Hugging Face's logo

diegola123
/
mit-b0-finetuned-sidewalks

Transformers
TensorFlow
segformer
generated_from_keras_callback
Inference Endpoints
Model card Files Community
diegola123 commited on
Commit
ab6bfdc
•
1 Parent(s): 89d8fe9

Training in progress epoch 1

Browse files
Files changed (2) hide show
  1. README.md +41 -40
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,22 +15,22 @@ probably proofread and complete it, then remove this comment. -->
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: 1.2568
19
- - Validation Loss: 1.0277
20
- - Validation Mean Iou: 0.1717
21
- - Validation Mean Accuracy: 0.2305
22
- - Validation Overall Accuracy: 0.7089
23
  - Validation Accuracy Unlabeled: 0.0
24
- - Validation Accuracy Flat-road: 0.7565
25
- - Validation Accuracy Flat-sidewalk: 0.8215
26
- - Validation Accuracy Flat-crosswalk: 0.6421
27
- - Validation Accuracy Flat-cyclinglane: 0.4804
28
- - Validation Accuracy Flat-parkingdriveway: 0.1174
29
  - Validation Accuracy Flat-railtrack: nan
30
- - Validation Accuracy Flat-curb: 0.2548
31
- - Validation Accuracy Human-person: 0.0847
32
  - Validation Accuracy Human-rider: 0.0
33
- - Validation Accuracy Vehicle-car: 0.7733
34
  - Validation Accuracy Vehicle-truck: 0.0
35
  - Validation Accuracy Vehicle-bus: 0.0
36
  - Validation Accuracy Vehicle-tramtrain: nan
@@ -38,34 +38,34 @@ It achieves the following results on the evaluation set:
38
  - Validation Accuracy Vehicle-bicycle: 0.0
39
  - Validation Accuracy Vehicle-caravan: nan
40
  - Validation Accuracy Vehicle-cartrailer: 0.0
41
- - Validation Accuracy Construction-building: 0.6221
42
  - Validation Accuracy Construction-door: 0.0
43
- - Validation Accuracy Construction-wall: 0.1317
44
- - Validation Accuracy Construction-fenceguardrail: 0.0002
45
  - Validation Accuracy Construction-bridge: 0.0
46
  - Validation Accuracy Construction-tunnel: 0.0
47
  - Validation Accuracy Construction-stairs: 0.0
48
- - Validation Accuracy Object-pole: 0.0988
49
- - Validation Accuracy Object-trafficsign: 0.0
50
  - Validation Accuracy Object-trafficlight: 0.0
51
- - Validation Accuracy Nature-vegetation: 0.9727
52
- - Validation Accuracy Nature-terrain: 0.6553
53
- - Validation Accuracy Sky: 0.9463
54
  - Validation Accuracy Void-ground: 0.0
55
  - Validation Accuracy Void-dynamic: 0.0
56
- - Validation Accuracy Void-static: 0.0173
57
  - Validation Accuracy Void-unclear: 0.0
58
  - Validation Iou Unlabeled: 0.0
59
- - Validation Iou Flat-road: 0.4869
60
- - Validation Iou Flat-sidewalk: 0.7244
61
- - Validation Iou Flat-crosswalk: 0.3171
62
- - Validation Iou Flat-cyclinglane: 0.4769
63
- - Validation Iou Flat-parkingdriveway: 0.0943
64
  - Validation Iou Flat-railtrack: nan
65
- - Validation Iou Flat-curb: 0.1866
66
- - Validation Iou Human-person: 0.0608
67
  - Validation Iou Human-rider: 0.0
68
- - Validation Iou Vehicle-car: 0.4146
69
  - Validation Iou Vehicle-truck: 0.0
70
  - Validation Iou Vehicle-bus: 0.0
71
  - Validation Iou Vehicle-tramtrain: nan
@@ -73,24 +73,24 @@ It achieves the following results on the evaluation set:
73
  - Validation Iou Vehicle-bicycle: 0.0
74
  - Validation Iou Vehicle-caravan: nan
75
  - Validation Iou Vehicle-cartrailer: 0.0
76
- - Validation Iou Construction-building: 0.4891
77
  - Validation Iou Construction-door: 0.0
78
- - Validation Iou Construction-wall: 0.1186
79
- - Validation Iou Construction-fenceguardrail: 0.0002
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: 0.0939
84
- - Validation Iou Object-trafficsign: 0.0
85
  - Validation Iou Object-trafficlight: 0.0
86
- - Validation Iou Nature-vegetation: 0.6589
87
- - Validation Iou Nature-terrain: 0.5986
88
- - Validation Iou Sky: 0.7578
89
  - Validation Iou Void-ground: 0.0
90
  - Validation Iou Void-dynamic: 0.0
91
- - Validation Iou Void-static: 0.0160
92
  - Validation Iou Void-unclear: 0.0
93
- - Epoch: 0
94
 
