Hugging Face's logo

Vrjb
/
SegFormer_b2_

Transformers
Safetensors
segformer
Generated from Trainer
Model card Files
xet
 Community
Vrjb commited on
Commit
ded9f26
·
verified ·
1 Parent(s): 1bf4cfe

Model save

Browse files
Files changed (4) hide show
  1. README.md +125 -158
  2. config.json +112 -144
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,158 +1,125 @@
1
- ---
2
- library_name: transformers
3
- license: other
4
- base_model: nvidia/segformer-b1-finetuned-cityscapes-1024-1024
5
- tags:
6
- - vision
7
- - image-segmentation
8
- - generated_from_trainer
9
- model-index:
10
- - name: SegFormer_b2_
11
- results: []
12
- ---
13
-
14
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
- should probably proofread and complete it, then remove this comment. -->
16
-
17
- # SegFormer_b2_
18
-
19
- This model is a fine-tuned version of [nvidia/segformer-b1-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b1-finetuned-cityscapes-1024-1024) on the Cityscapes dataset.
20
- It achieves the following results on the evaluation set:
21
- - Loss: nan
22
- - Mean Iou: 0.0
23
- - Mean Accuracy: 0.0
24
- - Overall Accuracy: 0.0
25
- - Accuracy Unlabeled: nan
26
- - Accuracy Ego vehicle: nan
27
- - Accuracy Rectification border: nan
28
- - Accuracy Out of roi: nan
29
- - Accuracy Static: nan
30
- - Accuracy Dynamic: nan
31
- - Accuracy Ground: nan
32
- - Accuracy Road: 0.0
33
- - Accuracy Sidewalk: 0.0
34
- - Accuracy Parking: nan
35
- - Accuracy Rail track: nan
36
- - Accuracy Building: 0.0
37
- - Accuracy Wall: 0.0
38
- - Accuracy Fence: 0.0
39
- - Accuracy Guard rail: nan
40
- - Accuracy Bridge: nan
41
- - Accuracy Tunnel: nan
42
- - Accuracy Pole: 0.0
43
- - Accuracy Polegroup: nan
44
- - Accuracy Traffic light: 0.0
45
- - Accuracy Traffic sign: 0.0
46
- - Accuracy Vegetation: 0.0
47
- - Accuracy Terrain: 0.0
48
- - Accuracy Sky: nan
49
- - Accuracy Person: 0.0
50
- - Accuracy Rider: 0.0
51
- - Accuracy Car: 0.0
52
- - Accuracy Truck: 0.0
53
- - Accuracy Bus: 0.0
54
- - Accuracy Caravan: nan
55
- - Accuracy Trailer: nan
56
- - Accuracy Train: 0.0
57
- - Accuracy Motorcycle: 0.0
58
- - Accuracy Bicycle: 0.0
59
- - Accuracy License plate: nan
60
- - Iou Unlabeled: 0.0
61
- - Iou Ego vehicle: nan
62
- - Iou Rectification border: nan
63
- - Iou Out of roi: nan
64
- - Iou Static: nan
65
- - Iou Dynamic: nan
66
- - Iou Ground: nan
67
- - Iou Road: 0.0
68
- - Iou Sidewalk: 0.0
69
- - Iou Parking: nan
70
- - Iou Rail track: nan
71
- - Iou Building: 0.0
72
- - Iou Wall: 0.0
73
- - Iou Fence: 0.0
74
- - Iou Guard rail: nan
75
- - Iou Bridge: nan
76
- - Iou Tunnel: nan
77
- - Iou Pole: 0.0
78
- - Iou Polegroup: nan
79
- - Iou Traffic light: 0.0
80
- - Iou Traffic sign: 0.0
81
- - Iou Vegetation: 0.0
82
- - Iou Terrain: 0.0
83
- - Iou Sky: nan
84
- - Iou Person: 0.0
85
- - Iou Rider: 0.0
86
- - Iou Car: 0.0
87
- - Iou Truck: 0.0
88
- - Iou Bus: 0.0
89
- - Iou Caravan: nan
90
- - Iou Trailer: nan
91
- - Iou Train: 0.0
92
- - Iou Motorcycle: 0.0
93
- - Iou Bicycle: 0.0
94
- - Iou License plate: nan
95
-
96
- ## Model description
97
-
98
- More information needed
99
-
100
- ## Intended uses & limitations
101
-
102
- More information needed
103
-
104
- ## Training and evaluation data
105
-
106
- More information needed
107
-
108
- ## Training procedure
109
-
110
- ### Training hyperparameters
111
-
112
- The following hyperparameters were used during training:
113
- - learning_rate: 0.0005
114
- - train_batch_size: 2
115
- - eval_batch_size: 2
116
- - seed: 42
117
- - gradient_accumulation_steps: 4
118
- - total_train_batch_size: 8
119
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
120
- - lr_scheduler_type: linear
121
- - lr_scheduler_warmup_steps: 500
122
- - num_epochs: 30
123
- - mixed_precision_training: Native AMP
124
-
125
- ### Training results
126
-
127
