SegFormer_PADDING_x.6

AhamadShaik/SegFormer_PADDING_x.6

SegFormer_PADDING_x.6 is a machine learning model from AhamadShaik. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.

probably proofread and complete it, then remove this comment. --

Downloads · 30 days

16% of all-time downloads

All-time downloads

Public

Repo size

1.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.h515.1 MB · 100%

At a glance

Library: transformers
License: other
Model type: segformer
Access: Public
Created: Mar 30, 2023
Updated: Mar 31, 2023
SHA: e2ec15e0

Model card

From the Hugging Face model README

AhamadShaik/SegFormer_PADDING_x.6

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: 0.0159
Train Dice Coef: 0.8034
Train Iou: 0.6803
Validation Loss: 0.0223
Validation Dice Coef: 0.8606
Validation Iou: 0.7573
Train Lr: 1e-10
Epoch: 99

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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-10, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train Dice Coef	Train Iou	Validation Loss	Validation Dice Coef	Validation Iou	Train Lr	Epoch
0.2116	0.3018	0.1931	0.0863	0.6813	0.5211	1e-04	0
0.0722	0.4966	0.3490	0.0565	0.7560	0.6108	1e-04	1
0.0544	0.5768	0.4227	0.0465	0.7728	0.6368	1e-04	2
0.0446	0.6305	0.4771	0.0379	0.8130	0.6869	1e-04	3
0.0422	0.6479	0.4950	0.0366	0.8005	0.6719	1e-04	4
0.0375	0.6776	0.5273	0.0315	0.8327	0.7155	1e-04	5
0.0351	0.6926	0.5428	0.0311	0.8340	0.7177	1e-04	6
0.0341	0.6967	0.5485	0.0295	0.8377	0.7228	1e-04	7
0.0307	0.7246	0.5794	0.0278	0.8444	0.7328	1e-04	8
0.0318	0.7119	0.5664	0.0278	0.8423	0.7297	1e-04	9
0.0284	0.7362	0.5940	0.0280	0.8435	0.7314	1e-04	10
0.0278	0.7382	0.5979	0.0284	0.8371	0.7232	1e-04	11
0.0268	0.7429	0.6030	0.0261	0.8504	0.7419	1e-04	12
0.0262	0.7464	0.6072	0.0285	0.8408	0.7280	1e-04	13
0.0247	0.7560	0.6189	0.0255	0.8505	0.7419	1e-04	14
0.0244	0.7580	0.6209	0.0249	0.8524	0.7450	1e-04	15
0.0221	0.7719	0.6385	0.0246	0.8503	0.7422	1e-04	16
0.0234	0.7623	0.6261	0.0233	0.8567	0.7516	1e-04	17
0.0253	0.7527	0.6147	0.0258	0.8481	0.7401	1e-04	18
0.0241	0.7597	0.6236	0.0258	0.8430	0.7331	1e-04	19
0.0230	0.7657	0.6310	0.0224	0.8571	0.7522	1e-04	20
0.0210	0.7755	0.6431	0.0220	0.8609	0.7577	1e-04	21
0.0195	0.7867	0.6572	0.0231	0.8578	0.7531	1e-04	22
0.0192	0.7880	0.6592	0.0226	0.8602	0.7568	1e-04	23
0.0185	0.7909	0.6630	0.0231	0.8591	0.7549	1e-04	24
0.0186	0.7906	0.6626	0.0221	0.8590	0.7551	1e-04	25
0.0196	0.7836	0.6531	0.0239	0.8550	0.7491	1e-04	26
0.0177	0.7975	0.6717	0.0223	0.8589	0.7549	5e-06	27
0.0173	0.7979	0.6727	0.0228	0.8585	0.7542	5e-06	28
0.0170	0.7980	0.6731	0.0215	0.8594	0.7556	5e-06	29
0.0168	0.8003	0.6755	0.0213	0.8616	0.7590	5e-06	30
0.0167	0.8016	0.6774	0.0211	0.8614	0.7587	5e-06	31
0.0167	0.8044	0.6807	0.0217	0.8598	0.7562	5e-06	32
0.0167	0.8048	0.6815	0.0211	0.8622	0.7599	5e-06	33
0.0164	0.8013	0.6773	0.0213	0.8621	0.7596	5e-06	34
0.0162	0.8025	0.6790	0.0216	0.8608	0.7578	5e-06	35
0.0163	0.8018	0.6784	0.0212	0.8615	0.7587	5e-06	36
0.0161	0.8043	0.6818	0.0211	0.8627	0.7605	2.5e-07	37
0.0161	0.8025	0.6793	0.0218	0.8604	0.7572	2.5e-07	38
0.0163	0.8039	0.6810	0.0211	0.8618	0.7592	2.5e-07	39
0.0159	0.8044	0.6816	0.0215	0.8622	0.7597	2.5e-07	40
