nateraw commited on
Commit
4c01f6d
1 Parent(s): dc0ba28

Training in progress epoch 28

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: 0.2146
18
- - Validation Loss: 0.4515
19
- - Validation Mean Iou: 0.3472
20
- - Validation Mean Accuracy: 0.4129
21
- - Validation Overall Accuracy: 0.8760
22
- - Validation Per Category Iou: [0. 0.77768215 0.87939478 0.75655563 0.85872515 0.51912277
23
- nan 0.47242163 0.57270343 0.04912978 0.84772409 0.04133148
24
- 0. 0.28216704 0. 0.50142357 0. 0.
25
- 0.72646668 0.08708308 0.41888468 0.46264328 0. nan
26
- 0.00952928 0.24906863 0.23188316 0. 0.86985544 0.75426408
27
- 0.93570207 0. 0.00161353 0.15174018 0. ]
28
- - Validation Per Category Accuracy: [0. 0.91082524 0.9223558 0.86526048 0.93459861 0.70221741
29
- nan 0.61752143 0.76844318 0.064682 0.94790176 0.04432765
30
- 0. 0.38675743 0. 0.58171337 0. 0.
31
- 0.86150488 0.08919156 0.64534791 0.76292334 0. nan
32
- 0.01094578 0.29978017 0.26035297 0. 0.9390376 0.84793111
33
- 0.96900737 0. 0.00383813 0.18862775 0. ]
34
- - Epoch: 27
35
 
36
  ## Model description
37
 
@@ -419,6 +419,17 @@ The following hyperparameters were used during training:
419
  0.86150488 0.08919156 0.64534791 0.76292334 0. nan
420
  0.01094578 0.29978017 0.26035297 0. 0.9390376 0.84793111
421
  0.96900737 0. 0.00383813 0.18862775 0. ] | 27 |
 
 
 
 
 
 
 
 
 
 
 
422
 
423
 
424
  ### 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: 0.2245
18
+ - Validation Loss: 0.4819
19
+ - Validation Mean Iou: 0.3481
20
+ - Validation Mean Accuracy: 0.4183
21
+ - Validation Overall Accuracy: 0.8677
22
+ - Validation Per Category Iou: [0. 0.74754716 0.87589221 0.7595096 0.75176585 0.46424109
23
+ nan 0.43492805 0.55661905 0.04973311 0.85506372 0.1407866
24
+ 0. 0.15455217 0. 0.4863142 0. 0.
25
+ 0.72532016 0.16110796 0.37871237 0.54738549 0. nan
26
+ 0.03596414 0.27015132 0.27383189 0. 0.87155837 0.74696253
27
+ 0.93097913 0.03859201 0.03974808 0.19051036 0. ]
28
+ - Validation Per Category Accuracy: [0. 0.92496748 0.93198417 0.91066332 0.76595448 0.59939476
29
+ nan 0.57168392 0.76530022 0.06892197 0.94636898 0.19843316
30
+ 0. 0.30218647 0. 0.5681646 0. 0.
31
+ 0.83417317 0.18737447 0.68308592 0.66512645 0. nan
32
+ 0.03932127 0.32249168 0.30377988 0. 0.94566641 0.86854326
33
+ 0.97023299 0.04389577 0.11848144 0.26846741 0. ]
34
+ - Epoch: 28
35
 
36
  ## Model description
37
 
 
419
  0.86150488 0.08919156 0.64534791 0.76292334 0. nan
420
  0.01094578 0.29978017 0.26035297 0. 0.9390376 0.84793111
421
  0.96900737 0. 0.00383813 0.18862775 0. ] | 27 |
422
+ | 0.2245 | 0.4819 | 0.3481 | 0.4183 | 0.8677 | [0. 0.74754716 0.87589221 0.7595096 0.75176585 0.46424109
423
+ nan 0.43492805 0.55661905 0.04973311 0.85506372 0.1407866
424
+ 0. 0.15455217 0. 0.4863142 0. 0.
425
+ 0.72532016 0.16110796 0.37871237 0.54738549 0. nan
426
+ 0.03596414 0.27015132 0.27383189 0. 0.87155837 0.74696253
427
+ 0.93097913 0.03859201 0.03974808 0.19051036 0. ] | [0. 0.92496748 0.93198417 0.91066332 0.76595448 0.59939476
428
+ nan 0.57168392 0.76530022 0.06892197 0.94636898 0.19843316
429
+ 0. 0.30218647 0. 0.5681646 0. 0.
430
+ 0.83417317 0.18737447 0.68308592 0.66512645 0. nan
431
+ 0.03932127 0.32249168 0.30377988 0. 0.94566641 0.86854326
432
+ 0.97023299 0.04389577 0.11848144 0.26846741 0. ] | 28 |
433
 
434
 
435
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:197db73568e0b0916be2a60f6fbfc90d8a6ef2c2d81fdf01bc26578050285ddf
3
  size 15167588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a690f664ae42c286f59c0a4144cdf5c8348ff852bd36fcde04c96d72b9eb10bf
3
  size 15167588