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Ego vehicle | Accuracy Rectification border | Accuracy Out of roi | Accuracy Static | Accuracy Dynamic | Accuracy Ground | Accuracy Road | Accuracy Sidewalk | Accuracy Parking | Accuracy Rail track | Accuracy Building | Accuracy Wall | Accuracy Fence | Accuracy Guard rail | Accuracy Bridge | Accuracy Tunnel | Accuracy Pole | Accuracy Polegroup | Accuracy Traffic light | Accuracy Traffic sign | Accuracy Vegetation | Accuracy Terrain | Accuracy Sky | Accuracy Person | Accuracy Rider | Accuracy Car | Accuracy Truck | Accuracy Bus | Accuracy Caravan | Accuracy Trailer | Accuracy Train | Accuracy Motorcycle | Accuracy Bicycle | Accuracy License plate | Iou Unlabeled | Iou Ego vehicle | Iou Rectification border | Iou Out of roi | Iou Static | Iou Dynamic | Iou Ground | Iou Road | Iou Sidewalk | Iou Parking | Iou Rail track | Iou Building | Iou Wall | Iou Fence | Iou Guard rail | Iou Bridge | Iou Tunnel | Iou Pole | Iou Polegroup | Iou Traffic light | Iou Traffic sign | Iou Vegetation | Iou Terrain | Iou Sky | Iou Person | Iou Rider | Iou Car | Iou Truck | Iou Bus | Iou Caravan | Iou Trailer | Iou Train | Iou Motorcycle | Iou Bicycle | Iou License plate |
128
- |:-------------:|:-------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:--------------------:|:-----------------------------:|:-------------------:|:---------------:|:----------------:|:---------------:|:-------------:|:-----------------:|:----------------:|:-------------------:|:-----------------:|:-------------:|:--------------:|:-------------------:|:---------------:|:---------------:|:-------------:|:------------------:|:----------------------:|:---------------------:|:-------------------:|:----------------:|:------------:|:---------------:|:--------------:|:------------:|:--------------:|:------------:|:----------------:|:----------------:|:--------------:|:-------------------:|:----------------:|:----------------------:|:-------------:|:---------------:|:------------------------:|:--------------:|:----------:|:-----------:|:----------:|:--------:|:------------:|:-----------:|:--------------:|:------------:|:--------:|:---------:|:--------------:|:----------:|:----------:|:--------:|:-------------:|:-----------------:|:----------------:|:--------------:|:-----------:|:-------:|:----------:|:---------:|:-------:|:---------:|:-------:|:-----------:|:-----------:|:---------:|:--------------:|:-----------:|:-----------------:|
129
- | 3.755 | 1.3333 | 100 | 0.9383 | 0.1384 | 0.2588 | 0.8106 | nan | nan | nan | nan | nan | nan | nan | 0.8873 | 0.9424 | nan | nan | 0.8453 | 0.0 | 0.0 | nan | nan | nan | 0.0004 | nan | 0.0 | 0.0000 | 0.9722 | 0.0554 | nan | 0.0 | 0.0 | 0.9558 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.8753 | 0.4899 | nan | nan | 0.7308 | 0.0 | 0.0 | 0.0 | nan | nan | 0.0004 | nan | 0.0 | 0.0000 | 0.7093 | 0.0530 | 0.0 | 0.0 | 0.0 | 0.6013 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan |
130
- | 3.5819 | 2.6667 | 200 | 0.8973 | 0.2347 | 0.2923 | 0.8588 | nan | nan | nan | nan | nan | nan | nan | 0.9702 | 0.8745 | nan | nan | 0.9583 | 0.0 | 0.0 | nan | nan | nan | 0.0119 | nan | 0.0 | 0.0109 | 0.9300 | 0.6001 | nan | 0.0 | 0.0 | 0.9034 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0029 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9339 | 0.6285 | nan | nan | 0.7532 | 0.0 | 0.0 | nan | nan | nan | 0.0108 | nan | 0.0 | 0.0109 | 0.8075 | 0.3047 | nan | 0.0 | 0.0 | 0.7719 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0029 | nan |
131
- | 3.4526 | 4.0 | 300 | 0.8577 | 0.3695 | 0.4670 | 0.8832 | nan | nan | nan | nan | nan | nan | nan | 0.9652 | 0.8320 | nan | nan | 0.9184 | 0.0883 | 0.4000 | nan | nan | nan | 0.4403 | nan | 0.4507 | 0.5527 | 0.9010 | 0.3627 | nan | 0.7381 | 0.0 | 0.9458 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.8118 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9510 | 0.6748 | nan | nan | 0.8033 | 0.0779 | 0.2467 | nan | nan | nan | 0.2748 | nan | 0.2947 | 0.4604 | 0.8320 | 0.2896 | nan | 0.5065 | 0.0 | 0.7999 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.4397 | nan |
132
- | 3.4048 | 5.3333 | 400 | 0.8470 | 0.3974 | 0.5091 | 0.8874 | nan | nan | nan | nan | nan | nan | nan | 0.9705 | 0.8096 | nan | nan | 0.8898 | 0.4703 | 0.4542 | nan | nan | nan | 0.5279 | nan | 0.4516 | 0.6413 | 0.9128 | 0.5371 | nan | 0.7890 | 0.0 | 0.9384 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.7708 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9523 | 0.6657 | nan | nan | 0.8088 | 0.3145 | 0.2499 | nan | nan | nan | 0.3371 | nan | 0.3497 | 0.4649 | 0.8400 | 0.3735 | nan | 0.5543 | 0.0 | 0.8130 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.4291 | nan |
133
