metadata

license: other
tags:
  - generated_from_keras_callback
model-index:
  - name: AhamadShaik/SegFormer_RESIZE_NLM
    results: []

AhamadShaik/SegFormer_RESIZE_NLM

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

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'learning_rate': 5e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Train Loss	Train Dice Coef	Train Iou	Validation Loss	Validation Dice Coef	Validation Iou	Train Lr	Epoch
0.2282	0.5657	0.4102	0.1322	0.6524	0.4967	1e-04	0
0.1354	0.6853	0.5329	0.0855	0.7853	0.6544	1e-04	1
0.1105	0.7364	0.5924	0.0737	0.8147	0.6916	1e-04	2
0.0985	0.7610	0.6226	0.0632	0.8518	0.7440	1e-04	3
0.0933	0.7745	0.6399	0.0627	0.8455	0.7351	1e-04	4
0.0886	0.7856	0.6535	0.0584	0.8603	0.7566	1e-04	5
0.0831	0.7971	0.6695	0.0559	0.8621	0.7596	1e-04	6
0.0770	0.8107	0.6867	0.0530	0.8726	0.7756	1e-04	7
0.0741	0.8160	0.6942	0.0512	0.8775	0.7832	1e-04	8
0.0750	0.8163	0.6945	0.0581	0.8627	0.7606	1e-04	9
0.0678	0.8306	0.7138	0.0531	0.8719	0.7745	1e-04	10
0.0659	0.8341	0.7196	0.0519	0.8738	0.7781	1e-04	11
0.0626	0.8412	0.7294	0.0496	0.8789	0.7853	1e-04	12
0.0637	0.8383	0.7257	0.0515	0.8772	0.7828	1e-04	13
0.0601	0.8462	0.7367	0.0498	0.8765	0.7814	1e-04	14
0.0573	0.8525	0.7458	0.0474	0.8817	0.7897	1e-04	15
0.0565	0.8520	0.7456	0.0459	0.8850	0.7948	1e-04	16
0.0633	0.8381	0.7262	0.0487	0.8797	0.7868	1e-04	17
0.0558	0.8544	0.7489	0.0476	0.8828	0.7917	1e-04	18
0.0523	0.8617	0.7595	0.0454	0.8872	0.7983	1e-04	19
0.0516	0.8632	0.7617	0.0465	0.8838	0.7934	1e-04	20
0.0515	0.8636	0.7625	0.0494	0.8816	0.7894	1e-04	21
0.0518	0.8630	0.7615	0.0487	0.8836	0.7930	1e-04	22
0.0521	0.8616	0.7595	0.0483	0.8822	0.7908	1e-04	23
0.0510	0.8634	0.7624	0.0501	0.8814	0.7899	1e-04	24