Hugging Face's logo

lalla123
/
mit-b0-finetuned-sidewalks

Transformers
TensorFlow
segformer
generated_from_keras_callback
Inference Endpoints
Model card Files Community
lalla123 commited on
Commit
f69be88
•
1 Parent(s): 908bde2

Training in progress epoch 4

Browse files
Files changed (2) hide show
  1. README.md +46 -44
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  base_model: nvidia/mit-b0
3
  tags:
4
  - generated_from_keras_callback
@@ -14,82 +15,82 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 1.3795
18
- - Validation Loss: 1.2564
19
- - Validation Mean Iou: 0.1365
20
- - Validation Mean Accuracy: 0.1987
21
- - Validation Overall Accuracy: 0.7068
22
  - Validation Accuracy Unlabeled: 0.0
23
- - Validation Accuracy Flat-road: 0.7505
24
- - Validation Accuracy Flat-sidewalk: 0.9141
25
- - Validation Accuracy Flat-crosswalk: 0.0000
26
- - Validation Accuracy Flat-cyclinglane: 0.4222
27
- - Validation Accuracy Flat-parkingdriveway: 0.0106
28
  - Validation Accuracy Flat-railtrack: nan
29
- - Validation Accuracy Flat-curb: 0.0001
30
- - Validation Accuracy Human-person: 0.0031
31
  - Validation Accuracy Human-rider: 0.0
32
- - Validation Accuracy Vehicle-car: 0.8707
33
  - Validation Accuracy Vehicle-truck: 0.0
34
  - Validation Accuracy Vehicle-bus: 0.0
35
  - Validation Accuracy Vehicle-tramtrain: nan
36
  - Validation Accuracy Vehicle-motorcycle: 0.0
37
- - Validation Accuracy Vehicle-bicycle: 0.0642
38
  - Validation Accuracy Vehicle-caravan: 0.0
39
  - Validation Accuracy Vehicle-cartrailer: 0.0
40
- - Validation Accuracy Construction-building: 0.8057
41
- - Validation Accuracy Construction-door: 0.0003
42
- - Validation Accuracy Construction-wall: 0.0290
43
- - Validation Accuracy Construction-fenceguardrail: 0.0011
44
  - Validation Accuracy Construction-bridge: 0.0
45
  - Validation Accuracy Construction-tunnel: nan
46
  - Validation Accuracy Construction-stairs: 0.0
47
- - Validation Accuracy Object-pole: 0.0027
48
  - Validation Accuracy Object-trafficsign: 0.0
49
  - Validation Accuracy Object-trafficlight: 0.0
50
- - Validation Accuracy Nature-vegetation: 0.8671
51
- - Validation Accuracy Nature-terrain: 0.6862
52
- - Validation Accuracy Sky: 0.9098
53
- - Validation Accuracy Void-ground: 0.0002
54
  - Validation Accuracy Void-dynamic: 0.0
55
- - Validation Accuracy Void-static: 0.0217
56
  - Validation Accuracy Void-unclear: 0.0
57
  - Validation Iou Unlabeled: 0.0
58
- - Validation Iou Flat-road: 0.5495
59
- - Validation Iou Flat-sidewalk: 0.6821
60
- - Validation Iou Flat-crosswalk: 0.0000
61
  - Validation Iou Flat-cyclinglane: 0.3661
62
- - Validation Iou Flat-parkingdriveway: 0.0102
63
- - Validation Iou Flat-railtrack: 0.0
64
- - Validation Iou Flat-curb: 0.0001
65
- - Validation Iou Human-person: 0.0031
66
  - Validation Iou Human-rider: 0.0
67
- - Validation Iou Vehicle-car: 0.6154
68
  - Validation Iou Vehicle-truck: 0.0
69
  - Validation Iou Vehicle-bus: 0.0
70
  - Validation Iou Vehicle-tramtrain: 0.0
71
  - Validation Iou Vehicle-motorcycle: 0.0
72
- - Validation Iou Vehicle-bicycle: 0.0327
73
  - Validation Iou Vehicle-caravan: 0.0
74
  - Validation Iou Vehicle-cartrailer: 0.0
75
- - Validation Iou Construction-building: 0.4963
76
- - Validation Iou Construction-door: 0.0003
77
- - Validation Iou Construction-wall: 0.0267
78
- - Validation Iou Construction-fenceguardrail: 0.0011
79
  - Validation Iou Construction-bridge: 0.0
80
  - Validation Iou Construction-tunnel: 0.0
81
  - Validation Iou Construction-stairs: 0.0
82
- - Validation Iou Object-pole: 0.0026
83
  - Validation Iou Object-trafficsign: 0.0
84
  - Validation Iou Object-trafficlight: 0.0
85
- - Validation Iou Nature-vegetation: 0.7200
86
- - Validation Iou Nature-terrain: 0.4961
87
- - Validation Iou Sky: 0.7580
88
- - Validation Iou Void-ground: 0.0002
89
  - Validation Iou Void-dynamic: 0.0
90
- - Validation Iou Void-static: 0.0177
91
  - Validation Iou Void-unclear: 0.0
92
- - Epoch: 3
93
 