- | 3.4212 | 6.6667 | 500 | 0.8482 | 0.3908 | 0.5205 | 0.8840 | nan | nan | nan | nan | nan | nan | nan | 0.9741 | 0.7407 | nan | nan | 0.8888 | 0.4470 | 0.5549 | nan | nan | nan | 0.4040 | nan | 0.5435 | 0.4594 | 0.9137 | 0.7625 | nan | 0.8283 | 0.1594 | 0.9340 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.7588 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9505 | 0.6502 | nan | nan | 0.8098 | 0.2247 | 0.3171 | nan | nan | nan | 0.3191 | nan | 0.3480 | 0.4133 | 0.8343 | 0.3451 | nan | 0.5192 | 0.0594 | 0.8250 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.4180 | nan |
134
- | 3.4114 | 8.0 | 600 | 0.8429 | 0.4058 | 0.5164 | 0.8917 | nan | nan | nan | nan | nan | nan | nan | 0.9759 | 0.7691 | nan | nan | 0.9273 | 0.4184 | 0.3096 | nan | nan | nan | 0.4970 | nan | 0.5734 | 0.5840 | 0.9132 | 0.3975 | nan | 0.7365 | 0.4413 | 0.9502 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0007 | 0.8004 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9561 | 0.6621 | nan | nan | 0.8074 | 0.2969 | 0.2256 | nan | nan | nan | 0.3493 | nan | 0.3593 | 0.4611 | 0.8538 | 0.3394 | nan | 0.5642 | 0.2026 | 0.7968 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0006 | 0.4298 | nan |
135
- | 3.4243 | 9.3333 | 700 | 0.8421 | 0.4113 | 0.5281 | 0.8872 | nan | nan | nan | nan | nan | nan | nan | 0.9733 | 0.8029 | nan | nan | 0.9111 | 0.5037 | 0.1957 | nan | nan | nan | 0.5265 | nan | 0.5456 | 0.6040 | 0.9240 | 0.6433 | nan | 0.5487 | 0.4212 | 0.9263 | 0.0 | 0.0 | nan | nan | 0.0 | 0.1608 | 0.8193 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9529 | 0.6701 | nan | nan | 0.7833 | 0.3549 | 0.1583 | nan | nan | nan | 0.3276 | nan | 0.3272 | 0.4805 | 0.8473 | 0.4463 | nan | 0.4875 | 0.2052 | 0.8465 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0639 | 0.4518 | nan |
136
- | 3.5026 | 10.6667 | 800 | 0.8371 | 0.4297 | 0.5592 | 0.8886 | nan | nan | nan | nan | nan | nan | nan | 0.9847 | 0.6821 | nan | nan | 0.8845 | 0.6906 | 0.5910 | nan | nan | nan | 0.5701 | nan | 0.5295 | 0.7013 | 0.9028 | 0.6018 | nan | 0.7627 | 0.4178 | 0.9476 | 0.0 | 0.0 | nan | nan | 0.0 | 0.1075 | 0.6923 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9475 | 0.6242 | nan | nan | 0.8112 | 0.3530 | 0.3081 | nan | nan | nan | 0.3674 | nan | 0.3744 | 0.4862 | 0.8436 | 0.3914 | nan | 0.5829 | 0.2331 | 0.8193 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0813 | 0.5117 | nan |
137
- | 3.3698 | 12.0 | 900 | 0.8388 | 0.4281 | 0.5317 | 0.8918 | nan | nan | nan | nan | nan | nan | nan | 0.9710 | 0.8288 | nan | nan | 0.9319 | 0.3848 | 0.2834 | nan | nan | nan | 0.5602 | nan | 0.5049 | 0.5811 | 0.9226 | 0.5574 | nan | 0.5867 | 0.4213 | 0.9057 | 0.0 | 0.0 | nan | nan | 0.0 | 0.3658 | 0.7652 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9547 | 0.6691 | nan | nan | 0.8013 | 0.2644 | 0.1957 | nan | nan | nan | 0.3708 | nan | 0.3734 | 0.5156 | 0.8542 | 0.4007 | nan | 0.5186 | 0.2580 | 0.8232 | 0.0 | 0.0 | nan | nan | 0.0 | 0.2199 | 0.4857 | nan |
138
- | 3.3425 | 13.3333 | 1000 | 0.8353 | 0.4426 | 0.5518 | 0.8986 | nan | nan | nan | nan | nan | nan | nan | 0.9770 | 0.8037 | nan | nan | 0.9208 | 0.5682 | 0.2792 | nan | nan | nan | 0.5133 | nan | 0.6080 | 0.6292 | 0.9285 | 0.5659 | nan | 0.7919 | 0.4348 | 0.9467 | 0.0 | 0.0 | nan | nan | 0.0 | 0.2592 | 0.7069 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9583 | 0.6962 | nan | nan | 0.8133 | 0.3545 | 0.2186 | nan | nan | nan | 0.3695 | nan | 0.3731 | 0.5222 | 0.8546 | 0.4323 | nan | 0.5889 | 0.2696 | 0.8218 | 0.0 | 0.0 | nan | nan | 0.0 | 0.1700 | 0.5240 | nan |
139
- | 3.3253 | 14.6667 | 1100 | 0.8351 | 0.4376 | 0.5344 | 0.8979 | nan | nan | nan | nan | nan | nan | nan | 0.9737 | 0.8059 | nan | nan | 0.9410 | 0.4488 | 0.3606 | nan | nan | nan | 0.4856 | nan | 0.4954 | 0.5185 | 0.9169 | 0.6076 | nan | 0.7581 | 0.4803 | 0.9461 | 0.0 | 0.0 | nan | nan | 0.0 | 0.1666 | 0.7133 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9562 | 0.6896 | nan | nan | 0.8131 | 0.2940 | 0.2390 | nan | nan | nan | 0.3655 | nan | 0.3987 | 0.4737 | 0.8582 | 0.4463 | nan | 0.5869 | 0.2675 | 0.8345 | 0.0 | 0.0 | nan | nan | 0.0 | 0.1301 | 0.5234 | nan |
140
- | 3.3526 | 16.0 | 1200 | 0.8346 | 0.4508 | 0.5527 | 0.8999 | nan | nan | nan | nan | nan | nan | nan | 0.9709 | 0.8514 | nan | nan | 0.9254 | 0.5278 | 0.3773 | nan | nan | nan | 0.5083 | nan | 0.5045 | 0.6501 | 0.9353 | 0.5337 | nan | 0.7273 | 0.4569 | 0.9351 | 0.0 | 0.0 | nan | nan | 0.0 | 0.3162 | 0.7286 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9588 | 0.7123 | nan | nan | 0.8150 | 0.3688 | 0.2323 | nan | nan | nan | 0.3742 | nan | 0.4043 | 0.4760 | 0.8550 | 0.4403 | nan | 0.5970 | 0.2986 | 0.8455 | 0.0 | 0.0 | nan | nan | 0.0 | 0.2194 | 0.5161 | nan |
