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
0b2de8f
·
1 Parent(s): f998caa

Training in progress epoch 7

Browse files
Files changed (2) hide show
  1. README.md +28 -17
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,24 +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: 0.4936
18
- - Validation Loss: 0.6299
19
  - Validation Mean Iou: 0.2980
20
- - Validation Mean Accuracy: 0.3599
21
- - Validation Overall Accuracy: 0.8264
22
- - Validation Per Category Iou: [0. 0.66237142 0.83413529 0.50181208 0.52374508 0.34163702
23
- nan 0.35933641 0.43258492 0. 0.76814068 0.
24
- 0. nan 0. 0.49822203 0. 0.
25
- 0.65539745 0. 0.3955574 0.32740018 0. nan
26
- 0. 0.31514128 0.04382747 0. 0.84497596 0.79425761
27
- 0.89798116 0.00201253 0.18109898 0.15596963 0. ]
28
- - Validation Per Category Accuracy: [0. 0.72498823 0.94241029 0.63156495 0.72628664 0.44784858
29
- nan 0.50327208 0.59434829 0. 0.91352866 0.
30
- 0. nan 0. 0.62105434 0. 0.
31
- 0.90132969 0. 0.4624487 0.42016669 0. nan
32
- 0. 0.37948533 0.04393027 0. 0.94520928 0.88447616
33
- 0.94729824 0.00247937 0.23226938 0.19132714 0. ]
34
- - Epoch: 6
35
 
36
  ## Model description
37
 
@@ -140,6 +140,17 @@ The following hyperparameters were used during training:
140
  0.90132969 0. 0.4624487 0.42016669 0. nan
141
  0. 0.37948533 0.04393027 0. 0.94520928 0.88447616
142
  0.94729824 0.00247937 0.23226938 0.19132714 0. ] | 6 |
 
 
 
 
 
 
 
 
 
 
 
143
 
144
 
145
  ### 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: 0.4528
18
+ - Validation Loss: 0.6340
19
  - Validation Mean Iou: 0.2980
20
+ - Validation Mean Accuracy: 0.3664
21
+ - Validation Overall Accuracy: 0.8212
22
+ - Validation Per Category Iou: [0. 0.60868123 0.83498291 0.18287132 0.46939835 0.31058578
23
+ nan 0.34162709 0.445366 0. 0.78966215 0.
24
+ 0. nan 0. 0.53583212 0. 0.
25
+ 0.71233622 0.03447214 0.47235409 0.37419598 0. nan
26
+ 0. 0.32268508 0.05312127 0. 0.83874416 0.79217023
27
+ 0.89975806 0.00192312 0.20492869 0.31166384 0. ]
28
+ - Validation Per Category Accuracy: [0. 0.70588336 0.94249106 0.19298309 0.73275474 0.44094168
29
+ nan 0.48341533 0.71859918 0. 0.90854187 0.
30
+ 0. nan 0. 0.6752697 0. 0.
31
+ 0.88312382 0.03451747 0.65575793 0.42127597 0. nan
32
+ 0. 0.39094462 0.05356577 0. 0.95291962 0.86480438
33
+ 0.95973926 0.00251199 0.29803261 0.40525743 0. ]
34
+ - Epoch: 7
35
 
36
  ## Model description
37
 
 
140
  0.90132969 0. 0.4624487 0.42016669 0. nan
141
  0. 0.37948533 0.04393027 0. 0.94520928 0.88447616
142
  0.94729824 0.00247937 0.23226938 0.19132714 0. ] | 6 |
143
+ | 0.4528 | 0.6340 | 0.2980 | 0.3664 | 0.8212 | [0. 0.60868123 0.83498291 0.18287132 0.46939835 0.31058578
144
+ nan 0.34162709 0.445366 0. 0.78966215 0.
145
+ 0. nan 0. 0.53583212 0. 0.
146
+ 0.71233622 0.03447214 0.47235409 0.37419598 0. nan
147
+ 0. 0.32268508 0.05312127 0. 0.83874416 0.79217023
148
+ 0.89975806 0.00192312 0.20492869 0.31166384 0. ] | [0. 0.70588336 0.94249106 0.19298309 0.73275474 0.44094168
149
+ nan 0.48341533 0.71859918 0. 0.90854187 0.
150
+ 0. nan 0. 0.6752697 0. 0.
151
+ 0.88312382 0.03451747 0.65575793 0.42127597 0. nan
152
+ 0. 0.39094462 0.05356577 0. 0.95291962 0.86480438
153
+ 0.95973926 0.00251199 0.29803261 0.40525743 0. ] | 7 |
154
 
155
 
156
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22001204507ac8006fe3952a632515eb4fb9cca41d58e4804df1ae8560ee567c
3
  size 15167588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8646cb606f2ec9def37bd221e0af59c073e1487adfef0e399ff0d6fd5f067f
3
  size 15167588