94
  ## Model description
95
 
@@ -119,6 +120,7 @@ The following hyperparameters were used during training:
119
  | 2.0643 | 1.6749 | 0.1030 | 0.1583 | 0.6241 | 0.0 | 0.5562 | 0.8974 | 0.0000 | 0.0126 | 0.0053 | nan | 0.0001 | 0.0002 | 0.0 | 0.8013 | 0.0 | 0.0 | nan | 0.0 | 0.0928 | 0.0 | 0.0 | 0.7299 | 0.0000 | 0.0023 | 0.0522 | 0.0 | nan | 0.0137 | 0.0006 | 0.0 | 0.0 | 0.9393 | 0.1737 | 0.7552 | 0.0105 | 0.0001 | 0.0214 | 0.0 | 0.0 | 0.4201 | 0.5989 | 0.0000 | 0.0125 | 0.0052 | 0.0 | 0.0001 | 0.0002 | 0.0 | 0.5466 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0256 | 0.0 | 0.0 | 0.4609 | 0.0000 | 0.0022 | 0.0450 | 0.0 | 0.0 | 0.0022 | 0.0006 | 0.0 | 0.0 | 0.6592 | 0.1499 | 0.6526 | 0.0060 | 0.0001 | 0.0171 | 0.0 | 1 |
120
  | 1.7439 | 1.4214 | 0.1264 | 0.1860 | 0.6745 | 0.0 | 0.8063 | 0.8609 | 0.0 | 0.1874 | 0.0075 | nan | 0.0000 | 0.0008 | 0.0 | 0.8652 | 0.0 | 0.0 | nan | 0.0 | 0.1508 | 0.0 | 0.0 | 0.7206 | 0.0008 | 0.0019 | 0.0062 | 0.0 | nan | 0.0282 | 0.0022 | 0.0 | 0.0 | 0.9237 | 0.4783 | 0.8933 | 0.0006 | 0.0 | 0.0170 | 0.0 | 0.0 | 0.4746 | 0.6616 | 0.0 | 0.1848 | 0.0073 | nan | 0.0000 | 0.0008 | 0.0 | 0.5882 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0407 | 0.0 | 0.0 | 0.4779 | 0.0006 | 0.0019 | 0.0060 | 0.0 | 0.0 | 0.0056 | 0.0021 | 0.0 | 0.0 | 0.7045 | 0.3983 | 0.7282 | 0.0006 | 0.0 | 0.0150 | 0.0 | 2 |
121
  | 1.3795 | 1.2564 | 0.1365 | 0.1987 | 0.7068 | 0.0 | 0.7505 | 0.9141 | 0.0000 | 0.4222 | 0.0106 | nan | 0.0001 | 0.0031 | 0.0 | 0.8707 | 0.0 | 0.0 | nan | 0.0 | 0.0642 | 0.0 | 0.0 | 0.8057 | 0.0003 | 0.0290 | 0.0011 | 0.0 | nan | 0.0 | 0.0027 | 0.0 | 0.0 | 0.8671 | 0.6862 | 0.9098 | 0.0002 | 0.0 | 0.0217 | 0.0 | 0.0 | 0.5495 | 0.6821 | 0.0000 | 0.3661 | 0.0102 | 0.0 | 0.0001 | 0.0031 | 0.0 | 0.6154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0327 | 0.0 | 0.0 | 0.4963 | 0.0003 | 0.0267 | 0.0011 | 0.0 | 0.0 | 0.0 | 0.0026 | 0.0 | 0.0 | 0.7200 | 0.4961 | 0.7580 | 0.0002 | 0.0 | 0.0177 | 0.0 | 3 |
 
122
 
123
 
124
  ### Framework versions
 
1
  ---
2
+ license: other
3
  base_model: nvidia/mit-b0
4
  tags:
5
  - generated_from_keras_callback
 
