metadata

license: other
tags:
  - generated_from_keras_callback
model-index:
  - name: sayakpaul/mit-b0-finetuned-sidewalks
    results: []

sayakpaul/mit-b0-finetuned-sidewalks

This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.4936
Validation Loss: 0.6299
Validation Mean Iou: 0.2980
Validation Mean Accuracy: 0.3599
Validation Overall Accuracy: 0.8264
Validation Per Category Iou: [0. 0.66237142 0.83413529 0.50181208 0.52374508 0.34163702 nan 0.35933641 0.43258492 0. 0.76814068 0.

           nan 0.         0.49822203 0.         0.

0.65539745 0. 0.3955574 0.32740018 0. nan 0. 0.31514128 0.04382747 0. 0.84497596 0.79425761 0.89798116 0.00201253 0.18109898 0.15596963 0. ]

Validation Per Category Accuracy: [0. 0.72498823 0.94241029 0.63156495 0.72628664 0.44784858 nan 0.50327208 0.59434829 0. 0.91352866 0.

           nan 0.         0.62105434 0.         0.

0.90132969 0. 0.4624487 0.42016669 0. nan 0. 0.37948533 0.04393027 0. 0.94520928 0.88447616 0.94729824 0.00247937 0.23226938 0.19132714 0. ]

Epoch: 6

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'learning_rate': 6e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Validation Mean Iou	Validation Mean Accuracy	Validation Overall Accuracy	Validation Per Category Iou
1.5309	0.9380	0.1674	0.2153	0.7545	[0.00000000e+00 5.50637719e-01 7.61499932e-01 6.48396077e-04
3.56923200e-01 9.75833116e-02 0.00000000e+00 2.82588573e-02
5.28802378e-02 0.00000000e+00 5.93637894e-01 0.00000000e+00
0.00000000e+00 nan 0.00000000e+00 0.00000000e+00
0.00000000e+00 0.00000000e+00 5.53393589e-01 0.00000000e+00
1.50378244e-01 1.75413833e-02 0.00000000e+00 nan
0.00000000e+00 2.76097981e-02 0.00000000e+00 0.00000000e+00
7.86211179e-01 7.05492777e-01 8.34315629e-01 0.00000000e+00
0.00000000e+00 7.43899822e-03 0.00000000e+00]	[0.00000000e+00 7.08723416e-01 9.71019213e-01 6.48665345e-04
4.09438347e-01 1.09468057e-01 nan 3.05932982e-02
5.44133505e-02 0.00000000e+00 8.74063503e-01 0.00000000e+00
0.00000000e+00 nan 0.00000000e+00 0.00000000e+00
0.00000000e+00 0.00000000e+00 8.66648886e-01 0.00000000e+00
1.61194155e-01 1.77691783e-02 0.00000000e+00 nan
0.00000000e+00 2.81195635e-02 0.00000000e+00 0.00000000e+00
9.17500033e-01 8.30294930e-01 9.02491399e-01 0.00000000e+00
0.00000000e+00 7.77243386e-03 0.00000000e+00]	0
0.8850	0.7741	0.2215	0.2711	0.7807	[0. 0.56319416 0.79436978 0.22447649 0.37746306 0.2182132

    nan 0.17433499 0.35240193 0.         0.64391654 0.

           nan 0.         0.         0.         0.