95
  ## Model description
96
 
@@ -117,6 +117,7 @@ The following hyperparameters were used during training:
117
  | Train Loss | Validation Loss | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Accuracy Unlabeled | Validation Accuracy Flat-road | Validation Accuracy Flat-sidewalk | Validation Accuracy Flat-crosswalk | Validation Accuracy Flat-cyclinglane | Validation Accuracy Flat-parkingdriveway | Validation Accuracy Flat-railtrack | Validation Accuracy Flat-curb | Validation Accuracy Human-person | Validation Accuracy Human-rider | Validation Accuracy Vehicle-car | Validation Accuracy Vehicle-truck | Validation Accuracy Vehicle-bus | Validation Accuracy Vehicle-tramtrain | Validation Accuracy Vehicle-motorcycle | Validation Accuracy Vehicle-bicycle | Validation Accuracy Vehicle-caravan | Validation Accuracy Vehicle-cartrailer | Validation Accuracy Construction-building | Validation Accuracy Construction-door | Validation Accuracy Construction-wall | Validation Accuracy Construction-fenceguardrail | Validation Accuracy Construction-bridge | Validation Accuracy Construction-tunnel | Validation Accuracy Construction-stairs | Validation Accuracy Object-pole | Validation Accuracy Object-trafficsign | Validation Accuracy Object-trafficlight | Validation Accuracy Nature-vegetation | Validation Accuracy Nature-terrain | Validation Accuracy Sky | Validation Accuracy Void-ground | Validation Accuracy Void-dynamic | Validation Accuracy Void-static | Validation Accuracy Void-unclear | Validation Iou Unlabeled | Validation Iou Flat-road | Validation Iou Flat-sidewalk | Validation Iou Flat-crosswalk | Validation Iou Flat-cyclinglane | Validation Iou Flat-parkingdriveway | Validation Iou Flat-railtrack | Validation Iou Flat-curb | Validation Iou Human-person | Validation Iou Human-rider | Validation Iou Vehicle-car | Validation Iou Vehicle-truck | Validation Iou Vehicle-bus | Validation Iou Vehicle-tramtrain | Validation Iou Vehicle-motorcycle | Validation Iou Vehicle-bicycle | Validation Iou Vehicle-caravan | Validation Iou Vehicle-cartrailer | Validation Iou Construction-building | Validation Iou Construction-door | Validation Iou Construction-wall | Validation Iou Construction-fenceguardrail | Validation Iou Construction-bridge | Validation Iou Construction-tunnel | Validation Iou Construction-stairs | Validation Iou Object-pole | Validation Iou Object-trafficsign | Validation Iou Object-trafficlight | Validation Iou Nature-vegetation | Validation Iou Nature-terrain | Validation Iou Sky | Validation Iou Void-ground | Validation Iou Void-dynamic | Validation Iou Void-static | Validation Iou Void-unclear | Epoch |
118
  |:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:-----------------------------:|:-----------------------------:|:---------------------------------:|:----------------------------------:|:------------------------------------:|:----------------------------------------:|:----------------------------------:|:-----------------------------:|:--------------------------------:|:-------------------------------:|:-------------------------------:|:---------------------------------:|:-------------------------------:|:-------------------------------------:|:--------------------------------------:|:-----------------------------------:|:-----------------------------------:|:--------------------------------------:|:-----------------------------------------:|:-------------------------------------:|:-------------------------------------:|:-----------------------------------------------:|:---------------------------------------:|:---------------------------------------:|:---------------------------------------:|:-------------------------------:|:--------------------------------------:|:---------------------------------------:|:-------------------------------------:|:----------------------------------:|:-----------------------:|:-------------------------------:|:--------------------------------:|:-------------------------------:|:--------------------------------:|:------------------------:|:------------------------:|:----------------------------:|:-----------------------------:|:-------------------------------:|:-----------------------------------:|:-----------------------------:|:------------------------:|:---------------------------:|:--------------------------:|:--------------------------:|:----------------------------:|:--------------------------:|:--------------------------------:|:---------------------------------:|:------------------------------:|:------------------------------:|:---------------------------------:|:------------------------------------:|:--------------------------------:|:--------------------------------:|:------------------------------------------:|:----------------------------------:|:----------------------------------:|:----------------------------------:|:--------------------------:|:---------------------------------:|:----------------------------------:|:--------------------------------:|:-----------------------------:|:------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:-----:|
119
  | 1.2568 | 1.0277 | 0.1717 | 0.2305 | 0.7089 | 0.0 | 0.7565 | 0.8215 | 0.6421 | 0.4804 | 0.1174 | nan | 0.2548 | 0.0847 | 0.0 | 0.7733 | 0.0 | 0.0 | nan | 0.0 | 0.0 | nan | 0.0 | 0.6221 | 0.0 | 0.1317 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.0988 | 0.0 | 0.0 | 0.9727 | 0.6553 | 0.9463 | 0.0 | 0.0 | 0.0173 | 0.0 | 0.0 | 0.4869 | 0.7244 | 0.3171 | 0.4769 | 0.0943 | nan | 0.1866 | 0.0608 | 0.0 | 0.4146 | 0.0 | 0.0 | nan | 0.0 | 0.0 | nan | 0.0 | 0.4891 | 0.0 | 0.1186 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.0939 | 0.0 | 0.0 | 0.6589 | 0.5986 | 0.7578 | 0.0 | 0.0 | 0.0160 | 0.0 | 0 |
 
