445
58
+ - Iou Train: 0.6995
59
+ - Iou Motorcycle: 0.5142
60
+ - Iou Bicycle: 0.7285
61
 
62
  ## Model description
63
 
 
77
 
78
  The following hyperparameters were used during training:
79
  - learning_rate: 0.0002
80
+ - train_batch_size: 2
81
+ - eval_batch_size: 2
82
  - seed: 42
83
  - gradient_accumulation_steps: 4
84
+ - total_train_batch_size: 8
85
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
86
  - lr_scheduler_type: linear
87
+ - lr_scheduler_warmup_steps: 1000
88
  - num_epochs: 130
89
  - mixed_precision_training: Native AMP
90
 
91
  ### Training results
92
 
93
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Road | Accuracy Sidewalk | Accuracy Building | Accuracy Wall | Accuracy Fence | Accuracy Pole | Accuracy Traffic light | Accuracy Traffic sign | Accuracy Vegetation | Accuracy Terrain | Accuracy Sky | Accuracy Person | Accuracy Rider | Accuracy Car | Accuracy Truck | Accuracy Bus | Accuracy Train | Accuracy Motorcycle | Accuracy Bicycle | Iou Road | Iou Sidewalk | Iou Building | Iou Wall | Iou Fence | Iou Pole | Iou Traffic light | Iou Traffic sign | Iou Vegetation | Iou Terrain | Iou Sky | Iou Person | Iou Rider | Iou Car | Iou Truck | Iou Bus | Iou Train | Iou Motorcycle | Iou Bicycle |
94
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------:|:-----------------:|:-----------------:|:-------------:|:--------------:|:-------------:|:----------------------:|:---------------------:|:-------------------:|:----------------:|:------------:|:---------------:|:--------------:|:------------:|:--------------:|:------------:|:--------------:|:-------------------:|:----------------:|:--------:|:------------:|:------------:|:--------:|:---------:|:--------:|:-----------------:|:----------------:|:--------------:|:-----------:|:-------:|:----------:|:---------:|:-------:|:---------:|:-------:|:---------:|:--------------:|:-----------:|
95
+ | 0.6593 | 0.2688 | 100 | 0.5767 | 0.7490 | 0.8653 | 0.9557 | 0.9879 | 0.9291 | 0.9527 | 0.6811 | 0.6907 | 0.7639 | 0.8966 | 0.8935 | 0.9505 | 0.7808 | 0.9856 | 0.9001 | 0.7336 | 0.9768 | 0.7932 | 0.9450 | 0.8737 | 0.8252 | 0.8802 | 0.9820 | 0.8569 | 0.9152 | 0.6022 | 0.5665 | 0.5525 | 0.6085 | 0.7337 | 0.9183 | 0.6399 | 0.9381 | 0.7709 | 0.5525 | 0.9413 | 0.7157 | 0.8153 | 0.8165 | 0.5705 | 0.7338 |
96
+ | 0.6791 | 0.5376 | 200 | 0.5698 | 0.7492 | 0.8600 | 0.9561 | 0.9880 | 0.9336 | 0.9583 | 0.6325 | 0.7103 | 0.7513 | 0.8553 | 0.8639 | 0.9489 | 0.7918 | 0.9852 | 0.8956 | 0.7517 | 0.9729 | 0.7818 | 0.9393 | 0.8832 | 0.8112 | 0.8840 | 0.9821 | 0.8560 | 0.9163 | 0.5714 | 0.5725 | 0.5599 | 0.6532 | 0.7479 | 0.9181 | 0.6287 | 0.9407 | 0.7748 | 0.5506 | 0.9428 | 0.6955 | 0.8014 | 0.8020 | 0.5780 | 0.7421 |
97