141
- | 3.2327 | 17.3333 | 1300 | 0.8312 | 0.4615 | 0.5690 | 0.9013 | nan | nan | nan | nan | nan | nan | nan | 0.9716 | 0.8332 | nan | nan | 0.9273 | 0.4939 | 0.4670 | nan | nan | nan | 0.5436 | nan | 0.5961 | 0.6227 | 0.9281 | 0.5203 | nan | 0.7661 | 0.4891 | 0.9369 | 0.0 | 0.0 | nan | nan | 0.0 | 0.3647 | 0.7820 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9566 | 0.6925 | nan | nan | 0.8194 | 0.3798 | 0.3265 | nan | nan | nan | 0.3855 | nan | 0.4107 | 0.5344 | 0.8597 | 0.4213 | nan | 0.6009 | 0.3341 | 0.8238 | 0.0 | 0.0 | nan | nan | 0.0 | 0.1902 | 0.5724 | nan |
142
- | 3.3569 | 18.6667 | 1400 | 0.8283 | 0.4645 | 0.5811 | 0.9030 | nan | nan | nan | nan | nan | nan | nan | 0.9805 | 0.7908 | nan | nan | 0.9206 | 0.5556 | 0.4924 | nan | nan | nan | 0.4971 | nan | 0.5337 | 0.6751 | 0.9380 | 0.5081 | nan | 0.7830 | 0.5421 | 0.9372 | 0.0 | 0.0 | nan | nan | 0.0 | 0.5349 | 0.7708 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9570 | 0.7031 | nan | nan | 0.8228 | 0.3598 | 0.2921 | nan | nan | nan | 0.3764 | nan | 0.3991 | 0.5512 | 0.8637 | 0.4058 | nan | 0.6184 | 0.3403 | 0.8567 | 0.0 | 0.0 | nan | nan | 0.0 | 0.2573 | 0.5565 | nan |
143
- | 3.3253 | 20.0 | 1500 | 0.8285 | 0.4600 | 0.5776 | 0.9030 | nan | nan | nan | nan | nan | nan | nan | 0.9750 | 0.8362 | nan | nan | 0.9218 | 0.6299 | 0.4950 | nan | nan | nan | 0.5371 | nan | 0.5943 | 0.6391 | 0.9299 | 0.4728 | nan | 0.7612 | 0.4364 | 0.9424 | 0.0 | 0.0 | nan | nan | 0.0 | 0.4902 | 0.7361 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9586 | 0.6967 | nan | nan | 0.8332 | 0.2604 | 0.3330 | nan | nan | nan | 0.3958 | nan | 0.4305 | 0.5296 | 0.8673 | 0.4065 | nan | 0.6224 | 0.3112 | 0.8505 | 0.0 | 0.0 | nan | nan | 0.0 | 0.2628 | 0.5224 | nan |
144
- | 3.3064 | 21.3333 | 1600 | 0.8287 | 0.4609 | 0.5642 | 0.9008 | nan | nan | nan | nan | nan | nan | nan | 0.9700 | 0.8473 | nan | nan | 0.9367 | 0.4915 | 0.3201 | nan | nan | nan | 0.5431 | nan | 0.6030 | 0.6595 | 0.9239 | 0.5320 | nan | 0.7439 | 0.5000 | 0.9420 | 0.0 | 0.0 | nan | nan | 0.0 | 0.4356 | 0.7062 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9545 | 0.6881 | nan | nan | 0.8120 | 0.3058 | 0.2449 | nan | nan | nan | 0.3861 | nan | 0.4217 | 0.5584 | 0.8659 | 0.4321 | nan | 0.6136 | 0.3377 | 0.8640 | 0.0 | 0.0 | nan | nan | 0.0 | 0.2707 | 0.5405 | nan |
145
- | 3.2969 | 22.6667 | 1700 | 0.8276 | 0.4653 | 0.5739 | 0.9043 | nan | nan | nan | nan | nan | nan | nan | 0.9784 | 0.8177 | nan | nan | 0.9150 | 0.6059 | 0.3958 | nan | nan | nan | 0.5383 | nan | 0.5889 | 0.6500 | 0.9446 | 0.6122 | nan | 0.7898 | 0.4951 | 0.9474 | 0.0 | 0.0 | nan | nan | 0.0 | 0.3429 | 0.7083 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9601 | 0.7197 | nan | nan | 0.8302 | 0.3487 | 0.2649 | nan | nan | nan | 0.3897 | nan | 0.4360 | 0.5635 | 0.8593 | 0.4664 | nan | 0.6143 | 0.3323 | 0.8358 | 0.0 | 0.0 | nan | nan | 0.0 | 0.2319 | 0.5236 | nan |
146
- | 1.2986 | 24.0 | 1800 | 0.3513 | 0.3352 | 0.3800 | 0.8703 | nan | nan | nan | nan | nan | nan | nan | 0.9800 | 0.7257 | nan | nan | 0.9567 | 0.2963 | 0.2305 | nan | nan | nan | 0.1231 | nan | 0.0982 | 0.3188 | 0.9103 | 0.4716 | nan | 0.2967 | 0.0839 | 0.9317 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0179 | 0.3992 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9406 | 0.5970 | nan | nan | 0.7343 | 0.2594 | 0.2069 | nan | nan | nan | 0.1199 | nan | 0.0975 | 0.3111 | 0.8230 | 0.4053 | nan | 0.2862 | 0.0813 | 0.7789 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0168 | 0.3745 | nan |
147
- | 1.3374 | 25.3333 | 1900 | 0.3427 | 0.3055 | 0.3520 | 0.8621 | nan | nan | nan | nan | nan | nan | nan | 0.9777 | 0.7592 | nan | nan | 0.9324 | 0.2561 | 0.2247 | nan | nan | nan | 0.0898 | nan | 0.0463 | 0.2690 | 0.9192 | 0.4020 | nan | 0.2080 | 0.0298 | 0.9191 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.3024 | nan | nan | nan | nan | nan | nan | nan | nan | 0.9348 | 0.5820 | nan | nan | 0.7301 | 0.2279 | 0.2037 | nan | nan | nan | 0.0882 | nan | 0.0462 | 0.2642 | 0.8075 | 0.3523 | nan | 0.2045 | 0.0294 | 0.7382 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.2894 | nan |
148