0.61824159 0. 0.36925143 0.09610409 0. nan 0. 0.23049759 0. 0. 0.79662258 0.72121144 0.85940151 0. 0.00144295 0.04769959 0. ] | [0. 0.7334003 0.94650286 0.24751216 0.4478931 0.27208929 nan 0.22448353 0.45667969 0. 0.92555657 0. 0. nan 0. 0. 0. 0. 0.85871282 0. 0.43579563 0.09928831 0. nan 0. 0.25660062 0. 0. 0.93127726 0.85151776 0.9323404 0. 0.00144459 0.05442322 0. ] | 1 | | 0.7280 | 0.6948 | 0.2608 | 0.3178 | 0.8009 | [0. 0.5833859 0.81088427 0.37870695 0.42920979 0.26901769 nan 0.26967864 0.37309309 0. 0.73143999 0. 0. nan 0. 0.30875952 0. 0. 0.64460152 0. 0.36681761 0.20754432 0. nan 0. 0.27251923 0.01267829 0. 0.82057447 0.76705857 0.86538224 0. 0.13369659 0.09996937 0. ] | [0. 0.71016102 0.95278314 0.44786052 0.50520329 0.32109583 nan 0.37049571 0.63857903 0. 0.88589428 0. 0. nan 0. 0.34012586 0. 0. 0.88972948 0. 0.49551485 0.25354461 0. nan 0. 0.3309279 0.01267829 0. 0.93305477 0.86649237 0.94355496 0. 0.14937745 0.12218876 0. ] | 2 | | 0.6505 | 0.6601 | 0.2774 | 0.3400 | 0.8158 | [0. 0.67274147 0.83098512 0.46721789 0.48492165 0.28810209 nan 0.30676731 0.41116935 0. 0.73679658 0. 0. nan 0. 0.47421792 0. 0. 0.66232704 0. 0.40729478 0.27226345 0. nan 0. 0.22211219 0.00310618 0. 0.81170746 0.73786496 0.88368738 0. 0.07716099 0.12776685 0. ] | [0. 0.80048159 0.93309497 0.558633 0.56439564 0.38053253 nan 0.46424754 0.60183499 0. 0.92479351 0. 0. nan 0. 0.60493457 0. 0. 0.88399244 0. 0.55428873 0.34754253 0. nan 0. 0.25438648 0.00310618 0. 0.90931833 0.91190458 0.94609539 0. 0.08323588 0.15250888 0. ] | 3 | | 0.5810 | 0.6610 | 0.2893 | 0.3501 | 0.8173 | [0. 0.64601276 0.81866457 0.46535767 0.50543168 0.28373075 nan 0.33004533 0.40404147 0. 0.76223358 0. 0. nan 0. 0.52641725 0. 0. 0.65767205 0. 0.39175791 0.25442534 0. nan 0. 0.30521727 0.03951998 0. 0.82740493 0.75297779 0.88342457 0. 0.20580056 0.19670152 0. ] | [0. 0.73558164 0.95660246 0.55532275 0.61966264 0.32151473 nan 0.47707119 0.54010289 0. 0.91394179 0. 0. nan 0. 0.63758616 0. 0. 0.88501875 0. 0.56845175 0.29123233 0. nan 0. 0.38980592 0.03987322 0. 0.92751577 0.84695264 0.93293488 0. 0.32582376 0.23722217 0. ] | 4 | | 0.5288 | 0.6364 | 0.3033 | 0.3717 | 0.8260 | [0. 0.64487768 0.8377146 0.48707167 0.50884928 0.34176886 nan 0.34887555 0.45218372 0. 0.75715898 0. 0. nan 0. 0.5222127 0. 0. 0.69808156 0. 0.42644563 0.35474225 0. nan 0. 0.28867161 0.03742875 0. 0.83332433 0.7818028 0.88638015 0.00137015 0.2124537 0.28445749 0. ] | [0. 0.74189035 0.92893266 0.625763 0.62296571 0.54003942 nan 0.49591369 0.64509343 0. 0.92976992 0. 0. nan 0. 0.66209669 0. 0. 0.86461114 0. 0.54041026 0.4796133 0. nan 0. 0.33899822 0.03746434 0. 0.92987636 0.92582211 0.96099073 0.00151698 0.26040449 0.36377671 0. ] | 5 | | 0.4936 | 0.6299 | 0.2980 | 0.3599 | 0.8264 | [0. 0.66237142 0.83413529 0.50181208 0.52374508 0.34163702 nan 0.35933641 0.43258492 0. 0.76814068 0. 0. nan 0. 0.49822203 0. 0. 0.65539745 0. 0.3955574 0.32740018 0. nan 0. 0.31514128 0.04382747 0. 0.84497596 0.79425761 0.89798116 0.00201253 0.18109898 0.15596963 0. ] | [0. 0.72498823 0.94241029 0.63156495 0.72628664 0.44784858 nan 0.50327208 0.59434829 0. 0.91352866 0. 0. nan 0. 0.62105434 0. 0. 0.90132969 0. 0.4624487 0.42016669 0. nan 0. 0.37948533 0.04393027 0. 0.94520928 0.88447616 0.94729824 0.00247937 0.23226938 0.19132714 0. ] | 6 |

Framework versions

Transformers 4.24.0
TensorFlow 2.9.2
Datasets 2.6.1
Tokenizers 0.13.1