brandyDolly
commited on
Commit
•
640eb97
1
Parent(s):
96f2d87
Model save
Browse files
README.md
CHANGED
@@ -3,8 +3,6 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: microsoft/beit-base-finetuned-ade-640-640
|
5 |
tags:
|
6 |
-
- image-segmentation
|
7 |
-
- vision
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: segformer-finetuned-sidewalk-10k-steps
|
@@ -16,82 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# segformer-finetuned-sidewalk-10k-steps
|
18 |
|
19 |
-
This model is a fine-tuned version of [microsoft/beit-base-finetuned-ade-640-640](https://huggingface.co/microsoft/beit-base-finetuned-ade-640-640) on
|
20 |
-
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 3.7016
|
22 |
-
- Mean Iou: 0.0657
|
23 |
-
- Mean Accuracy: 0.1096
|
24 |
-
- Overall Accuracy: 0.5747
|
25 |
-
- Accuracy Unlabeled: nan
|
26 |
-
- Accuracy Flat-road: 0.0688
|
27 |
-
- Accuracy Flat-sidewalk: 0.9323
|
28 |
-
- Accuracy Flat-crosswalk: 0.0208
|
29 |
-
- Accuracy Flat-cyclinglane: 0.1128
|
30 |
-
- Accuracy Flat-parkingdriveway: 0.0001
|
31 |
-
- Accuracy Flat-railtrack: nan
|
32 |
-
- Accuracy Flat-curb: 0.0000
|
33 |
-
- Accuracy Human-person: 0.0036
|
34 |
-
- Accuracy Human-rider: 0.0
|
35 |
-
- Accuracy Vehicle-car: 0.0119
|
36 |
-
- Accuracy Vehicle-truck: 0.0031
|
37 |
-
- Accuracy Vehicle-bus: 0.0
|
38 |
-
- Accuracy Vehicle-tramtrain: nan
|
39 |
-
- Accuracy Vehicle-motorcycle: 0.0
|
40 |
-
- Accuracy Vehicle-bicycle: 0.0041
|
41 |
-
- Accuracy Vehicle-caravan: nan
|
42 |
-
- Accuracy Vehicle-cartrailer: 0.0
|
43 |
-
- Accuracy Construction-building: 0.8154
|
44 |
-
- Accuracy Construction-door: 0.0
|
45 |
-
- Accuracy Construction-wall: 0.0063
|
46 |
-
- Accuracy Construction-fenceguardrail: 0.0003
|
47 |
-
- Accuracy Construction-bridge: 0.0
|
48 |
-
- Accuracy Construction-tunnel: 0.0
|
49 |
-
- Accuracy Construction-stairs: 0.0
|
50 |
-
- Accuracy Object-pole: 0.0000
|
51 |
-
- Accuracy Object-trafficsign: 0.0
|
52 |
-
- Accuracy Object-trafficlight: 0.0
|
53 |
-
- Accuracy Nature-vegetation: 0.8720
|
54 |
-
- Accuracy Nature-terrain: 0.4628
|
55 |
-
- Accuracy Sky: 0.0239
|
56 |
-
- Accuracy Void-ground: 0.0
|
57 |
-
- Accuracy Void-dynamic: 0.0044
|
58 |
-
- Accuracy Void-static: 0.0087
|
59 |
-
- Accuracy Void-unclear: 0.0448
|
60 |
-
- Iou Unlabeled: 0.0
|
61 |
-
- Iou Flat-road: 0.0678
|
62 |
-
- Iou Flat-sidewalk: 0.7148
|
63 |
-
- Iou Flat-crosswalk: 0.0018
|
64 |
-
- Iou Flat-cyclinglane: 0.0571
|
65 |
-
- Iou Flat-parkingdriveway: 0.0001
|
66 |
-
- Iou Flat-railtrack: 0.0
|
67 |
-
- Iou Flat-curb: 0.0000
|
68 |
-
- Iou Human-person: 0.0017
|
69 |
-
- Iou Human-rider: 0.0
|
70 |
-
- Iou Vehicle-car: 0.0117
|
71 |
-
- Iou Vehicle-truck: 0.0002
|
72 |
-
- Iou Vehicle-bus: 0.0
|
73 |
-
- Iou Vehicle-tramtrain: 0.0
|
74 |
-
- Iou Vehicle-motorcycle: 0.0
|
75 |
-
- Iou Vehicle-bicycle: 0.0010
|
76 |
-
- Iou Vehicle-caravan: 0.0
|
77 |
-
- Iou Vehicle-cartrailer: 0.0
|
78 |
-
- Iou Construction-building: 0.4872
|
79 |
-
- Iou Construction-door: 0.0
|
80 |
-
- Iou Construction-wall: 0.0048
|
81 |
-
- Iou Construction-fenceguardrail: 0.0003
|
82 |
-
- Iou Construction-bridge: 0.0
|
83 |
-
- Iou Construction-tunnel: 0.0
|
84 |
-
- Iou Construction-stairs: 0.0
|
85 |
-
- Iou Object-pole: 0.0000
|
86 |
-
- Iou Object-trafficsign: 0.0
|
87 |
-
- Iou Object-trafficlight: 0.0
|
88 |
-
- Iou Nature-vegetation: 0.5625
|
89 |
-
- Iou Nature-terrain: 0.3569
|
90 |