- | 0.0 | 26.6667 | 2000 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan |
149
- | 0.0 | 28.0 | 2100 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan |
150
- | 0.0 | 29.3333 | 2200 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan |
151
-
152
-
153
- ### Framework versions
154
-
155
- - Transformers 4.47.1
156
- - Pytorch 2.5.1+cu121
157
- - Datasets 3.2.0
158
- - Tokenizers 0.21.0
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: nvidia/segformer-b2-finetuned-cityscapes-1024-1024
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: SegFormer_b2_
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # SegFormer_b2_
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: 1.9394
20
+ - Mean Iou: 0.6247
21
+ - Mean Accuracy: 0.7299
22
+ - Overall Accuracy: 0.9233
23
+ - Accuracy Road: 0.9836
24
+ - Accuracy Sidewalk: 0.8334
25
+ - Accuracy Building: 0.9387
26
+ - Accuracy Wall: 0.5535
27
+ - Accuracy Fence: 0.5674
28
+ - Accuracy Pole: 0.5316
29
+ - Accuracy Traffic light: 0.6698
30
+ - Accuracy Traffic sign: 0.6901
31
+ - Accuracy Vegetation: 0.9239
32
+ - Accuracy Terrain: 0.6285
33
+ - Accuracy Sky: 0.9506
34
+ - Accuracy Person: 0.7416
35
+ - Accuracy Rider: 0.5474
36
+ - Accuracy Car: 0.9271
37
+ - Accuracy Truck: 0.6458
38
+ - Accuracy Bus: 0.7972
39
+ - Accuracy Train: 0.6846
40
+ - Accuracy Motorcycle: 0.5459
41
+ - Accuracy Bicycle: 0.7077
42
+ - Iou Road: 0.9563
43
+ - Iou Sidewalk: 0.7156
44
+ - Iou Building: 0.8667
45
+ - Iou Wall: 0.4851
46
+ - Iou Fence: 0.4486
47
+ - Iou Pole: 0.3497
48
+ - Iou Traffic light: 0.4737
49
+ - Iou Traffic sign: 0.5639
50
+ - Iou Vegetation: 0.8710
51
+ - Iou Terrain: 0.5384
52
+ - Iou Sky: 0.9042
53
+ - Iou Person: 0.5739
54
+ - Iou Rider: 0.3597
55
+ - Iou Car: 0.8723
56
+ - Iou Truck: 0.5765
57
+ - Iou Bus: 0.6862
58
+ - Iou Train: 0.6377
59
+ - Iou Motorcycle: 0.4203
60
+ - Iou Bicycle: 0.5696
61
+
62
+ ## Model description
63
+
64
+ More information needed
65
+
66
+ ## Intended uses & limitations
67
+
68
+ More information needed
69
+
70
+ ## Training and evaluation data
71
+
72
+ More information needed
73
+
74
+ ## Training procedure
75
+
76
+ ### Training hyperparameters
77
+
78
+ The following hyperparameters were used during training:
79
+ - learning_rate: 0.0001
80
+ - train_batch_size: 16
81
+ - eval_batch_size: 16
82
+ - seed: 42
83
+ - gradient_accumulation_steps: 4
84
+ - total_train_batch_size: 64
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: 50
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
+ | 19.4865 | 2.1290 | 100 | 0.6760 | 0.9595 | 0.6477 | 0.9704 | 0.4505 | 0.1910 | 0.7935 | 0.4306 | 0.2263 | 0.9779 | 0.8829 | 0.8935 | 0.6355 | 0.3591 | 0.5761 | 0.4981 | 0.4556 | 0.9358 | 0.4775 | 0.5832 | 0.8589 | 0.6213 | 0.8596 | 0.4151 | 0.1888 | 0.5894 | 0.3086 | 0.2113 | 0.9647 | 0.7523 | 0.8745 | 0.5754 | 0.3375 | 0.5248 | 0.4826 | 0.4506 | 0.8800 | 0.4587 | 3.6075 | 0.6336 | 0.5756 | 0.9251 |
96
+ | 14.9818 | 4.2581 | 200 | 0.7567 | 0.9313 | 0.6464 | 0.9389 | 0.5175 | 0.2690 | 0.7244 | 0.4230 | 0.3868 | 0.9810 | 0.7244 | 0.9358 | 0.5898 | 0.5458 | 0.6784 | 0.3124 | 0.4566 | 0.9169 | 0.4688 | 0.5633 | 0.8534 | 0.6322 | 0.8468 | 0.4453 | 0.2576 | 0.5478 | 0.2504 | 0.3156 | 0.9365 | 0.6019 | 0.8950 | 0.5168 | 0.4225 | 0.4789 | 0.3110 | 0.4531 | 0.8656 | 0.4450 | 2.4551 | 0.6423 | 0.5599 | 0.9085 |
97
+ | 12.8497 | 6.3871 | 300 | 0.7841 | 0.9297 | 0.7192 | 0.9196 | 0.5112 | 0.3392 | 0.7300 | 0.4176 | 0.5774 | 0.9783 | 0.7591 | 0.9284 | 0.6359 | 0.6403 | 0.6451 | 0.4652 | 0.5414 | 0.9207 | 0.5152 | 0.5406 | 0.8545 | 0.6950 | 0.8493 | 0.4189 | 0.3168 | 0.5295 | 0.2799 | 0.3377 | 0.9390 | 0.6199 | 0.8913 | 0.5214 | 0.4012 | 0.5196 | 0.4495 | 0.5292 | 0.8633 | 0.4692 | 2.2342 | 0.6820 | 0.5803 | 0.9102 |
98
+ | 10.1248 | 8.5161 | 400 | 0.6868 | 0.9161 | 0.7117 | 0.9243 | 0.5337 | 0.3373 | 0.7113 | 0.4116 | 0.4864 | 0.9766 | 0.6904 | 0.9158 | 0.6209 | 0.7034 | 0.6768 | 0.2975 | 0.4268 | 0.9234 | 0.4671 | 0.5360 | 0.8470 | 0.6855 | 0.8320 | 0.4207 | 0.2977 | 0.5282 | 0.2729 | 0.3348 | 0.9254 | 0.5580 | 0.8837 | 0.4890 | 0.3556 | 0.5091 | 0.2968 | 0.4231 | 0.8540 | 0.4329 | 2.2664 | 0.6536 | 0.5517 | 0.9015 |
99
