Hugging Face's logo

EgorGrinevich
/
mit-b0-finetuned-sidewalks

Transformers
TensorFlow
segformer
generated_from_keras_callback
Model card Files
xet
Community
EgorGrinevich commited on
Commit
0e41cfa
·
1 Parent(s): 681e3b6

Training in progress epoch 2

Browse files
Files changed (2) hide show
  1. README.md +43 -42
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,82 +15,82 @@ 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: 0.8317
19
- - Validation Loss: 0.7333
20
- - Validation Mean Iou: 0.2208
21
- - Validation Mean Accuracy: 0.2679
22
- - Validation Overall Accuracy: 0.7828
23
  - Validation Accuracy Unlabeled: 0.0
24
- - Validation Accuracy Flat-road: 0.8055
25
- - Validation Accuracy Flat-sidewalk: 0.8965
26
- - Validation Accuracy Flat-crosswalk: 0.5122
27
- - Validation Accuracy Flat-cyclinglane: 0.6911
28
- - Validation Accuracy Flat-parkingdriveway: 0.3397
29
  - Validation Accuracy Flat-railtrack: nan
30
- - Validation Accuracy Flat-curb: 0.2233
31
- - Validation Accuracy Human-person: 0.3391
32
  - Validation Accuracy Human-rider: 0.0
33
- - Validation Accuracy Vehicle-car: 0.8793
34
  - Validation Accuracy Vehicle-truck: 0.0
35
  - Validation Accuracy Vehicle-bus: 0.0
36
  - Validation Accuracy Vehicle-tramtrain: 0.0
37
  - Validation Accuracy Vehicle-motorcycle: 0.0
38
- - Validation Accuracy Vehicle-bicycle: 0.0263
39
  - Validation Accuracy Vehicle-caravan: 0.0
40
  - Validation Accuracy Vehicle-cartrailer: 0.0
41
- - Validation Accuracy Construction-building: 0.7717
42
  - Validation Accuracy Construction-door: 0.0
43
- - Validation Accuracy Construction-wall: 0.5182
44
- - Validation Accuracy Construction-fenceguardrail: 0.1341
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: 0.0227
49
  - Validation Accuracy Object-trafficsign: 0.0
50
  - Validation Accuracy Object-trafficlight: 0.0
51
- - Validation Accuracy Nature-vegetation: 0.9423
52
- - Validation Accuracy Nature-terrain: 0.7332
53
- - Validation Accuracy Sky: 0.9396
54
  - Validation Accuracy Void-ground: 0.0
55
- - Validation Accuracy Void-dynamic: 0.0
56
- - Validation Accuracy Void-static: 0.0642
57
  - Validation Accuracy Void-unclear: 0.0
58
  - Validation Iou Unlabeled: 0.0
59
- - Validation Iou Flat-road: 0.5536
60
- - Validation Iou Flat-sidewalk: 0.8016
61
- - Validation Iou Flat-crosswalk: 0.5026
62
- - Validation Iou Flat-cyclinglane: 0.5975
63
- - Validation Iou Flat-parkingdriveway: 0.2511
64
  - Validation Iou Flat-railtrack: nan
65
- - Validation Iou Flat-curb: 0.1826
66
- - Validation Iou Human-person: 0.2382
67
  - Validation Iou Human-rider: 0.0
68
- - Validation Iou Vehicle-car: 0.7744
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: 0.0260
74
  - Validation Iou Vehicle-caravan: 0.0
75
  - Validation Iou Vehicle-cartrailer: 0.0
76
- - Validation Iou Construction-building: 0.6104
77
  - Validation Iou Construction-door: 0.0
78
- - Validation Iou Construction-wall: 0.3726
79
- - Validation Iou Construction-fenceguardrail: 0.1160
80
  - Validation Iou Construction-bridge: 0.0
81
  - Validation Iou Construction-tunnel: nan
82
  - Validation Iou Construction-stairs: 0.0
83
- - Validation Iou Object-pole: 0.0217
84
  - Validation Iou Object-trafficsign: 0.0
85
  - Validation Iou Object-trafficlight: 0.0
86
- - Validation Iou Nature-vegetation: 0.7518
87
- - Validation Iou Nature-terrain: 0.6109
88
- - Validation Iou Sky: 0.8268
89
  - Validation Iou Void-ground: 0.0
90
- - Validation Iou Void-dynamic: 0.0
91
- - Validation Iou Void-static: 0.0495
92
  - Validation Iou Void-unclear: 0.0
93
- - Epoch: 1
94
 