-
- Iou Sky: 0.0239
|
91 |
-
- Iou Void-ground: 0.0
|
92 |
-
- Iou Void-dynamic: 0.0028
|
93 |
-
- Iou Void-static: 0.0055
|
94 |
-
- Iou Void-unclear: 0.0001
|
95 |
|
96 |
## Model description
|
97 |
|
@@ -122,7 +45,7 @@ The following hyperparameters were used during training:
|
|
122 |
|
123 |
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Flat-road | Accuracy Flat-sidewalk | Accuracy Flat-crosswalk | Accuracy Flat-cyclinglane | Accuracy Flat-parkingdriveway | Accuracy Flat-railtrack | Accuracy Flat-curb | Accuracy Human-person | Accuracy Human-rider | Accuracy Vehicle-car | Accuracy Vehicle-truck | Accuracy Vehicle-bus | Accuracy Vehicle-tramtrain | Accuracy Vehicle-motorcycle | Accuracy Vehicle-bicycle | Accuracy Vehicle-caravan | Accuracy Vehicle-cartrailer | Accuracy Construction-building | Accuracy Construction-door | Accuracy Construction-wall | Accuracy Construction-fenceguardrail | Accuracy Construction-bridge | Accuracy Construction-tunnel | Accuracy Construction-stairs | Accuracy Object-pole | Accuracy Object-trafficsign | Accuracy Object-trafficlight | Accuracy Nature-vegetation | Accuracy Nature-terrain | Accuracy Sky | Accuracy Void-ground | Accuracy Void-dynamic | Accuracy Void-static | Accuracy Void-unclear | Iou Unlabeled | Iou Flat-road | Iou Flat-sidewalk | Iou Flat-crosswalk | Iou Flat-cyclinglane | Iou Flat-parkingdriveway | Iou Flat-railtrack | Iou Flat-curb | Iou Human-person | Iou Human-rider | Iou Vehicle-car | Iou Vehicle-truck | Iou Vehicle-bus | Iou Vehicle-tramtrain | Iou Vehicle-motorcycle | Iou Vehicle-bicycle | Iou Vehicle-caravan | Iou Vehicle-cartrailer | Iou Construction-building | Iou Construction-door | Iou Construction-wall | Iou Construction-fenceguardrail | Iou Construction-bridge | Iou Construction-tunnel | Iou Construction-stairs | Iou Object-pole | Iou Object-trafficsign | Iou Object-trafficlight | Iou Nature-vegetation | Iou Nature-terrain | Iou Sky | Iou Void-ground | Iou Void-dynamic | Iou Void-static | Iou Void-unclear |
|
124 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:------------------:|:----------------------:|:-----------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------:|:---------------------:|:--------------------:|:--------------------:|:----------------------:|:--------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------:|:---------------------------:|:------------------------------:|:--------------------------:|:--------------------------:|:------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:--------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-----------------------:|:------------:|:--------------------:|:---------------------:|:--------------------:|:---------------------:|:-------------:|:-------------:|:-----------------:|:------------------:|:--------------------:|:------------------------:|:------------------:|:-------------:|:----------------:|:---------------:|:---------------:|:-----------------:|:---------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------:|:----------------------:|:-------------------------:|:---------------------:|:---------------------:|:-------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:---------------:|:----------------------:|:-----------------------:|:---------------------:|:------------------:|:-------:|:---------------:|:----------------:|:---------------:|:----------------:|
|
125 |
-
| No log | 0.0235 | 10 | 3.