120
 
121
 
122
  ### Framework versions
 
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: 0.9385
19
+ - Validation Loss: 0.8219
20
+ - Validation Mean Iou: 0.1978
21
+ - Validation Mean Accuracy: 0.2443
22
+ - Validation Overall Accuracy: 0.7617
23
  - Validation Accuracy Unlabeled: 0.0
24
+ - Validation Accuracy Flat-road: 0.7657
25
+ - Validation Accuracy Flat-sidewalk: 0.9179
26
+ - Validation Accuracy Flat-crosswalk: 0.4156
27
+ - Validation Accuracy Flat-cyclinglane: 0.6428
28
+ - Validation Accuracy Flat-parkingdriveway: 0.3116
29
  - Validation Accuracy Flat-railtrack: nan
30
+ - Validation Accuracy Flat-curb: 0.1868
31
+ - Validation Accuracy Human-person: 0.0310
32
  - Validation Accuracy Human-rider: 0.0
33
+ - Validation Accuracy Vehicle-car: 0.8157
34
  - Validation Accuracy Vehicle-truck: 0.0
35
  - Validation Accuracy Vehicle-bus: 0.0
36
  - Validation Accuracy Vehicle-tramtrain: nan
 
38
  - Validation Accuracy Vehicle-bicycle: 0.0
39
  - Validation Accuracy Vehicle-caravan: nan
40
  - Validation Accuracy Vehicle-cartrailer: 0.0
41
+ - Validation Accuracy Construction-building: 0.8090
42
  - Validation Accuracy Construction-door: 0.0
43
+ - Validation Accuracy Construction-wall: 0.2585
44
+ - Validation Accuracy Construction-fenceguardrail: 0.1117
45
  - Validation Accuracy Construction-bridge: 0.0
46
  - Validation Accuracy Construction-tunnel: 0.0
47
  - Validation Accuracy Construction-stairs: 0.0
48
+ - Validation Accuracy Object-pole: 0.1427
49
+ - Validation Accuracy Object-trafficsign: 0.0009
50
  - Validation Accuracy Object-trafficlight: 0.0
51
+ - Validation Accuracy Nature-vegetation: 0.9491
52
+ - Validation Accuracy Nature-terrain: 0.6740
53
+ - Validation Accuracy Sky: 0.7821
54
  - Validation Accuracy Void-ground: 0.0
55
  - Validation Accuracy Void-dynamic: 0.0
56
+ - Validation Accuracy Void-static: 0.0037
57
  - Validation Accuracy Void-unclear: 0.0
58
  - Validation Iou Unlabeled: 0.0
59
+ - Validation Iou Flat-road: 0.5953
60
+ - Validation Iou Flat-sidewalk: 0.7737
61
+ - Validation Iou Flat-crosswalk: 0.3640
62
+ - Validation Iou Flat-cyclinglane: 0.5889
63
+ - Validation Iou Flat-parkingdriveway: 0.1813
64
  - Validation Iou Flat-railtrack: nan
65
+ - Validation Iou Flat-curb: 0.1674
66
+ - Validation Iou Human-person: 0.0300
67
  - Validation Iou Human-rider: 0.0
68
+ - Validation Iou Vehicle-car: 0.5407
69
  - Validation Iou Vehicle-truck: 0.0
70
  - Validation Iou Vehicle-bus: 0.0
71
  - Validation Iou Vehicle-tramtrain: nan
 