95
  ## Model description
96
 
@@ -118,6 +118,7 @@ The following hyperparameters were used during training:
118
  |:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:-----------------------------:|:-----------------------------:|:---------------------------------:|:----------------------------------:|:------------------------------------:|:----------------------------------------:|:----------------------------------:|:-----------------------------:|:--------------------------------:|:-------------------------------:|:-------------------------------:|:---------------------------------:|:-------------------------------:|:-------------------------------------:|:--------------------------------------:|:-----------------------------------:|:-----------------------------------:|:--------------------------------------:|:-----------------------------------------:|:-------------------------------------:|:-------------------------------------:|:-----------------------------------------------:|:---------------------------------------:|:---------------------------------------:|:---------------------------------------:|:-------------------------------:|:--------------------------------------:|:---------------------------------------:|:-------------------------------------:|:----------------------------------:|:-----------------------:|:-------------------------------:|:--------------------------------:|:-------------------------------:|:--------------------------------:|:------------------------:|:------------------------:|:----------------------------:|:-----------------------------:|:-------------------------------:|:-----------------------------------:|:-----------------------------:|:------------------------:|:---------------------------:|:--------------------------:|:--------------------------:|:----------------------------:|:--------------------------:|:--------------------------------:|:---------------------------------:|:------------------------------:|:------------------------------:|:---------------------------------:|:------------------------------------:|:--------------------------------:|:--------------------------------:|:------------------------------------------:|:----------------------------------:|:----------------------------------:|:----------------------------------:|:--------------------------:|:---------------------------------:|:----------------------------------:|:--------------------------------:|:-----------------------------:|:------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:-----:|
119
  | 1.3415 | 0.8109 | 0.1900 | 0.2324 | 0.7650 | 0.0 | 0.6711 | 0.9475 | 0.6314 | 0.7144 | 0.1245 | nan | 0.1784 | 0.0013 | 0.0 | 0.8892 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.8853 | 0.0 | 0.0868 | 0.0346 | 0.0 | nan | 0.0 | 0.0006 | 0.0 | 0.0 | 0.9018 | 0.6821 | 0.9120 | 0.0 | 0.0 | 0.0084 | 0.0 | 0.0 | 0.5714 | 0.7578 | 0.5849 | 0.5753 | 0.1077 | nan | 0.1464 | 0.0012 | 0.0 | 0.6923 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5522 | 0.0 | 0.0843 | 0.0346 | 0.0 | nan | 0.0 | 0.0006 | 0.0 | 0.0 | 0.7606 | 0.5641 | 0.8300 | 0.0 | 0.0 | 0.0080 | 0.0 | 0 |
120
  | 0.8317 | 0.7333 | 0.2208 | 0.2679 | 0.7828 | 0.0 | 0.8055 | 0.8965 | 0.5122 | 0.6911 | 0.3397 | nan | 0.2233 | 0.3391 | 0.0 | 0.8793 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0263 | 0.0 | 0.0 | 0.7717 | 0.0 | 0.5182 | 0.1341 | 0.0 | nan | 0.0 | 0.0227 | 0.0 | 0.0 | 0.9423 | 0.7332 | 0.9396 | 0.0 | 0.0 | 0.0642 | 0.0 | 0.0 | 0.5536 | 0.8016 | 0.5026 | 0.5975 | 0.2511 | nan | 0.1826 | 0.2382 | 0.0 | 0.7744 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0260 | 0.0 | 0.0 | 0.6104 | 0.0 | 0.3726 | 0.1160 | 0.0 | nan | 0.0 | 0.0217 | 0.0 | 0.0 | 0.7518 | 0.6109 | 0.8268 | 0.0 | 0.0 | 0.0495 | 0.0 | 1 |
 
