update model card README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
|
|
|
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
- name: segformer-finetuned-sidewalk-50-epochs
|
@@ -12,7 +14,82 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# segformer-finetuned-sidewalk-50-epochs
|
14 |
|
15 |
-
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
+
- image-segmentation
|
5 |
+
- vision
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: segformer-finetuned-sidewalk-50-epochs
|
|
|
14 |
|
15 |
# segformer-finetuned-sidewalk-50-epochs
|
16 |
|
17 |
+
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the segments/sidewalk-semantic dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7794
|
20 |
+
- Mean Iou: 0.2323
|
21 |
+
- Mean Accuracy: 0.2967
|
22 |
+
- Overall Accuracy: 0.7880
|
23 |
+
- Accuracy Unlabeled: nan
|
24 |
+
- Accuracy Flat-road: 0.7710
|
25 |
+
- Accuracy Flat-sidewalk: 0.9216
|
26 |
+
- Accuracy Flat-crosswalk: 0.2824
|
27 |
+
- Accuracy Flat-cyclinglane: 0.7632
|
28 |
+
- Accuracy Flat-parkingdriveway: 0.2202
|
29 |
+
- Accuracy Flat-railtrack: nan
|
30 |
+
- Accuracy Flat-curb: 0.5054
|
31 |
+
- Accuracy Human-person: 0.5200
|
32 |
+
- Accuracy Human-rider: 0.0
|
33 |
+
- Accuracy Vehicle-car: 0.9194
|
34 |
+
- Accuracy Vehicle-truck: 0.0
|
35 |
+
- Accuracy Vehicle-bus: 0.0
|
36 |
+
- Accuracy Vehicle-tramtrain: nan
|
37 |
+
- Accuracy Vehicle-motorcycle: 0.0
|
38 |
+
- Accuracy Vehicle-bicycle: 0.0
|
39 |
+
- Accuracy Vehicle-caravan: 0.0
|
40 |
+
- Accuracy Vehicle-cartrailer: 0.0
|
41 |
+
- Accuracy Construction-building: 0.8614
|
42 |
+
- Accuracy Construction-door: 0.0
|
43 |
+
- Accuracy Construction-wall: 0.4325
|
44 |
+
- Accuracy Construction-fenceguardrail: 0.0652
|
45 |
+
- Accuracy Construction-bridge: 0.0
|
46 |
+
- Accuracy Construction-tunnel: nan
|
47 |
+
- Accuracy Construction-stairs: 0.0
|
48 |
+
- Accuracy Object-pole: 0.2563
|
49 |
+
- Accuracy Object-trafficsign: 0.0
|
50 |
+
- Accuracy Object-trafficlight: 0.0
|
51 |
+
- Accuracy Nature-vegetation: 0.9089
|
52 |
+
- Accuracy Nature-terrain: 0.8215
|
53 |
+
- Accuracy Sky: 0.8732
|
54 |
+
- Accuracy Void-ground: 0.0
|
55 |
+
- Accuracy Void-dynamic: 0.0
|
56 |
+
- Accuracy Void-static: 0.0739
|
57 |
+
- Accuracy Void-unclear: 0.0
|
58 |
+
- Iou Unlabeled: nan
|
59 |
+
- Iou Flat-road: 0.5975
|
60 |
+
- Iou Flat-sidewalk: 0.8299
|
61 |
+
- Iou Flat-crosswalk: 0.2624
|
62 |
+
- Iou Flat-cyclinglane: 0.5689
|
63 |
+
- Iou Flat-parkingdriveway: 0.1733
|
64 |
+
- Iou Flat-railtrack: nan
|
65 |
+
- Iou Flat-curb: 0.3084
|
66 |
+
- Iou Human-person: 0.3708
|
67 |
+
- Iou Human-rider: 0.0
|
68 |
+
- Iou Vehicle-car: 0.6164
|
69 |
+
- Iou Vehicle-truck: 0.0
|
70 |
+
- Iou Vehicle-bus: 0.0
|
71 |
+
- Iou Vehicle-tramtrain: nan
|
72 |
+
- Iou Vehicle-motorcycle: 0.0
|
73 |
+
- Iou Vehicle-bicycle: 0.0
|
74 |
+
- Iou Vehicle-caravan: 0.0
|
75 |
+
- Iou Vehicle-cartrailer: 0.0
|
76 |
+
- Iou Construction-building: 0.6305
|
77 |
+
- Iou Construction-door: 0.0
|
78 |
+
- Iou Construction-wall: 0.3016
|
79 |
+
- Iou Construction-fenceguardrail: 0.0580
|
80 |
+
- Iou Construction-bridge: 0.0
|
81 |
+
- Iou Construction-tunnel: nan
|
82 |
+
- Iou Construction-stairs: 0.0
|
83 |
+
- Iou Object-pole: 0.1310
|
84 |
+
- Iou Object-trafficsign: 0.0
|
85 |
+
- Iou Object-trafficlight: 0.0
|
86 |
+
- Iou Nature-vegetation: 0.7954
|
87 |
+
- Iou Nature-terrain: 0.6628
|
88 |
+
- Iou Sky: 0.8233
|
89 |
+
- Iou Void-ground: 0.0
|
90 |
+
- Iou Void-dynamic: 0.0
|
91 |
+
- Iou Void-static: 0.0705
|
92 |
+
- Iou Void-unclear: 0.0
|
93 |
|
94 |
## Model description
|
95 |
|