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
46bbddf
·
1 Parent(s): 098b7bf

Training in progress epoch 9

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: 0.4458
18
- - Validation Loss: 0.6356
19
- - Validation Mean Iou: 0.3066
20
- - Validation Mean Accuracy: 0.3759
21
- - Validation Overall Accuracy: 0.8311
22
- - Validation Per Category Iou: [0. 0.66186021 0.83364406 0.48364478 0.53627121 0.27582606
23
- nan 0.35739504 0.41076225 0. 0.77850446 0.
24
- 0. nan 0. 0.50299945 0. 0.
25
- 0.70340595 0.01741996 0.40137463 0.32885851 0. nan
26
- 0. 0.32114603 0.05439069 0. 0.84655176 0.80081688
27
- 0.90314194 0.00292704 0.24599153 0.34524384 0. ]
28
- - Validation Per Category Accuracy: [0. 0.74699777 0.95226432 0.65030589 0.70566846 0.35272168
29
- nan 0.47019568 0.71372001 0. 0.91011138 0.
30
- 0. nan 0. 0.62189092 0. 0.
31
- 0.87945472 0.01742109 0.52016264 0.36958738 0. nan
32
- 0. 0.3993222 0.05508716 0. 0.928178 0.89821483
33
- 0.96116851 0.0033765 0.40579212 0.46633448 0. ]
34
- - Epoch: 8
35
 
36
  ## Model description
37
 
@@ -162,6 +162,17 @@ The following hyperparameters were used during training:
162
  0.87945472 0.01742109 0.52016264 0.36958738 0. nan
163
  0. 0.3993222 0.05508716 0. 0.928178 0.89821483
164
  0.96116851 0.0033765 0.40579212 0.46633448 0. ] | 8 |
 
 
 
 
 
 
 
 
 
 
 
165
 
166
 
167
  ### 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: 0.3970
18
+ - Validation Loss: 0.6094
19
+ - Validation Mean Iou: 0.3154
20
+ - Validation Mean Accuracy: 0.3845
21
+ - Validation Overall Accuracy: 0.8365
22
+ - Validation Per Category Iou: [0. 0.70298046 0.85101569 0.48546331 0.53875077 0.30506197
23
+ nan 0.36967252 0.46956636 0. 0.78487773 0.
24
+ 0. nan 0. 0.54510928 0. 0.
25
+ 0.69555357 0.0474544 0.43944078 0.34243937 0. nan
26
+ 0. 0.31970314 0.07436481 0. 0.84065947 0.79505994
27
+ 0.90045732 0.0134226 0.27125836 0.30161838 0. ]
28
+ - Validation Per Category Accuracy: [0. 0.78336023 0.94550091 0.59681159 0.65835184 0.43832978
29
+ nan 0.56126034 0.72465395 0. 0.92553299 0.
30
+ 0. nan 0. 0.67204825 0. 0.
31
+ 0.84423958 0.04768476 0.62117922 0.41246864 0. nan
32
+ 0. 0.38035291 0.07866878 0. 0.9420769 0.91782163
33
+ 0.95911561 0.01988386 0.38917934 0.38662485 0. ]
34
+ - Epoch: 9
35
 
36
  ## Model description
37
 
 
162
  0.87945472 0.01742109 0.52016264 0.36958738 0. nan
163
  0. 0.3993222 0.05508716 0. 0.928178 0.89821483
164
  0.96116851 0.0033765 0.40579212 0.46633448 0. ] | 8 |
165
+ | 0.3970 | 0.6094 | 0.3154 | 0.3845 | 0.8365 | [0. 0.70298046 0.85101569 0.48546331 0.53875077 0.30506197
166
+ nan 0.36967252 0.46956636 0. 0.78487773 0.
167
+ 0. nan 0. 0.54510928 0. 0.
168
+ 0.69555357 0.0474544 0.43944078 0.34243937 0. nan
169
+ 0. 0.31970314 0.07436481 0. 0.84065947 0.79505994
170
+ 0.90045732 0.0134226 0.27125836 0.30161838 0. ] | [0. 0.78336023 0.94550091 0.59681159 0.65835184 0.43832978
171
+ nan 0.56126034 0.72465395 0. 0.92553299 0.
172
+ 0. nan 0. 0.67204825 0. 0.
173
+ 0.84423958 0.04768476 0.62117922 0.41246864 0. nan
174
+ 0. 0.38035291 0.07866878 0. 0.9420769 0.91782163
175
+ 0.95911561 0.01988386 0.38917934 0.38662485 0. ] | 9 |
176
 
177
 
178
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7296d22da245469f541f0a1edbea989595cec88e7b88389d543dfb8272b18a39
3
  size 15167588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076d1b80c77c6b2726647076e350ffc51b28c9b607b2001e7ff4ea024006e3e2
3
  size 15167588