121
 
122
 
123
  ### 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: 0.6909
19
+ - Validation Loss: 0.5868
20
+ - Validation Mean Iou: 0.2613
21
+ - Validation Mean Accuracy: 0.3220
22
+ - Validation Overall Accuracy: 0.8273
23
  - Validation Accuracy Unlabeled: 0.0
24
+ - Validation Accuracy Flat-road: 0.8676
25
+ - Validation Accuracy Flat-sidewalk: 0.9207
26
+ - Validation Accuracy Flat-crosswalk: 0.8263
27
+ - Validation Accuracy Flat-cyclinglane: 0.7711
28
+ - Validation Accuracy Flat-parkingdriveway: 0.4930
29
  - Validation Accuracy Flat-railtrack: nan
30
+ - Validation Accuracy Flat-curb: 0.4095
31
+ - Validation Accuracy Human-person: 0.6480
32
  - Validation Accuracy Human-rider: 0.0
33
+ - Validation Accuracy Vehicle-car: 0.9295
34
  - Validation Accuracy Vehicle-truck: 0.0
35
  - Validation Accuracy Vehicle-bus: 0.0
36
  - Validation Accuracy Vehicle-tramtrain: 0.0
37
  - Validation Accuracy Vehicle-motorcycle: 0.0
38
+ - Validation Accuracy Vehicle-bicycle: 0.3762
39
  - Validation Accuracy Vehicle-caravan: 0.0
40
  - Validation Accuracy Vehicle-cartrailer: 0.0
41
+ - Validation Accuracy Construction-building: 0.8764
42
  - Validation Accuracy Construction-door: 0.0
43
+ - Validation Accuracy Construction-wall: 0.4062
44
+ - Validation Accuracy Construction-fenceguardrail: 0.1756
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: 0.0996
49
  - Validation Accuracy Object-trafficsign: 0.0
50
  - Validation Accuracy Object-trafficlight: 0.0
51
+ - Validation Accuracy Nature-vegetation: 0.9260
52
+ - Validation Accuracy Nature-terrain: 0.7816
53
+ - Validation Accuracy Sky: 0.9533
54
  - Validation Accuracy Void-ground: 0.0
55
+ - Validation Accuracy Void-dynamic: 0.0069
56
+ - Validation Accuracy Void-static: 0.1579
57
  - Validation Accuracy Void-unclear: 0.0
58
  - Validation Iou Unlabeled: 0.0
59
+ - Validation Iou Flat-road: 0.7101
60
+ - Validation Iou Flat-sidewalk: 0.8596
61
+ - Validation Iou Flat-crosswalk: 0.6695
62
+ - Validation Iou Flat-cyclinglane: 0.6535
63
+ - Validation Iou Flat-parkingdriveway: 0.3411
64
  - Validation Iou Flat-railtrack: nan
65
+ - Validation Iou Flat-curb: 0.3182
66
+ - Validation Iou Human-person: 0.3259
67
  - Validation Iou Human-rider: 0.0
68
+ - Validation Iou Vehicle-car: 0.7776
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: 0.2912
74
  - Validation Iou Vehicle-caravan: 0.0
75
  - Validation Iou Vehicle-cartrailer: 0.0
76
+ - Validation Iou Construction-building: 0.6492
77
  - Validation Iou Construction-door: 0.0
78
+ - Validation Iou Construction-wall: 0.3519
79
+ - Validation Iou Construction-fenceguardrail: 0.1676
80
  - Validation Iou Construction-bridge: 0.0
81
  - Validation Iou Construction-tunnel: nan
82
  - Validation Iou Construction-stairs: 0.0
83
+ - Validation Iou Object-pole: 0.0863
84
  - Validation Iou Object-trafficsign: 0.0
85
  - Validation Iou Object-trafficlight: 0.0
86
+ - Validation Iou Nature-vegetation: 0.7991
87
+ - Validation Iou Nature-terrain: 0.6168
88
+ - Validation Iou Sky: 0.8961
89
  - Validation Iou Void-ground: 0.0
90
+ - Validation Iou Void-dynamic: 0.0069
91
+ - Validation Iou Void-static: 0.1034
92
  - Validation Iou Void-unclear: 0.0
93
+ - Epoch: 2
94
 