15
 
16
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.3346
19
+ - Validation Loss: 1.1664
20
+ - Validation Mean Iou: 0.1412
21
+ - Validation Mean Accuracy: 0.1958
22
+ - Validation Overall Accuracy: 0.7144
23
  - Validation Accuracy Unlabeled: 0.0
24
+ - Validation Accuracy Flat-road: 0.8177
25
+ - Validation Accuracy Flat-sidewalk: 0.8998
26
+ - Validation Accuracy Flat-crosswalk: 0.0009
27
+ - Validation Accuracy Flat-cyclinglane: 0.4161
28
+ - Validation Accuracy Flat-parkingdriveway: 0.0254
29
  - Validation Accuracy Flat-railtrack: nan
30
+ - Validation Accuracy Flat-curb: 0.0
31
+ - Validation Accuracy Human-person: 0.0159
32
  - Validation Accuracy Human-rider: 0.0
33
+ - Validation Accuracy Vehicle-car: 0.8980
34
  - Validation Accuracy Vehicle-truck: 0.0
35
  - Validation Accuracy Vehicle-bus: 0.0
36
  - Validation Accuracy Vehicle-tramtrain: nan
37
  - Validation Accuracy Vehicle-motorcycle: 0.0
38
+ - Validation Accuracy Vehicle-bicycle: 0.0094
39
  - Validation Accuracy Vehicle-caravan: 0.0
40
  - Validation Accuracy Vehicle-cartrailer: 0.0
41
+ - Validation Accuracy Construction-building: 0.8424
42
+ - Validation Accuracy Construction-door: 0.0
43
+ - Validation Accuracy Construction-wall: 0.0179
44
+ - Validation Accuracy Construction-fenceguardrail: 0.0007
45
  - Validation Accuracy Construction-bridge: 0.0
46
  - Validation Accuracy Construction-tunnel: nan
47
  - Validation Accuracy Construction-stairs: 0.0
48
+ - Validation Accuracy Object-pole: 0.0039
49
  - Validation Accuracy Object-trafficsign: 0.0
50
  - Validation Accuracy Object-trafficlight: 0.0
51
+ - Validation Accuracy Nature-vegetation: 0.9113
52
+ - Validation Accuracy Nature-terrain: 0.5713
53
+ - Validation Accuracy Sky: 0.8346
54
+ - Validation Accuracy Void-ground: 0.0
55
  - Validation Accuracy Void-dynamic: 0.0
56
+ - Validation Accuracy Void-static: 0.0017
57
  - Validation Accuracy Void-unclear: 0.0
58
  - Validation Iou Unlabeled: 0.0
59
+ - Validation Iou Flat-road: 0.5710
60
+ - Validation Iou Flat-sidewalk: 0.6881
61
+ - Validation Iou Flat-crosswalk: 0.0009
62
  - Validation Iou Flat-cyclinglane: 0.3661
63
+ - Validation Iou Flat-parkingdriveway: 0.0228
64
+ - Validation Iou Flat-railtrack: nan
65
+ - Validation Iou Flat-curb: 0.0
66
+ - Validation Iou Human-person: 0.0155
67
  - Validation Iou Human-rider: 0.0
68
+ - Validation Iou Vehicle-car: 0.6173
69
  - Validation Iou Vehicle-truck: 0.0
70
  - Validation Iou Vehicle-bus: 0.0
71
  - Validation Iou Vehicle-tramtrain: 0.0
72
  - Validation Iou Vehicle-motorcycle: 0.0
73
+ - Validation Iou Vehicle-bicycle: 0.0082
74
  - Validation Iou Vehicle-caravan: 0.0
75
  - Validation Iou Vehicle-cartrailer: 0.0
76
+ - Validation Iou Construction-building: 0.5245
77
+ - Validation Iou Construction-door: 0.0
78
+ - Validation Iou Construction-wall: 0.0173
79
+ - Validation Iou Construction-fenceguardrail: 0.0007
80
  - Validation Iou Construction-bridge: 0.0
81
  - Validation Iou Construction-tunnel: 0.0
82
  - Validation Iou Construction-stairs: 0.0
83
+ - Validation Iou Object-pole: 0.0036
84
  - Validation Iou Object-trafficsign: 0.0
85
  - Validation Iou Object-trafficlight: 0.0
86
+ - Validation Iou Nature-vegetation: 0.7286
87
+ - Validation Iou Nature-terrain: 0.4534
88
+ - Validation Iou Sky: 0.7817
89
+ - Validation Iou Void-ground: 0.0
90
  - Validation Iou Void-dynamic: 0.0
91
+ - Validation Iou Void-static: 0.0016
92
  - Validation Iou Void-unclear: 0.0
93
+ - Epoch: 4
94
 
