Hugging Face's logo

sayakpaul
/
mit-b0-finetuned-sidewalks

Transformers
TensorFlow
TensorBoard
segformer
generated_from_keras_callback
Inference Endpoints
Model card Files Metrics Community
sayakpaul HF staff commited on
Commit
728c45a
·
1 Parent(s): 8042bb9

Training in progress epoch 1

Browse files
Files changed (2) hide show
  1. README.md +29 -24
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,30 +14,24 @@ 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: 1.5309
18
- - Validation Loss: 0.9380
19
- - Validation Mean Iou: 0.1674
20
- - Validation Mean Accuracy: 0.2153
21
- - Validation Overall Accuracy: 0.7545
22
- - Validation Per Category Iou: [0.00000000e+00 5.50637719e-01 7.61499932e-01 6.48396077e-04
23
- 3.56923200e-01 9.75833116e-02 0.00000000e+00 2.82588573e-02
24
- 5.28802378e-02 0.00000000e+00 5.93637894e-01 0.00000000e+00
25
- 0.00000000e+00 nan 0.00000000e+00 0.00000000e+00
26
- 0.00000000e+00 0.00000000e+00 5.53393589e-01 0.00000000e+00
27
- 1.50378244e-01 1.75413833e-02 0.00000000e+00 nan
28
- 0.00000000e+00 2.76097981e-02 0.00000000e+00 0.00000000e+00
29
- 7.86211179e-01 7.05492777e-01 8.34315629e-01 0.00000000e+00
30
- 0.00000000e+00 7.43899822e-03 0.00000000e+00]
31
- - Validation Per Category Accuracy: [0.00000000e+00 7.08723416e-01 9.71019213e-01 6.48665345e-04
32
- 4.09438347e-01 1.09468057e-01 nan 3.05932982e-02
33
- 5.44133505e-02 0.00000000e+00 8.74063503e-01 0.00000000e+00
34
- 0.00000000e+00 nan 0.00000000e+00 0.00000000e+00
35
- 0.00000000e+00 0.00000000e+00 8.66648886e-01 0.00000000e+00
36
- 1.61194155e-01 1.77691783e-02 0.00000000e+00 nan
37
- 0.00000000e+00 2.81195635e-02 0.00000000e+00 0.00000000e+00
38
- 9.17500033e-01 8.30294930e-01 9.02491399e-01 0.00000000e+00
39
- 0.00000000e+00 7.77243386e-03 0.00000000e+00]
40
- - Epoch: 0
41
 
42
  ## Model description
43
 
@@ -80,6 +74,17 @@ The following hyperparameters were used during training:
80
  0.00000000e+00 2.81195635e-02 0.00000000e+00 0.00000000e+00
81
  9.17500033e-01 8.30294930e-01 9.02491399e-01 0.00000000e+00
82
  0.00000000e+00 7.77243386e-03 0.00000000e+00] | 0 |
 
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
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: 0.8850
18
+ - Validation Loss: 0.7741
19
+ - Validation Mean Iou: 0.2215
20
+ - Validation Mean Accuracy: 0.2711
21
+ - Validation Overall Accuracy: 0.7807
22
+ - Validation Per Category Iou: [0. 0.56319416 0.79436978 0.22447649 0.37746306 0.2182132
23
+ nan 0.17433499 0.35240193 0. 0.64391654 0.
24
+ 0. nan 0. 0. 0. 0.
25
+ 0.61824159 0. 0.36925143 0.09610409 0. nan
26
+ 0. 0.23049759 0. 0. 0.79662258 0.72121144
27
+ 0.85940151 0. 0.00144295 0.04769959 0. ]
28
+ - Validation Per Category Accuracy: [0. 0.7334003 0.94650286 0.24751216 0.4478931 0.27208929
29
+ nan 0.22448353 0.45667969 0. 0.92555657 0.
30
+ 0. nan 0. 0. 0. 0.
31
+ 0.85871282 0. 0.43579563 0.09928831 0. nan
32
+ 0. 0.25660062 0. 0. 0.93127726 0.85151776
33
+ 0.9323404 0. 0.00144459 0.05442322 0. ]
34
+ - Epoch: 1
 
 
 
 
 
 
35
 
36
  ## Model description
37
 
 
74
  0.00000000e+00 2.81195635e-02 0.00000000e+00 0.00000000e+00
75
  9.17500033e-01 8.30294930e-01 9.02491399e-01 0.00000000e+00
76
  0.00000000e+00 7.77243386e-03 0.00000000e+00] | 0 |
77
+ | 0.8850 | 0.7741 | 0.2215 | 0.2711 | 0.7807 | [0. 0.56319416 0.79436978 0.22447649 0.37746306 0.2182132
78
+ nan 0.17433499 0.35240193 0. 0.64391654 0.
79
+ 0. nan 0. 0. 0. 0.
80
+ 0.61824159 0. 0.36925143 0.09610409 0. nan
81
+ 0. 0.23049759 0. 0. 0.79662258 0.72121144
82
+ 0.85940151 0. 0.00144295 0.04769959 0. ] | [0. 0.7334003 0.94650286 0.24751216 0.4478931 0.27208929
83
+ nan 0.22448353 0.45667969 0. 0.92555657 0.
84
+ 0. nan 0. 0. 0. 0.
85
+ 0.85871282 0. 0.43579563 0.09928831 0. nan
86
+ 0. 0.25660062 0. 0. 0.93127726 0.85151776
87
+ 0.9323404 0. 0.00144459 0.05442322 0. ] | 1 |
88
 
89
 
90
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e6aa89dd660c8d75954db782313f985da41c8387e545b725b1e83c6616d1d6f
3
  size 15167588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4189475af3cbb4d6c6c5b538591c7ab45358f3c0c66c840b39066c6bd42974
3
  size 15167588