95
  ## Model description
96
 
 
118
  |:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:-----------------------------:|:-----------------------------:|:---------------------------------:|:----------------------------------:|:------------------------------------:|:----------------------------------------:|:----------------------------------:|:-----------------------------:|:--------------------------------:|:-------------------------------:|:-------------------------------:|:---------------------------------:|:-------------------------------:|:-------------------------------------:|:--------------------------------------:|:-----------------------------------:|:-----------------------------------:|:--------------------------------------:|:-----------------------------------------:|:-------------------------------------:|:-------------------------------------:|:-----------------------------------------------:|:---------------------------------------:|:---------------------------------------:|:---------------------------------------:|:-------------------------------:|:--------------------------------------:|:---------------------------------------:|:-------------------------------------:|:----------------------------------:|:-----------------------:|:-------------------------------:|:--------------------------------:|:-------------------------------:|:--------------------------------:|:------------------------:|:------------------------:|:----------------------------:|:-----------------------------:|:-------------------------------:|:-----------------------------------:|:-----------------------------:|:------------------------:|:---------------------------:|:--------------------------:|:--------------------------:|:----------------------------:|:--------------------------:|:--------------------------------:|:---------------------------------:|:------------------------------:|:------------------------------:|:---------------------------------:|:------------------------------------:|:--------------------------------:|:--------------------------------:|:------------------------------------------:|:----------------------------------:|:----------------------------------:|:----------------------------------:|:--------------------------:|:---------------------------------:|:----------------------------------:|:--------------------------------:|:-----------------------------:|:------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:-----:|
119
  | 1.3415 | 0.8109 | 0.1900 | 0.2324 | 0.7650 | 0.0 | 0.6711 | 0.9475 | 0.6314 | 0.7144 | 0.1245 | nan | 0.1784 | 0.0013 | 0.0 | 0.8892 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.8853 | 0.0 | 0.0868 | 0.0346 | 0.0 | nan | 0.0 | 0.0006 | 0.0 | 0.0 | 0.9018 | 0.6821 | 0.9120 | 0.0 | 0.0 | 0.0084 | 0.0 | 0.0 | 0.5714 | 0.7578 | 0.5849 | 0.5753 | 0.1077 | nan | 0.1464 | 0.0012 | 0.0 | 0.6923 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5522 | 0.0 | 0.0843 | 0.0346 | 0.0 | nan | 0.0 | 0.0006 | 0.0 | 0.0 | 0.7606 | 0.5641 | 0.8300 | 0.0 | 0.0 | 0.0080 | 0.0 | 0 |
120
  | 0.8317 | 0.7333 | 0.2208 | 0.2679 | 0.7828 | 0.0 | 0.8055 | 0.8965 | 0.5122 | 0.6911 | 0.3397 | nan | 0.2233 | 0.3391 | 0.0 | 0.8793 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0263 | 0.0 | 0.0 | 0.7717 | 0.0 | 0.5182 | 0.1341 | 0.0 | nan | 0.0 | 0.0227 | 0.0 | 0.0 | 0.9423 | 0.7332 | 0.9396 | 0.0 | 0.0 | 0.0642 | 0.0 | 0.0 | 0.5536 | 0.8016 | 0.5026 | 0.5975 | 0.2511 | nan | 0.1826 | 0.2382 | 0.0 | 0.7744 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0260 | 0.0 | 0.0 | 0.6104 | 0.0 | 0.3726 | 0.1160 | 0.0 | nan | 0.0 | 0.0217 | 0.0 | 0.0 | 0.7518 | 0.6109 | 0.8268 | 0.0 | 0.0 | 0.0495 | 0.0 | 1 |
121
+ | 0.6909 | 0.5868 | 0.2613 | 0.3220 | 0.8273 | 0.0 | 0.8676 | 0.9207 | 0.8263 | 0.7711 | 0.4930 | nan | 0.4095 | 0.6480 | 0.0 | 0.9295 | 0.0 | 0.0 | 0.0 | 0.0 | 0.3762 | 0.0 | 0.0 | 0.8764 | 0.0 | 0.4062 | 0.1756 | 0.0 | nan | 0.0 | 0.0996 | 0.0 | 0.0 | 0.9260 | 0.7816 | 0.9533 | 0.0 | 0.0069 | 0.1579 | 0.0 | 0.0 | 0.7101 | 0.8596 | 0.6695 | 0.6535 | 0.3411 | nan | 0.3182 | 0.3259 | 0.0 | 0.7776 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2912 | 0.0 | 0.0 | 0.6492 | 0.0 | 0.3519 | 0.1676 | 0.0 | nan | 0.0 | 0.0863 | 0.0 | 0.0 | 0.7991 | 0.6168 | 0.8961 | 0.0 | 0.0069 | 0.1034 | 0.0 | 2 |
122
 
123
 
124
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e6fa1462fbc97b892c07e395140268aeca1ba8b7ffe49b2d977c4f609851da2
3
  size 15167476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b0d564d4deb9bb9d33bfc785f6b9f56635baf8f12b86f1d9404f635621733d
3
  size 15167476