+ | 8.1288 | 10.6452 | 500 | 0.7852 | 0.9292 | 0.7670 | 0.9114 | 0.5181 | 0.2987 | 0.6637 | 0.4807 | 0.4590 | 0.9707 | 0.7914 | 0.9271 | 0.6678 | 0.6191 | 0.6648 | 0.5326 | 0.6058 | 0.9192 | 0.4718 | 0.5610 | 0.8523 | 0.7124 | 0.8535 | 0.4347 | 0.2818 | 0.5278 | 0.3054 | 0.3217 | 0.9354 | 0.6086 | 0.8888 | 0.5244 | 0.4309 | 0.5441 | 0.5212 | 0.5776 | 0.8577 | 0.4293 | 2.1501 | 0.6833 | 0.5878 | 0.9085 |
100
+ | 8.3238 | 12.7742 | 600 | 0.7818 | 0.9235 | 0.7698 | 0.9120 | 0.5285 | 0.4973 | 0.7194 | 0.4843 | 0.5705 | 0.9766 | 0.8115 | 0.9576 | 0.6124 | 0.6642 | 0.6829 | 0.5547 | 0.5998 | 0.9153 | 0.5458 | 0.5611 | 0.8558 | 0.7056 | 0.8627 | 0.4342 | 0.3823 | 0.5099 | 0.3111 | 0.3336 | 0.9433 | 0.6461 | 0.8838 | 0.5145 | 0.4324 | 0.5324 | 0.5270 | 0.5528 | 0.8631 | 0.4859 | 2.1170 | 0.7109 | 0.5967 | 0.9125 |
101
+ | 8.9039 | 14.9032 | 700 | 0.7615 | 0.9340 | 0.7759 | 0.9214 | 0.5726 | 0.4982 | 0.6710 | 0.4779 | 0.5724 | 0.9794 | 0.7971 | 0.9481 | 0.6864 | 0.6014 | 0.6676 | 0.4047 | 0.5534 | 0.9095 | 0.5584 | 0.5569 | 0.8570 | 0.7187 | 0.8624 | 0.4536 | 0.3817 | 0.5312 | 0.3190 | 0.3369 | 0.9449 | 0.6444 | 0.8945 | 0.5294 | 0.4543 | 0.5439 | 0.4023 | 0.5256 | 0.8613 | 0.4829 | 2.0632 | 0.6995 | 0.5948 | 0.9140 |
102
+ | 6.8474 | 17.0215 | 800 | 0.7639 | 0.9241 | 0.7635 | 0.9098 | 0.6152 | 0.4688 | 0.6985 | 0.4950 | 0.5632 | 0.9788 | 0.8365 | 0.9374 | 0.6416 | 0.6235 | 0.6679 | 0.6057 | 0.5879 | 0.9304 | 0.6211 | 0.5415 | 0.8613 | 0.7171 | 0.8582 | 0.4533 | 0.3791 | 0.5266 | 0.3222 | 0.3344 | 0.9510 | 0.6856 | 0.8965 | 0.5284 | 0.4566 | 0.5588 | 0.5792 | 0.5514 | 0.8670 | 0.5213 | 2.0679 | 0.7175 | 0.6100 | 0.9176 |
103
+ | 7.4347 | 19.5376 | 900 | 0.7122 | 0.9277 | 0.7490 | 0.9283 | 0.5929 | 0.3980 | 0.7050 | 0.5311 | 0.7026 | 0.9793 | 0.8403 | 0.9349 | 0.6278 | 0.6670 | 0.7038 | 0.6460 | 0.5609 | 0.9171 | 0.5750 | 0.5373 | 0.8599 | 0.7067 | 0.8658 | 0.4666 | 0.3392 | 0.5207 | 0.3327 | 0.3307 | 0.9518 | 0.6903 | 0.8948 | 0.5374 | 0.4542 | 0.5535 | 0.6120 | 0.5235 | 0.8669 | 0.5069 | 2.0968 | 0.7210 | 0.6079 | 0.9177 |
104
+ | 7.5228 | 21.6667 | 1000 | 0.6753 | 0.9294 | 0.8054 | 0.9299 | 0.5103 | 0.5224 | 0.7150 | 0.5414 | 0.5393 | 0.9822 | 0.8177 | 0.9422 | 0.6357 | 0.6628 | 0.7064 | 0.6089 | 0.6381 | 0.9243 | 0.6196 | 0.5381 | 0.8616 | 0.7231 | 0.8662 | 0.4515 | 0.4082 | 0.5591 | 0.3312 | 0.3474 | 0.9518 | 0.6919 | 0.8971 | 0.5222 | 0.4581 | 0.5556 | 0.5864 | 0.5795 | 0.8689 | 0.5222 | 2.0338 | 0.7214 | 0.6168 | 0.9194 |
105
+ | 6.7143 | 23.7957 | 1100 | 0.7380 | 0.9360 | 0.8039 | 0.9211 | 0.6212 | 0.5869 | 0.7588 | 0.5156 | 0.5796 | 0.9811 | 0.8255 | 0.9444 | 0.6144 | 0.6595 | 0.6831 | 0.6266 | 0.6627 | 0.9084 | 0.6149 | 0.5441 | 0.8623 | 0.7019 | 0.8666 | 0.4182 | 0.4132 | 0.5791 | 0.3375 | 0.3562 | 0.9533 | 0.6969 | 0.8952 | 0.5126 | 0.4605 | 0.5551 | 0.5989 | 0.5738 | 0.8642 | 0.5203 | 2.1118 | 0.7359 | 0.6163 | 0.9190 |
106
+ | 7.5104 | 25.9247 | 1200 | 0.6948 | 0.9288 | 0.8005 | 0.9219 | 0.6146 | 0.4523 | 0.7635 | 0.5523 | 0.5294 | 0.9805 | 0.8326 | 0.9384 | 0.6626 | 0.6950 | 0.6912 | 0.6974 | 0.5996 | 0.9226 | 0.5694 | 0.5740 | 0.8618 | 0.6997 | 0.8695 | 0.4462 | 0.3672 | 0.5465 | 0.3416 | 0.3485 | 0.9542 | 0.7017 | 0.8994 | 0.5250 | 0.4618 | 0.5565 | 0.6384 | 0.5587 | 0.8707 | 0.5081 | 2.0335 | 0.7288 | 0.6173 | 0.9200 |
107
+ | 7.861 | 28.0430 | 1300 | 0.7469 | 0.9369 | 0.8086 | 0.9207 | 0.5746 | 0.5260 | 0.7496 | 0.5465 | 0.5180 | 0.9818 | 0.8352 | 0.9433 | 0.6926 | 0.6455 | 0.7201 | 0.6200 | 0.6283 | 0.9077 | 0.6043 | 0.5726 | 0.8610 | 0.6940 | 0.8701 | 0.4558 | 0.4178 | 0.5486 | 0.3437 | 0.3578 | 0.9554 | 0.7092 | 0.8990 | 0.5346 | 0.4603 | 0.5598 | 0.5936 | 0.5681 | 0.8657 | 0.5123 | 2.0020 | 0.7319 | 0.6200 | 0.9204 |
108
+ | 7.0394 | 30.1720 | 1400 | 0.6941 | 0.9330 | 0.8556 | 0.9345 | 0.5390 | 0.4986 | 0.7452 | 0.5509 | 0.5745 | 0.9800 | 0.8528 | 0.9552 | 0.6988 | 0.7051 | 0.6983 | 0.6298 | 0.6150 | 0.9283 | 0.5627 | 0.5736 | 0.8676 | 0.7108 | 0.8749 | 0.4634 | 0.4036 | 0.5609 | 0.3516 | 0.3656 | 0.9579 | 0.7202 | 0.9034 | 0.5488 | 0.4546 | 0.5710 | 0.6060 | 0.5695 | 0.8737 | 0.5042 | 2.0133 | 0.7343 | 0.6253 | 0.9240 |
109
+ | 6.8533 | 32.3011 | 1500 | 0.7715 | 0.9388 | 0.7811 | 0.9163 | 0.5650 | 0.4690 | 0.7304 | 0.5132 | 0.5895 | 0.9831 | 0.8465 | 0.9467 | 0.6617 | 0.6596 | 0.6647 | 0.6119 | 0.6297 | 0.9265 | 0.5474 | 0.5743 | 0.8661 | 0.7119 | 0.8702 | 0.4352 | 0.3808 | 0.5582 | 0.3447 | 0.3609 | 0.9577 | 0.7217 | 0.9050 | 0.5461 | 0.4737 | 0.5609 | 0.5972 | 0.5612 | 0.8724 | 0.48 | 2.0117 | 0.7238 | 0.6199 | 0.9233 |
110