95
  ## Model description
96
 
 
120
  | 2.0643 | 1.6749 | 0.1030 | 0.1583 | 0.6241 | 0.0 | 0.5562 | 0.8974 | 0.0000 | 0.0126 | 0.0053 | nan | 0.0001 | 0.0002 | 0.0 | 0.8013 | 0.0 | 0.0 | nan | 0.0 | 0.0928 | 0.0 | 0.0 | 0.7299 | 0.0000 | 0.0023 | 0.0522 | 0.0 | nan | 0.0137 | 0.0006 | 0.0 | 0.0 | 0.9393 | 0.1737 | 0.7552 | 0.0105 | 0.0001 | 0.0214 | 0.0 | 0.0 | 0.4201 | 0.5989 | 0.0000 | 0.0125 | 0.0052 | 0.0 | 0.0001 | 0.0002 | 0.0 | 0.5466 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0256 | 0.0 | 0.0 | 0.4609 | 0.0000 | 0.0022 | 0.0450 | 0.0 | 0.0 | 0.0022 | 0.0006 | 0.0 | 0.0 | 0.6592 | 0.1499 | 0.6526 | 0.0060 | 0.0001 | 0.0171 | 0.0 | 1 |
121
  | 1.7439 | 1.4214 | 0.1264 | 0.1860 | 0.6745 | 0.0 | 0.8063 | 0.8609 | 0.0 | 0.1874 | 0.0075 | nan | 0.0000 | 0.0008 | 0.0 | 0.8652 | 0.0 | 0.0 | nan | 0.0 | 0.1508 | 0.0 | 0.0 | 0.7206 | 0.0008 | 0.0019 | 0.0062 | 0.0 | nan | 0.0282 | 0.0022 | 0.0 | 0.0 | 0.9237 | 0.4783 | 0.8933 | 0.0006 | 0.0 | 0.0170 | 0.0 | 0.0 | 0.4746 | 0.6616 | 0.0 | 0.1848 | 0.0073 | nan | 0.0000 | 0.0008 | 0.0 | 0.5882 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0407 | 0.0 | 0.0 | 0.4779 | 0.0006 | 0.0019 | 0.0060 | 0.0 | 0.0 | 0.0056 | 0.0021 | 0.0 | 0.0 | 0.7045 | 0.3983 | 0.7282 | 0.0006 | 0.0 | 0.0150 | 0.0 | 2 |
122
  | 1.3795 | 1.2564 | 0.1365 | 0.1987 | 0.7068 | 0.0 | 0.7505 | 0.9141 | 0.0000 | 0.4222 | 0.0106 | nan | 0.0001 | 0.0031 | 0.0 | 0.8707 | 0.0 | 0.0 | nan | 0.0 | 0.0642 | 0.0 | 0.0 | 0.8057 | 0.0003 | 0.0290 | 0.0011 | 0.0 | nan | 0.0 | 0.0027 | 0.0 | 0.0 | 0.8671 | 0.6862 | 0.9098 | 0.0002 | 0.0 | 0.0217 | 0.0 | 0.0 | 0.5495 | 0.6821 | 0.0000 | 0.3661 | 0.0102 | 0.0 | 0.0001 | 0.0031 | 0.0 | 0.6154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0327 | 0.0 | 0.0 | 0.4963 | 0.0003 | 0.0267 | 0.0011 | 0.0 | 0.0 | 0.0 | 0.0026 | 0.0 | 0.0 | 0.7200 | 0.4961 | 0.7580 | 0.0002 | 0.0 | 0.0177 | 0.0 | 3 |
123
+ | 1.3346 | 1.1664 | 0.1412 | 0.1958 | 0.7144 | 0.0 | 0.8177 | 0.8998 | 0.0009 | 0.4161 | 0.0254 | nan | 0.0 | 0.0159 | 0.0 | 0.8980 | 0.0 | 0.0 | nan | 0.0 | 0.0094 | 0.0 | 0.0 | 0.8424 | 0.0 | 0.0179 | 0.0007 | 0.0 | nan | 0.0 | 0.0039 | 0.0 | 0.0 | 0.9113 | 0.5713 | 0.8346 | 0.0 | 0.0 | 0.0017 | 0.0 | 0.0 | 0.5710 | 0.6881 | 0.0009 | 0.3661 | 0.0228 | nan | 0.0 | 0.0155 | 0.0 | 0.6173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0082 | 0.0 | 0.0 | 0.5245 | 0.0 | 0.0173 | 0.0007 | 0.0 | 0.0 | 0.0 | 0.0036 | 0.0 | 0.0 | 0.7286 | 0.4534 | 0.7817 | 0.0 | 0.0 | 0.0016 | 0.0 | 4 |
124
 
125
 
126
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ef7498ff87a9caae4c475d453529ca8a1954fcc71a882f28ceab413874ae5f6
3
  size 15167476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29922b4602dde601fa9bb263c9712a8a633747a92342b58232adf7bbca37674
3
  size 15167476