+ | 0.684 | 0.8065 | 300 | 0.5660 | 0.7540 | 0.8645 | 0.9570 | 0.9883 | 0.9310 | 0.9544 | 0.7076 | 0.7504 | 0.7494 | 0.8755 | 0.8758 | 0.9524 | 0.8069 | 0.9867 | 0.8878 | 0.7234 | 0.9740 | 0.7900 | 0.9457 | 0.8782 | 0.7426 | 0.9050 | 0.9827 | 0.8597 | 0.9187 | 0.6108 | 0.5737 | 0.5617 | 0.6427 | 0.7589 | 0.9198 | 0.6545 | 0.9430 | 0.7718 | 0.5517 | 0.9434 | 0.7264 | 0.7988 | 0.7947 | 0.5935 | 0.7189 |
98
+ | 0.658 | 1.0753 | 400 | 0.5648 | 0.7555 | 0.8713 | 0.9566 | 0.9876 | 0.9253 | 0.9519 | 0.7672 | 0.6932 | 0.7528 | 0.8699 | 0.8854 | 0.9538 | 0.7916 | 0.9818 | 0.9127 | 0.7634 | 0.9750 | 0.8688 | 0.9482 | 0.8984 | 0.7359 | 0.8924 | 0.9820 | 0.8559 | 0.9184 | 0.6372 | 0.5723 | 0.5547 | 0.6505 | 0.7551 | 0.9188 | 0.6353 | 0.9460 | 0.7588 | 0.5468 | 0.9409 | 0.7869 | 0.8348 | 0.7207 | 0.6050 | 0.7344 |
99
+ | 0.5832 | 1.3441 | 500 | 0.5662 | 0.7441 | 0.8714 | 0.9555 | 0.9888 | 0.9327 | 0.9422 | 0.7124 | 0.7149 | 0.7371 | 0.8847 | 0.8679 | 0.9616 | 0.7678 | 0.9862 | 0.8949 | 0.7883 | 0.9697 | 0.8754 | 0.9480 | 0.9008 | 0.7969 | 0.8863 | 0.9828 | 0.8533 | 0.9149 | 0.6197 | 0.5738 | 0.5542 | 0.6272 | 0.7509 | 0.9178 | 0.6262 | 0.9390 | 0.7630 | 0.5299 | 0.9410 | 0.7117 | 0.8474 | 0.7103 | 0.5715 | 0.7036 |
100
+ | 0.5949 | 1.6129 | 600 | 0.5658 | 0.7512 | 0.8710 | 0.9555 | 0.9878 | 0.9256 | 0.9433 | 0.7911 | 0.7468 | 0.7528 | 0.9006 | 0.8701 | 0.9563 | 0.7578 | 0.9817 | 0.9151 | 0.7248 | 0.9787 | 0.9052 | 0.9474 | 0.8130 | 0.7913 | 0.8603 | 0.9815 | 0.8545 | 0.9147 | 0.6437 | 0.5660 | 0.5541 | 0.6132 | 0.7441 | 0.9176 | 0.6410 | 0.9440 | 0.7493 | 0.5356 | 0.9394 | 0.7897 | 0.8492 | 0.7631 | 0.5436 | 0.7285 |
101
+ | 0.5894 | 1.8817 | 700 | 0.5636 | 0.7371 | 0.8666 | 0.9543 | 0.9869 | 0.9263 | 0.9460 | 0.7916 | 0.6749 | 0.7552 | 0.8802 | 0.8670 | 0.9504 | 0.8268 | 0.9835 | 0.9047 | 0.7147 | 0.9759 | 0.8055 | 0.9644 | 0.7929 | 0.8427 | 0.8767 | 0.9815 | 0.8548 | 0.9136 | 0.6382 | 0.5519 | 0.5478 | 0.6420 | 0.7505 | 0.9150 | 0.6215 | 0.9411 | 0.7632 | 0.5342 | 0.9389 | 0.7291 | 0.7657 | 0.7170 | 0.4891 | 0.7087 |
102
+ | 0.5715 | 2.1505 | 800 | 0.5679 | 0.7431 | 0.8700 | 0.9549 | 0.9862 | 0.9338 | 0.9460 | 0.7668 | 0.7404 | 0.7456 | 0.8754 | 0.8627 | 0.9608 | 0.7677 | 0.9812 | 0.8570 | 0.8195 | 0.9624 | 0.8757 | 0.9346 | 0.9068 | 0.7152 | 0.8921 | 0.9817 | 0.8523 | 0.9154 | 0.6357 | 0.5846 | 0.5438 | 0.6327 | 0.7417 | 0.9165 | 0.6558 | 0.9434 | 0.7518 | 0.4961 | 0.9354 | 0.6757 | 0.8227 | 0.7332 | 0.5868 | 0.7143 |
103
+ | 0.6365 | 2.4194 | 900 | 0.5647 | 0.7432 | 0.8610 | 0.9548 | 0.9870 | 0.9341 | 0.9505 | 0.6885 | 0.6909 | 0.7165 | 0.8781 | 0.8895 | 0.9547 | 0.7721 | 0.9881 | 0.8999 | 0.7258 | 0.9706 | 0.8670 | 0.9193 | 0.9065 | 0.7449 | 0.8744 | 0.9820 | 0.8544 | 0.9128 | 0.5677 | 0.5229 | 0.5553 | 0.6414 | 0.7557 | 0.9180 | 0.6489 | 0.9289 | 0.7704 | 0.5566 | 0.9367 | 0.7645 | 0.8216 | 0.7082 | 0.5442 | 0.7298 |
