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
d9166b8
•
1 Parent(s): 0240d39

Training in progress epoch 10

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: 0.3883
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
 
@@ -185,6 +185,17 @@ The following hyperparameters were used during training:
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
 
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: 0.3736
18
+ - Validation Loss: 0.4515
19
+ - Validation Mean Iou: 0.3180
20
+ - Validation Mean Accuracy: 0.3859
21
+ - Validation Overall Accuracy: 0.8600
22
+ - Validation Per Category Iou: [0. 0.77296038 0.8679117 0.60122746 0.84573808 0.42877201
23
+ nan 0.40372521 0.5356554 0. 0.82057963 0.
24
+ 0. 0. 0. 0.48309209 0. 0.
25
+ 0.70156487 0.07165346 0.31172072 0.45383525 0. nan
26
+ 0. 0.26337213 0.07457255 0. 0.85227381 0.7079085
27
+ 0.92271657 0.20363628 0.03853875 0.13249146 0. ]
28
+ - Validation Per Category Accuracy: [0. 0.90081404 0.93156248 0.71723323 0.91251575 0.57187527
29
+ nan 0.53665381 0.74547838 0. 0.93718616 0.
30
+ 0. 0. 0. 0.6410839 0. 0.
31
+ 0.80529967 0.07249561 0.6074764 0.5775282 0. nan
32
+ 0. 0.34898163 0.07545859 0. 0.95221746 0.80297775
33
+ 0.96768443 0.26155608 0.19382562 0.17354842 0. ]
34
+ - Epoch: 10
35
 
36
  ## Model description
37
 
 
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
+ | 0.3736 | 0.4515 | 0.3180 | 0.3859 | 0.8600 | [0. 0.77296038 0.8679117 0.60122746 0.84573808 0.42877201
189
+ nan 0.40372521 0.5356554 0. 0.82057963 0.
190
+ 0. 0. 0. 0.48309209 0. 0.
191
+ 0.70156487 0.07165346 0.31172072 0.45383525 0. nan
192
+ 0. 0.26337213 0.07457255 0. 0.85227381 0.7079085
193
+ 0.92271657 0.20363628 0.03853875 0.13249146 0. ] | [0. 0.90081404 0.93156248 0.71723323 0.91251575 0.57187527
194
+ nan 0.53665381 0.74547838 0. 0.93718616 0.
195
+ 0. 0. 0. 0.6410839 0. 0.
196
+ 0.80529967 0.07249561 0.6074764 0.5775282 0. nan
197
+ 0. 0.34898163 0.07545859 0. 0.95221746 0.80297775
198
+ 0.96768443 0.26155608 0.19382562 0.17354842 0. ] | 10 |
199
 
200
 
201
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70da25d5472419a589e997707d5e27148143e686d303c46e5f5a68ef7dfa185c
3
  size 15167588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8bc192e08a8eb41fb3390ccabb7afe227d1492f957de1904ca6b207bed6432
3
  size 15167588