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: 0.8850
Validation Loss: 0.7741
Validation Mean Iou: 0.2215
Validation Mean Accuracy: 0.2711
Validation Overall Accuracy: 0.7807
Validation Per Category Iou: [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. ]

Validation Per Category Accuracy: [0. 0.7334003 0.94650286 0.24751216 0.4478931 0.27208929 nan 0.22448353 0.45667969 0. 0.92555657 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. ]

Epoch: 1

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 |

Framework versions

Transformers 4.24.0
TensorFlow 2.9.2
Datasets 2.6.1
Tokenizers 0.13.1