+ | 7.2427 | 34.4301 | 1600 | 0.7191 | 0.9364 | 0.7781 | 0.9209 | 0.5210 | 0.4928 | 0.7391 | 0.5203 | 0.6457 | 0.9820 | 0.8448 | 0.9487 | 0.6476 | 0.6672 | 0.6934 | 0.6828 | 0.6149 | 0.9215 | 0.6113 | 0.5561 | 0.8643 | 0.7053 | 0.8697 | 0.4414 | 0.3841 | 0.5563 | 0.3425 | 0.3524 | 0.9558 | 0.7124 | 0.9030 | 0.5375 | 0.4699 | 0.5551 | 0.6438 | 0.5513 | 0.8710 | 0.5214 | 1.9949 | 0.7309 | 0.6207 | 0.9220 |
111
+ | 6.7778 | 36.5591 | 1700 | 0.7269 | 0.9389 | 0.8062 | 0.9264 | 0.5671 | 0.4382 | 0.7281 | 0.5163 | 0.5285 | 0.9824 | 0.8465 | 0.9505 | 0.6464 | 0.6739 | 0.6610 | 0.6729 | 0.6407 | 0.9316 | 0.5398 | 0.5776 | 0.8677 | 0.7070 | 0.8728 | 0.4520 | 0.3677 | 0.5765 | 0.3456 | 0.3626 | 0.9570 | 0.7182 | 0.9069 | 0.5520 | 0.4582 | 0.5598 | 0.6331 | 0.5808 | 0.8740 | 0.4879 | 1.9785 | 0.7222 | 0.6241 | 0.9243 |
112
+ | 6.5763 | 38.6882 | 1800 | 0.7485 | 0.9385 | 0.7854 | 0.9264 | 0.6005 | 0.4531 | 0.7187 | 0.5171 | 0.5683 | 0.9817 | 0.8446 | 0.9419 | 0.6652 | 0.6515 | 0.6864 | 0.6653 | 0.6521 | 0.9286 | 0.5884 | 0.5713 | 0.8662 | 0.6953 | 0.8732 | 0.4482 | 0.3809 | 0.5727 | 0.3480 | 0.3725 | 0.9580 | 0.7212 | 0.9040 | 0.5537 | 0.4705 | 0.5706 | 0.6333 | 0.5789 | 0.8723 | 0.5145 | 1.9691 | 0.7296 | 0.6266 | 0.9240 |
113
+ | 6.5878 | 40.8172 | 1900 | 0.7381 | 0.9350 | 0.7873 | 0.9238 | 0.5780 | 0.5450 | 0.7328 | 0.5148 | 0.5550 | 0.9835 | 0.8388 | 0.9479 | 0.6593 | 0.6625 | 0.6837 | 0.6830 | 0.6526 | 0.9247 | 0.5516 | 0.5734 | 0.8657 | 0.6889 | 0.8721 | 0.4468 | 0.4075 | 0.5674 | 0.3451 | 0.3605 | 0.9563 | 0.7123 | 0.9014 | 0.5452 | 0.4680 | 0.5641 | 0.6428 | 0.5564 | 0.8702 | 0.4884 | 1.9603 | 0.7315 | 0.6228 | 0.9227 |
114
+ | 6.2246 | 42.9462 | 2000 | 0.6965 | 0.9435 | 0.7914 | 0.9296 | 0.5240 | 0.5602 | 0.7195 | 0.5298 | 0.5844 | 0.9834 | 0.8383 | 0.9389 | 0.6232 | 0.6611 | 0.6819 | 0.6379 | 0.6310 | 0.9229 | 0.5725 | 0.5719 | 0.8653 | 0.6732 | 0.8720 | 0.4420 | 0.4200 | 0.5698 | 0.3492 | 0.3700 | 0.9570 | 0.7176 | 0.9014 | 0.5463 | 0.4744 | 0.5614 | 0.6100 | 0.5576 | 0.8706 | 0.4980 | 1.9342 | 0.7247 | 0.6225 | 0.9234 |
115
+ | 7.4045 | 45.0645 | 2100 | 0.7076 | 0.9380 | 0.8054 | 0.9286 | 0.5505 | 0.4858 | 0.7431 | 0.5202 | 0.5815 | 0.9837 | 0.8338 | 0.9423 | 0.6323 | 0.6712 | 0.6895 | 0.6615 | 0.6309 | 0.9318 | 0.5456 | 0.5740 | 0.8682 | 0.6932 | 0.8736 | 0.4476 | 0.3952 | 0.5701 | 0.3504 | 0.3631 | 0.9568 | 0.7172 | 0.9038 | 0.5471 | 0.4733 | 0.5649 | 0.6260 | 0.5743 | 0.8724 | 0.4843 | 1.9209 | 0.7254 | 0.6240 | 0.9240 |
116
+ | 6.6521 | 47.1935 | 2200 | 0.7241 | 0.9349 | 0.7896 | 0.9258 | 0.5411 | 0.5575 | 0.7431 | 0.5364 | 0.5836 | 0.9841 | 0.8297 | 0.9467 | 0.6298 | 0.6757 | 0.6985 | 0.6633 | 0.6485 | 0.9278 | 0.5435 | 0.5685 | 0.8664 | 0.6826 | 0.8722 | 0.4472 | 0.4163 | 0.5700 | 0.3488 | 0.3622 | 0.9558 | 0.7126 | 0.9040 | 0.5401 | 0.4692 | 0.5633 | 0.6280 | 0.5708 | 0.8716 | 0.4826 | 1.9400 | 0.7307 | 0.6228 | 0.9229 |
117
+ | 6.383 | 49.9677 | 2300 | 1.9394 | 0.6247 | 0.7299 | 0.9233 | 0.9836 | 0.8334 | 0.9387 | 0.5535 | 0.5674 | 0.5316 | 0.6698 | 0.6901 | 0.9239 | 0.6285 | 0.9506 | 0.7416 | 0.5474 | 0.9271 | 0.6458 | 0.7972 | 0.6846 | 0.5459 | 0.7077 | 0.9563 | 0.7156 | 0.8667 | 0.4851 | 0.4486 | 0.3497 | 0.4737 | 0.5639 | 0.8710 | 0.5384 | 0.9042 | 0.5739 | 0.3597 | 0.8723 | 0.5765 | 0.6862 | 0.6377 | 0.4203 | 0.5696 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.47.1
123
+ - Pytorch 2.1.2+cu121
124
+ - Datasets 3.2.0
125
+ - Tokenizers 0.21.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,144 +1,112 @@
1
- {
2
- "_name_or_path": "nvidia/segformer-b2-finetuned-cityscapes-1024-1024",
3
- "architectures": [
4
- "SegformerForSemanticSegmentation"
5
- ],
6
- "attention_probs_dropout_prob": 0.0,
7
- "classifier_dropout_prob": 0.1,
8
- "decoder_hidden_size": 768,
9
- "depths": [
10
- 3,
11
- 4,
12
- 6,
13
- 3
14
- ],
15
- "downsampling_rates": [
16
- 1,
17
- 4,
18
- 8,
19
- 16
20
- ],
21
- "drop_path_rate": 0.1,
22
- "hidden_act": "gelu",
23
- "hidden_dropout_prob": 0.0,
24
- "hidden_sizes": [
25
- 64,
26
- 128,
27
- 320,
28
- 512
29
- ],
30
- "id2label": {
31
- "0": "unlabeled",
32
- "1": "ego vehicle",
33
- "2": "rectification border",
34
- "3": "out of roi",
35
- "4": "static",
36
- "5": "dynamic",
37
- "6": "ground",
38
- "7": "road",
39
- "8": "sidewalk",
40
- "9": "parking",
41
- "10": "rail track",
42
- "11": "building",
43
- "12": "wall",
44
- "13": "fence",
