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
f998caa
·
1 Parent(s): 3089cd5

Training in progress epoch 6

Browse files
Files changed (2) hide show
  1. README.md +29 -18
  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: 0.5288
18
- - Validation Loss: 0.6364
19
- - Validation Mean Iou: 0.3033
20
- - Validation Mean Accuracy: 0.3717
21
- - Validation Overall Accuracy: 0.8260
22
- - Validation Per Category Iou: [0. 0.64487768 0.8377146 0.48707167 0.50884928 0.34176886
23
- nan 0.34887555 0.45218372 0. 0.75715898 0.
24
- 0. nan 0. 0.5222127 0. 0.
25
- 0.69808156 0. 0.42644563 0.35474225 0. nan
26
- 0. 0.28867161 0.03742875 0. 0.83332433 0.7818028
27
- 0.88638015 0.00137015 0.2124537 0.28445749 0. ]
28
- - Validation Per Category Accuracy: [0. 0.74189035 0.92893266 0.625763 0.62296571 0.54003942
29
- nan 0.49591369 0.64509343 0. 0.92976992 0.
30
- 0. nan 0. 0.66209669 0. 0.
31
- 0.86461114 0. 0.54041026 0.4796133 0. nan
32
- 0. 0.33899822 0.03746434 0. 0.92987636 0.92582211
33
- 0.96099073 0.00151698 0.26040449 0.36377671 0. ]
34
- - Epoch: 5
35
 
36
  ## Model description
37
 
@@ -129,6 +129,17 @@ The following hyperparameters were used during training:
129
  0.86461114 0. 0.54041026 0.4796133 0. nan
130
  0. 0.33899822 0.03746434 0. 0.92987636 0.92582211
131
  0.96099073 0.00151698 0.26040449 0.36377671 0. ] | 5 |
 
 
 
 
 
 
 
 
 
 
 
132
 
133
 
134
  ### 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: 0.4936
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
 
 
129
  0.86461114 0. 0.54041026 0.4796133 0. nan
130
  0. 0.33899822 0.03746434 0. 0.92987636 0.92582211
131
  0.96099073 0.00151698 0.26040449 0.36377671 0. ] | 5 |
132
+ | 0.4936 | 0.6299 | 0.2980 | 0.3599 | 0.8264 | [0. 0.66237142 0.83413529 0.50181208 0.52374508 0.34163702
133
+ nan 0.35933641 0.43258492 0. 0.76814068 0.
134
+ 0. nan 0. 0.49822203 0. 0.
135
+ 0.65539745 0. 0.3955574 0.32740018 0. nan
136
+ 0. 0.31514128 0.04382747 0. 0.84497596 0.79425761
137
+ 0.89798116 0.00201253 0.18109898 0.15596963 0. ] | [0. 0.72498823 0.94241029 0.63156495 0.72628664 0.44784858
138
+ nan 0.50327208 0.59434829 0. 0.91352866 0.
139
+ 0. nan 0. 0.62105434 0. 0.
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
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:641d3bcb062b66dadefbdb067180d8f4fd346e3784c56f2b434376479352a078
3
  size 15167588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22001204507ac8006fe3952a632515eb4fb9cca41d58e4804df1ae8560ee567c
3
  size 15167588