73
  - Validation Iou Vehicle-bicycle: 0.0
74
  - Validation Iou Vehicle-caravan: nan
75
  - Validation Iou Vehicle-cartrailer: 0.0
76
+ - Validation Iou Construction-building: 0.5474
77
  - Validation Iou Construction-door: 0.0
78
+ - Validation Iou Construction-wall: 0.2017
79
+ - Validation Iou Construction-fenceguardrail: 0.0897
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: 0.1280
84
+ - Validation Iou Object-trafficsign: 0.0009
85
  - Validation Iou Object-trafficlight: 0.0
86
+ - Validation Iou Nature-vegetation: 0.7228
87
+ - Validation Iou Nature-terrain: 0.6364
88
+ - Validation Iou Sky: 0.7594
89
  - Validation Iou Void-ground: 0.0
90
  - Validation Iou Void-dynamic: 0.0
91
+ - Validation Iou Void-static: 0.0036
92
  - Validation Iou Void-unclear: 0.0
93
+ - Epoch: 1
94
 
95
  ## Model description
96
 
 
117
  | Train Loss | Validation Loss | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Accuracy Unlabeled | Validation Accuracy Flat-road | Validation Accuracy Flat-sidewalk | Validation Accuracy Flat-crosswalk | Validation Accuracy Flat-cyclinglane | Validation Accuracy Flat-parkingdriveway | Validation Accuracy Flat-railtrack | Validation Accuracy Flat-curb | Validation Accuracy Human-person | Validation Accuracy Human-rider | Validation Accuracy Vehicle-car | Validation Accuracy Vehicle-truck | Validation Accuracy Vehicle-bus | Validation Accuracy Vehicle-tramtrain | Validation Accuracy Vehicle-motorcycle | Validation Accuracy Vehicle-bicycle | Validation Accuracy Vehicle-caravan | Validation Accuracy Vehicle-cartrailer | Validation Accuracy Construction-building | Validation Accuracy Construction-door | Validation Accuracy Construction-wall | Validation Accuracy Construction-fenceguardrail | Validation Accuracy Construction-bridge | Validation Accuracy Construction-tunnel | Validation Accuracy Construction-stairs | Validation Accuracy Object-pole | Validation Accuracy Object-trafficsign | Validation Accuracy Object-trafficlight | Validation Accuracy Nature-vegetation | Validation Accuracy Nature-terrain | Validation Accuracy Sky | Validation Accuracy Void-ground | Validation Accuracy Void-dynamic | Validation Accuracy Void-static | Validation Accuracy Void-unclear | Validation Iou Unlabeled | Validation Iou Flat-road | Validation Iou Flat-sidewalk | Validation Iou Flat-crosswalk | Validation Iou Flat-cyclinglane | Validation Iou Flat-parkingdriveway | Validation Iou Flat-railtrack | Validation Iou Flat-curb | Validation Iou Human-person | Validation Iou Human-rider | Validation Iou Vehicle-car | Validation Iou Vehicle-truck | Validation Iou Vehicle-bus | Validation Iou Vehicle-tramtrain | Validation Iou Vehicle-motorcycle | Validation Iou Vehicle-bicycle | Validation Iou Vehicle-caravan | Validation Iou Vehicle-cartrailer | Validation Iou Construction-building | Validation Iou Construction-door | Validation Iou Construction-wall | Validation Iou Construction-fenceguardrail | Validation Iou Construction-bridge | Validation Iou Construction-tunnel | Validation Iou Construction-stairs | Validation Iou Object-pole | Validation Iou Object-trafficsign | Validation Iou Object-trafficlight | Validation Iou Nature-vegetation | Validation Iou Nature-terrain | Validation Iou Sky | Validation Iou Void-ground | Validation Iou Void-dynamic | Validation Iou Void-static | Validation Iou Void-unclear | Epoch |
118
