Hugging Face's logo

nateraw
/
mit-b0-finetuned-sidewalks-v2

Transformers
TensorFlow
segformer
generated_from_keras_callback
Inference Endpoints
Model card Files Community
nateraw commited on
Commit
0240d39
•
1 Parent(s): bcea238

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: 0.4193
18
- - Validation Loss: 0.4487
19
- - Validation Mean Iou: 0.3073
20
- - Validation Mean Accuracy: 0.3633
21
- - Validation Overall Accuracy: 0.8594
22
- - Validation Per Category Iou: [0. 0.77081114 0.86089485 0.64464211 0.82962632 0.36186873
23
- nan 0.39092332 0.5399988 0. 0.81734925 0.
24
- 0. 0. 0. 0.50271555 0. 0.
25
- 0.70239658 0. 0.30875695 0.52195319 0. nan
26
- 0. 0.20124517 0.00696273 0. 0.84526591 0.72563399
27
- 0.91703372 0. 0.03526147 0.15693635 0. ]
28
- - Validation Per Category Accuracy: [0. 0.8654775 0.95711297 0.70665759 0.93130714 0.42436958
29
- nan 0.52892143 0.69243377 0. 0.91682626 0.
30
- 0. 0. 0. 0.62315913 0. 0.
31
- 0.86251114 0. 0.5607807 0.70416055 0. nan
32
- 0. 0.24483525 0.00698305 0. 0.921099 0.81848055
33
- 0.96789871 0. 0.06891948 0.18778302 0. ]
34
- - Epoch: 8
35
 
36
  ## Model description
37
 
@@ -174,6 +174,17 @@ The following hyperparameters were used during training:
174
  0.86251114 0. 0.5607807 0.70416055 0. nan
175
  0. 0.24483525 0.00698305 0. 0.921099 0.81848055
176
  0.96789871 0. 0.06891948 0.18778302 0. ] | 8 |
 
 
 
 
 
 
 
 
 
 
 
177
 
178
 
179
  ### 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: 0.3883
18
+ - Validation Loss: 0.4824
19
+ - Validation Mean Iou: 0.3086
20
+ - Validation Mean Accuracy: 0.3690
21
+ - Validation Overall Accuracy: 0.8527
22
+ - Validation Per Category Iou: [0. 0.76454291 0.86544951 0.70501066 0.77912256 0.39088976
23
+ nan 0.40275725 0.53334923 0. 0.82777802 0.
24
+ 0. 0. 0. 0.49916177 0. 0.
25
+ 0.68780083 0.01500768 0.31589145 0.53805504 0. nan
26
+ 0. 0.22450413 0.03544121 0. 0.82663975 0.60689445
27
+ 0.91513911 0.12702194 0.0163284 0.10604071 0. ]
28
+ - Validation Per Category Accuracy: [0. 0.86846682 0.93345513 0.77258597 0.90365389 0.54440067
29
+ nan 0.51997559 0.73323435 0. 0.92499729 0.
30
+ 0. 0. 0. 0.62015064 0. 0.
31
+ 0.8190305 0.01503264 0.61258781 0.62514291 0. nan
32
+ 0. 0.28141855 0.03574903 0. 0.95838638 0.66828866
33
+ 0.96505306 0.19804095 0.04463913 0.1315269 0. ]
34
+ - Epoch: 9
35
 
36
  ## Model description
37
 
 
174
  0.86251114 0. 0.5607807 0.70416055 0. nan
175
  0. 0.24483525 0.00698305 0. 0.921099 0.81848055
176
  0.96789871 0. 0.06891948 0.18778302 0. ] | 8 |
177
+ | 0.3883 | 0.4824 | 0.3086 | 0.3690 | 0.8527 | [0. 0.76454291 0.86544951 0.70501066 0.77912256 0.39088976
178
+ nan 0.40275725 0.53334923 0. 0.82777802 0.
179
+ 0. 0. 0. 0.49916177 0. 0.
180
+ 0.68780083 0.01500768 0.31589145 0.53805504 0. nan
181
+ 0. 0.22450413 0.03544121 0. 0.82663975 0.60689445
182
+ 0.91513911 0.12702194 0.0163284 0.10604071 0. ] | [0. 0.86846682 0.93345513 0.77258597 0.90365389 0.54440067
183
+ nan 0.51997559 0.73323435 0. 0.92499729 0.
184
+ 0. 0. 0. 0.62015064 0. 0.
185
+ 0.8190305 0.01503264 0.61258781 0.62514291 0. nan
186
+ 0. 0.28141855 0.03574903 0. 0.95838638 0.66828866
187
+ 0.96505306 0.19804095 0.04463913 0.1315269 0. ] | 9 |
188
 
189
 
190
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e63d034662ba8c744c7eb1e9a8e53c427ff6af286ff57083994304ee36f4bc93
3
  size 15167588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70da25d5472419a589e997707d5e27148143e686d303c46e5f5a68ef7dfa185c
3
  size 15167588