0.0157	0.8068	0.6841	0.0213	0.8612	0.7584	2.5e-07	41
0.0159	0.8063	0.6837	0.0214	0.8615	0.7588	1.25e-08	42
0.0160	0.8040	0.6814	0.0217	0.8609	0.7578	1.25e-08	43
0.0159	0.8072	0.6852	0.0213	0.8616	0.7589	1.25e-08	44
0.0160	0.8062	0.6836	0.0215	0.8611	0.7581	1.25e-08	45
0.0159	0.8045	0.6820	0.0211	0.8623	0.7600	1.25e-08	46
0.0162	0.8027	0.6798	0.0210	0.8622	0.7599	6.25e-10	47
0.0160	0.8039	0.6807	0.0218	0.8606	0.7575	6.25e-10	48
0.0159	0.8093	0.6874	0.0220	0.8601	0.7566	6.25e-10	49
0.0159	0.8072	0.6841	0.0217	0.8622	0.7596	6.25e-10	50
0.0159	0.8045	0.6815	0.0213	0.8614	0.7586	6.25e-10	51
0.0159	0.8111	0.6894	0.0216	0.8615	0.7588	6.25e-10	52
0.0158	0.8066	0.6843	0.0213	0.8617	0.7592	1e-10	53
0.0161	0.8042	0.6813	0.0212	0.8618	0.7592	1e-10	54
0.0163	0.8058	0.6829	0.0221	0.8604	0.7570	1e-10	55
0.0164	0.8017	0.6785	0.0214	0.8612	0.7583	1e-10	56
0.0160	0.8059	0.6827	0.0210	0.8620	0.7595	1e-10	57
0.0162	0.8038	0.6805	0.0216	0.8616	0.7587	1e-10	58
0.0160	0.8022	0.6791	0.0222	0.8598	0.7562	1e-10	59
0.0161	0.8045	0.6812	0.0215	0.8614	0.7585	1e-10	60
0.0159	0.8026	0.6794	0.0213	0.8605	0.7572	1e-10	61
0.0161	0.8069	0.6846	0.0216	0.8608	0.7577	1e-10	62
0.0159	0.8088	0.6873	0.0209	0.8628	0.7607	1e-10	63
0.0161	0.8016	0.6783	0.0212	0.8616	0.7588	1e-10	64
0.0161	0.8031	0.6798	0.0213	0.8612	0.7583	1e-10	65
0.0161	0.8038	0.6811	0.0215	0.8601	0.7566	1e-10	66
0.0160	0.8052	0.6827	0.0216	0.8608	0.7576	1e-10	67
0.0161	0.8051	0.6825	0.0216	0.8610	0.7580	1e-10	68
0.0159	0.8055	0.6826	0.0218	0.8601	0.7568	1e-10	69
0.0159	0.8024	0.6793	0.0212	0.8617	0.7591	1e-10	70
0.0158	0.8043	0.6813	0.0214	0.8608	0.7578	1e-10	71
0.0161	0.8074	0.6850	0.0212	0.8610	0.7579	1e-10	72
0.0161	0.8066	0.6841	0.0216	0.8615	0.7586	1e-10	73
0.0159	0.8065	0.6841	0.0214	0.8611	0.7582	1e-10	74
0.0162	0.8039	0.6808	0.0212	0.8617	0.7591	1e-10	75
0.0160	0.8036	0.6801	0.0214	0.8616	0.7589	1e-10	76
0.0161	0.8100	0.6879	0.0211	0.8619	0.7595	1e-10	77
0.0161	0.8049	0.6816	0.0211	0.8616	0.7590	1e-10	78
0.0161	0.8037	0.6805	0.0221	0.8596	0.7558	1e-10	79
0.0159	0.8044	0.6816	0.0219	0.8615	0.7587	1e-10	80
0.0161	0.8031	0.6796	0.0214	0.8611	0.7581	1e-10	81
0.0160	0.8016	0.6782	0.0209	0.8622	0.7599	1e-10	82
0.0162	0.8040	0.6810	0.0211	0.8623	0.7601	1e-10	83
0.0159	0.8065	0.6844	0.0210	0.8624	0.7602	1e-10	84
0.0159	0.8064	0.6841	0.0216	0.8613	0.7585	1e-10	85
0.0159	0.8068	0.6851	0.0212	0.8626	0.7604	1e-10	86
0.0158	0.8049	0.6822	0.0222	0.8600	0.7564	1e-10	87
0.0161	0.8028	0.6797	0.0210	0.8621	0.7597	1e-10	88
0.0163	0.8050	0.6814	0.0218	0.8602	0.7567	1e-10	89
0.0159	0.8077	0.6858	0.0215	0.8611	0.7582	1e-10	90
0.0159	0.8067	0.6841	0.0213	0.8623	0.7599	1e-10	91
0.0160	0.8064	0.6837	0.0213	0.8615	0.7588	1e-10	92
0.0160	0.8073	0.6847	0.0209	0.8627	0.7606	1e-10	93
0.0159	0.8056	0.6833	0.0214	0.8612	0.7583	1e-10	94
0.0159	0.8073	0.6852	0.0213	0.8616	0.7590	1e-10	95
0.0158	0.8051	0.6832	0.0219	0.8615	0.7587	1e-10	96
0.0161	0.8053	0.6826	0.0220	0.8593	0.7555	1e-10	97
0.0161	0.8059	0.6832	0.0218	0.8608	0.7577	1e-10	98
0.0159	0.8034	0.6803	0.0223	0.8606	0.7573	1e-10	99

Framework versions

Transformers 4.27.4
TensorFlow 2.11.0
Tokenizers 0.13.2

Library: transformers
Type: segformer
License: other
Created: Mar 30, 2023
Updated: Mar 31, 2023