|
126 |
|
127 |
|
128 |
### Framework versions
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: microsoft/beit-base-finetuned-ade-640-640
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: segformer-finetuned-sidewalk-10k-steps
|
|
|
14 |
|
15 |
# segformer-finetuned-sidewalk-10k-steps
|
16 |
|
17 |
+
This model is a fine-tuned version of [microsoft/beit-base-finetuned-ade-640-640](https://huggingface.co/microsoft/beit-base-finetuned-ade-640-640) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
45 |
|
46 |
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Flat-road | Accuracy Flat-sidewalk | Accuracy Flat-crosswalk | Accuracy Flat-cyclinglane | Accuracy Flat-parkingdriveway | Accuracy Flat-railtrack | Accuracy Flat-curb | Accuracy Human-person | Accuracy Human-rider | Accuracy Vehicle-car | Accuracy Vehicle-truck | Accuracy Vehicle-bus | Accuracy Vehicle-tramtrain | Accuracy Vehicle-motorcycle | Accuracy Vehicle-bicycle | Accuracy Vehicle-caravan | Accuracy Vehicle-cartrailer | Accuracy Construction-building | Accuracy Construction-door | Accuracy Construction-wall | Accuracy Construction-fenceguardrail | Accuracy Construction-bridge | Accuracy Construction-tunnel | Accuracy Construction-stairs | Accuracy Object-pole | Accuracy Object-trafficsign | Accuracy Object-trafficlight | Accuracy Nature-vegetation | Accuracy Nature-terrain | Accuracy Sky | Accuracy Void-ground | Accuracy Void-dynamic | Accuracy Void-static | Accuracy Void-unclear | Iou Unlabeled | Iou Flat-road | Iou Flat-sidewalk | Iou Flat-crosswalk | Iou Flat-cyclinglane | Iou Flat-parkingdriveway | Iou Flat-railtrack | Iou Flat-curb | Iou Human-person | Iou Human-rider | Iou Vehicle-car | Iou Vehicle-truck | Iou Vehicle-bus | Iou Vehicle-tramtrain | Iou Vehicle-motorcycle | Iou Vehicle-bicycle | Iou Vehicle-caravan | Iou Vehicle-cartrailer | Iou Construction-building | Iou Construction-door | Iou Construction-wall | Iou Construction-fenceguardrail | Iou Construction-bridge | Iou Construction-tunnel | Iou Construction-stairs | Iou Object-pole | Iou Object-trafficsign | Iou Object-trafficlight | Iou Nature-vegetation | Iou Nature-terrain | Iou Sky | Iou Void-ground | Iou Void-dynamic | Iou Void-static | Iou Void-unclear |
|
47 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:------------------:|:----------------------:|:-----------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------:|:---------------------:|:--------------------:|:--------------------:|:----------------------:|:--------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------:|:---------------------------:|:------------------------------:|:--------------------------:|:--------------------------:|:------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:--------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-----------------------:|:------------:|:--------------------:|:---------------------:|:--------------------:|:---------------------:|:-------------:|:-------------:|:-----------------:|:------------------:|:--------------------:|:------------------------:|:------------------:|:-------------:|:----------------:|:---------------:|:---------------:|:-----------------:|:---------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------:|:----------------------:|:-------------------------:|:---------------------:|:---------------------:|:-------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:---------------:|:----------------------:|:-----------------------:|:---------------------:|:------------------:|:-------:|:---------------:|:----------------:|:---------------:|:----------------:|
|
48 |
+
| No log | 0.0235 | 10 | 3.7903 | 0.0583 | 0.1188 | 0.5138 | nan | 0.3738 | 0.8070 | 0.2760 | 0.0412 | 0.0002 | nan | 0.0013 | 0.0073 | 0.0 | 0.9825 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0098 | 0.1165 | 0.0000 | 0.0 | 0.0 | nan | 0.0659 | 0.0438 | 0.0 | 0.0 | 0.9260 | 0.0287 | 0.0 | 0.0 | 0.0 | 0.0036 | 0.0 | 0.0 | 0.2457 | 0.6862 | 0.0806 | 0.0394 | 0.0001 | 0.0 | 0.0013 | 0.0044 | 0.0 | 0.3160 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0096 | 0.0317 | 0.0000 | 0.0 | 0.0 | 0.0 | 0.0103 | 0.0226 | 0.0 | 0.0 | 0.5656 | 0.0255 | 0.0 | 0.0 | 0.0 | 0.0031 | 0.0 |
|
49 |
|
50 |
|
51 |
### Framework versions
|