104
+ | 0.6795 | 2.6882 | 1000 | 0.5673 | 0.7301 | 0.8648 | 0.9525 | 0.9838 | 0.9305 | 0.9489 | 0.6736 | 0.7227 | 0.7042 | 0.9196 | 0.8746 | 0.9526 | 0.7629 | 0.9884 | 0.8850 | 0.7949 | 0.9674 | 0.8915 | 0.9001 | 0.8440 | 0.7920 | 0.8939 | 0.9788 | 0.8417 | 0.9104 | 0.5765 | 0.5507 | 0.5537 | 0.5471 | 0.7434 | 0.9160 | 0.6141 | 0.9285 | 0.7561 | 0.5163 | 0.9338 | 0.7324 | 0.8068 | 0.7732 | 0.4745 | 0.7187 |
105
+ | 0.6517 | 2.9570 | 1100 | 0.5647 | 0.7173 | 0.8507 | 0.9512 | 0.9836 | 0.9402 | 0.9490 | 0.7080 | 0.6173 | 0.7459 | 0.8519 | 0.8803 | 0.9454 | 0.7947 | 0.9821 | 0.8759 | 0.7743 | 0.9645 | 0.9189 | 0.9356 | 0.7035 | 0.7064 | 0.8856 | 0.9796 | 0.8370 | 0.9103 | 0.5719 | 0.5054 | 0.5426 | 0.6418 | 0.7274 | 0.9125 | 0.5885 | 0.9426 | 0.7510 | 0.5055 | 0.9346 | 0.7204 | 0.7279 | 0.6447 | 0.4707 | 0.7137 |
106
+ | 0.6038 | 3.2258 | 1200 | 0.5645 | 0.7330 | 0.8552 | 0.9526 | 0.9843 | 0.9456 | 0.9536 | 0.7353 | 0.7254 | 0.7528 | 0.8507 | 0.8675 | 0.9411 | 0.7901 | 0.9830 | 0.8741 | 0.7417 | 0.9695 | 0.7350 | 0.8992 | 0.8817 | 0.7758 | 0.8421 | 0.9799 | 0.8397 | 0.9131 | 0.6145 | 0.5277 | 0.5483 | 0.6496 | 0.7479 | 0.9124 | 0.5919 | 0.9413 | 0.7624 | 0.5452 | 0.9372 | 0.6455 | 0.7698 | 0.7256 | 0.5486 | 0.7257 |
107
+ | 0.6218 | 3.4946 | 1300 | 0.5641 | 0.7224 | 0.8571 | 0.9524 | 0.9863 | 0.9358 | 0.9425 | 0.7547 | 0.6836 | 0.7491 | 0.8775 | 0.8444 | 0.9505 | 0.8109 | 0.9820 | 0.9127 | 0.7426 | 0.9710 | 0.6970 | 0.9102 | 0.9148 | 0.7668 | 0.8517 | 0.9810 | 0.8483 | 0.9106 | 0.6126 | 0.5573 | 0.5396 | 0.6359 | 0.7261 | 0.9120 | 0.6001 | 0.9429 | 0.7474 | 0.5381 | 0.9369 | 0.6221 | 0.7279 | 0.6511 | 0.5116 | 0.7233 |
108
+ | 0.5334 | 3.7634 | 1400 | 0.5687 | 0.7141 | 0.8338 | 0.9518 | 0.9861 | 0.9403 | 0.9549 | 0.7046 | 0.7106 | 0.6880 | 0.8719 | 0.8349 | 0.9442 | 0.6876 | 0.9817 | 0.8778 | 0.5796 | 0.9746 | 0.7663 | 0.9041 | 0.7933 | 0.7614 | 0.8798 | 0.9809 | 0.8418 | 0.9125 | 0.5459 | 0.5277 | 0.5466 | 0.6398 | 0.7499 | 0.9115 | 0.5282 | 0.9396 | 0.7568 | 0.4521 | 0.9319 | 0.6160 | 0.7445 | 0.6995 | 0.5142 | 0.7285 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
 
110
 
111
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba652b8d76d9a68be84bc4773449dfa96317200712c0c2a66c61dfc466636de6
3
  size 109496316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57522c4980c5c17635f5e8282b8e85f5e2ebf63fd04418f6aa538161afcbfa1
3
  size 109496316
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:716ac1f62c9fd84ada6161ccc3719f0ba619419682b6d33f00761651c302eaad
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5774cf234067716bb5d9aa78503f8ec059ecdd12adf900dadb6a00989d73c2a4
3
  size 5368