45
- "14": "guard rail",
46
- "15": "bridge",
47
- "16": "tunnel",
48
- "17": "pole",
49
- "18": "polegroup",
50
- "19": "traffic light",
51
- "20": "traffic sign",
52
- "21": "vegetation",
53
- "22": "terrain",
54
- "23": "sky",
55
- "24": "person",
56
- "25": "rider",
57
- "26": "car",
58
- "27": "truck",
59
- "28": "bus",
60
- "29": "caravan",
61
- "30": "trailer",
62
- "31": "train",
63
- "32": "motorcycle",
64
- "33": "bicycle",
65
- "34": "license plate"
66
- },
67
- "image_size": 224,
68
- "initializer_range": 0.02,
69
- "label2id": {
70
- "bicycle": 33,
71
- "bridge": 15,
72
- "building": 11,
73
- "bus": 28,
74
- "car": 26,
75
- "caravan": 29,
76
- "dynamic": 5,
77
- "ego vehicle": 1,
78
- "fence": 13,
79
- "ground": 6,
80
- "guard rail": 14,
81
- "license plate": 34,
82
- "motorcycle": 32,
83
- "out of roi": 3,
84
- "parking": 9,
85
- "person": 24,
86
- "pole": 17,
87
- "polegroup": 18,
88
- "rail track": 10,
89
- "rectification border": 2,
90
- "rider": 25,
91
- "road": 7,
92
- "sidewalk": 8,
93
- "sky": 23,
94
- "static": 4,
95
- "terrain": 22,
96
- "traffic light": 19,
97
- "traffic sign": 20,
98
- "trailer": 30,
99
- "train": 31,
100
- "truck": 27,
101
- "tunnel": 16,
102
- "unlabeled": 0,
103
- "vegetation": 21,
104
- "wall": 12
105
- },
106
- "layer_norm_eps": 1e-06,
107
- "mlp_ratios": [
108
- 4,
109
- 4,
110
- 4,
111
- 4
112
- ],
113
- "model_type": "segformer",
114
- "num_attention_heads": [
115
- 1,
116
- 2,
117
- 5,
118
- 8
119
- ],
120
- "num_channels": 3,
121
- "num_encoder_blocks": 4,
122
- "patch_sizes": [
123
- 7,
124
- 3,
125
- 3,
126
- 3
127
- ],
128
- "reshape_last_stage": true,
129
- "semantic_loss_ignore_index": 255,
130
- "sr_ratios": [
131
- 8,
132
- 4,
133
- 2,
134
- 1
135
- ],
136
- "strides": [
137
- 4,
138
- 2,
139
- 2,
140
- 2
141
- ],
142
- "torch_dtype": "float32",
143
- "transformers_version": "4.47.1"
144
- }
 
1
+ {
2
+ "_name_or_path": "nvidia/segformer-b2-finetuned-cityscapes-1024-1024",
3
+ "architectures": [
4
+ "SegformerForSemanticSegmentation"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout_prob": 0.1,
8
+ "decoder_hidden_size": 768,
9
+ "depths": [
10
+ 3,
11
+ 4,
12
+ 6,
13
+ 3
14
+ ],
15
+ "downsampling_rates": [
16
+ 1,
17
+ 4,
18
+ 8,
19
+ 16
20
+ ],
21
+ "drop_path_rate": 0.1,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.0,
24
+ "hidden_sizes": [
25
+ 64,
26
+ 128,
27
+ 320,
28
+ 512
29
+ ],
30
+ "id2label": {
31
+ "0": "road",
32
+ "1": "sidewalk",
33
+ "2": "building",
34
+ "3": "wall",
35
+ "4": "fence",
36
+ "5": "pole",
37
+ "6": "traffic light",
38
+ "7": "traffic sign",
39
+ "8": "vegetation",
40
+ "9": "terrain",
41
+ "10": "sky",
42
+ "11": "person",
43
+ "12": "rider",
44
+ "13": "car",
45
+ "14": "truck",
46
+ "15": "bus",
47
+ "16": "train",
48
+ "17": "motorcycle",
49
+ "18": "bicycle"
50
+ },
51
+ "image_size": 224,
52
+ "initializer_range": 0.02,
53
+ "label2id": {
54
+ "bicycle": 18,
55
+ "building": 2,
56
+ "bus": 15,
57
+ "car": 13,
58
+ "fence": 4,
59
+ "motorcycle": 17,
60
+ "person": 11,
61
+ "pole": 5,
62
+ "rider": 12,
63
+ "road": 0,
64
+ "sidewalk": 1,
65
+ "sky": 10,
66
+ "terrain": 9,
67
+ "traffic light": 6,
68
+ "traffic sign": 7,
69
+ "train": 16,
70
+ "truck": 14,
71
+ "vegetation": 8,
72
+ "wall": 3
73
+ },
74
+ "layer_norm_eps": 1e-06,
75
+ "mlp_ratios": [
76
+ 4,
77
+ 4,
78
+ 4,
79
+ 4
80
+ ],
81
+ "model_type": "segformer",
82
+ "num_attention_heads": [
83
+ 1,
84
+ 2,
85
+ 5,
86
+ 8
87
+ ],
88
+ "num_channels": 3,
89
+ "num_encoder_blocks": 4,
90
+ "patch_sizes": [
91
+ 7,
92
+ 3,
93
+ 3,
94
+ 3
95
+ ],
96
+ "reshape_last_stage": true,
97
+ "semantic_loss_ignore_index": 255,
98
+ "sr_ratios": [
99
+ 8,
100
+ 4,
101
+ 2,
102
+ 1
103
+ ],
104
+ "strides": [
105
+ 4,
106
+ 2,
107
+ 2,
108
+ 2
109
+ ],
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.47.1"
112
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f56ce59e0768b30e8450e5ffa84c0a120cd117fb9ee55a5ab900c9998c77831
3
- size 109545532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eac781c2102d64f3ed8ebcfd80a47b03d5e5d671a0caa193da495ce267c4846
3
+ size 109496316
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28ef6edbccf7186726d6b941b60875f1273fd622605b47b93a0101febe01ebd8
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e06dbc447fa2f9f0b13ad506d6608c93cec2297bec3f8aaf1c7d44bdbfe269
3
  size 5368