  |:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:-----------------------------:|:-----------------------------:|:---------------------------------:|:----------------------------------:|:------------------------------------:|:----------------------------------------:|:----------------------------------:|:-----------------------------:|:--------------------------------:|:-------------------------------:|:-------------------------------:|:---------------------------------:|:-------------------------------:|:-------------------------------------:|:--------------------------------------:|:-----------------------------------:|:-----------------------------------:|:--------------------------------------:|:-----------------------------------------:|:-------------------------------------:|:-------------------------------------:|:-----------------------------------------------:|:---------------------------------------:|:---------------------------------------:|:---------------------------------------:|:-------------------------------:|:--------------------------------------:|:---------------------------------------:|:-------------------------------------:|:----------------------------------:|:-----------------------:|:-------------------------------:|:--------------------------------:|:-------------------------------:|:--------------------------------:|:------------------------:|:------------------------:|:----------------------------:|:-----------------------------:|:-------------------------------:|:-----------------------------------:|:-----------------------------:|:------------------------:|:---------------------------:|:--------------------------:|:--------------------------:|:----------------------------:|:--------------------------:|:--------------------------------:|:---------------------------------:|:------------------------------:|:------------------------------:|:---------------------------------:|:------------------------------------:|:--------------------------------:|:--------------------------------:|:------------------------------------------:|:----------------------------------:|:----------------------------------:|:----------------------------------:|:--------------------------:|:---------------------------------:|:----------------------------------:|:--------------------------------:|:-----------------------------:|:------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:-----:|
119
  | 1.2568 | 1.0277 | 0.1717 | 0.2305 | 0.7089 | 0.0 | 0.7565 | 0.8215 | 0.6421 | 0.4804 | 0.1174 | nan | 0.2548 | 0.0847 | 0.0 | 0.7733 | 0.0 | 0.0 | nan | 0.0 | 0.0 | nan | 0.0 | 0.6221 | 0.0 | 0.1317 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.0988 | 0.0 | 0.0 | 0.9727 | 0.6553 | 0.9463 | 0.0 | 0.0 | 0.0173 | 0.0 | 0.0 | 0.4869 | 0.7244 | 0.3171 | 0.4769 | 0.0943 | nan | 0.1866 | 0.0608 | 0.0 | 0.4146 | 0.0 | 0.0 | nan | 0.0 | 0.0 | nan | 0.0 | 0.4891 | 0.0 | 0.1186 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.0939 | 0.0 | 0.0 | 0.6589 | 0.5986 | 0.7578 | 0.0 | 0.0 | 0.0160 | 0.0 | 0 |
120
+ | 0.9385 | 0.8219 | 0.1978 | 0.2443 | 0.7617 | 0.0 | 0.7657 | 0.9179 | 0.4156 | 0.6428 | 0.3116 | nan | 0.1868 | 0.0310 | 0.0 | 0.8157 | 0.0 | 0.0 | nan | 0.0 | 0.0 | nan | 0.0 | 0.8090 | 0.0 | 0.2585 | 0.1117 | 0.0 | 0.0 | 0.0 | 0.1427 | 0.0009 | 0.0 | 0.9491 | 0.6740 | 0.7821 | 0.0 | 0.0 | 0.0037 | 0.0 | 0.0 | 0.5953 | 0.7737 | 0.3640 | 0.5889 | 0.1813 | nan | 0.1674 | 0.0300 | 0.0 | 0.5407 | 0.0 | 0.0 | nan | 0.0 | 0.0 | nan | 0.0 | 0.5474 | 0.0 | 0.2017 | 0.0897 | 0.0 | 0.0 | 0.0 | 0.1280 | 0.0009 | 0.0 | 0.7228 | 0.6364 | 0.7594 | 0.0 | 0.0 | 0.0036 | 0.0 | 1 |
121
 
122
 
123
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bc783b0f9d51d82eefa694aefc85f2bf34e2dc17d56160299172937f3880d5c
3
  size 15167476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab0b70ca5c82cfa866350f6a17b506b8c5743dfb8e83920132577859d6f92467
3
  size 15167476