You can deploy this model and start earning money today!

NICOPOI-9/
segformer-b5-finetuned-ade20k-hgo-coord_40epochs_distortion_ver2_global_norm_with_void

Name: segformer-b5-finetuned-ade20k-hgo-coord_40epochs_distortion_ver2_global_norm_with_void
Availability: InStock

generated_from_trainer

NICOPOI-9/segformer-b5-finetuned-ade20k-morphpadver1-hgo-coord_40epochs_distortion_ver2_global_norm

finetune

other

endpoints_compatible

Views

No views yet

segformer-b5-finetuned-ade20k-hgo-coord_40epochs_distortion_ver2_global_norm_with_void

This model is a fine-tuned version of NICOPOI-9/segformer-b5-finetuned-ade20k-morphpadver1-hgo-coord_40epochs_distortion_ver2_global_norm on the NICOPOI-9/Modphad_Perlin_two_void_coord_global_norm dataset. It achieves the following results on the evaluation set:

Loss: 0.6311
Mean Iou: 0.6911
Mean Accuracy: 0.8163
Overall Accuracy: 0.8286
Accuracy [0,0]: 0.7939
Accuracy [0,1]: 0.8321
Accuracy [1,0]: 0.8829
Accuracy [1,1]: 0.8507
Accuracy [0,2]: 0.8508
Accuracy [0,3]: 0.8123
Accuracy [1,2]: 0.7400
Accuracy [1,3]: 0.8753
Accuracy [2,0]: 0.8248
Accuracy [2,1]: 0.7955
Accuracy [2,2]: 0.8149
Accuracy [2,3]: 0.8180
Accuracy [3,0]: 0.8247
Accuracy [3,1]: 0.6637
Accuracy [3,2]: 0.7559
Accuracy [3,3]: 0.8296
Accuracy Void: 0.9120
Iou [0,0]: 0.7079
Iou [0,1]: 0.7563
Iou [1,0]: 0.6888
Iou [1,1]: 0.6479
Iou [0,2]: 0.7244
Iou [0,3]: 0.6633
Iou [1,2]: 0.6849
Iou [1,3]: 0.7019
Iou [2,0]: 0.6984
Iou [2,1]: 0.6967
Iou [2,2]: 0.6674
Iou [2,3]: 0.6785
Iou [3,0]: 0.7044
Iou [3,1]: 0.6013
Iou [3,2]: 0.6736
Iou [3,3]: 0.5709
Iou Void: 0.8820

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:

learning_rate: 6e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy [0,0]	Accuracy [0,1]	Accuracy [1,0]	Accuracy [1,1]	Accuracy [0,2]	Accuracy [0,3]	Accuracy [1,2]	Accuracy [1,3]	Accuracy [2,0]	Accuracy [2,1]	Accuracy [2,2]	Accuracy [2,3]	Accuracy [3,0]	Accuracy [3,1]	Accuracy [3,2]	Accuracy [3,3]	Accuracy Void	Iou [0,0]	Iou [0,1]	Iou [1,0]	Iou [1,1]	Iou [0,2]	Iou [0,3]	Iou [1,2]	Iou [1,3]	Iou [2,0]	Iou [2,1]	Iou [2,2]	Iou [2,3]	Iou [3,0]	Iou [3,1]	Iou [3,2]	Iou [3,3]	Iou Void
0.5689	7.3260	4000	0.9452	0.5040	0.6606	0.6993	0.7091	0.8427	0.8018	0.7929	0.6478	0.6410	0.5079	0.7260	0.5133	0.5678	0.4949	0.5141	0.7155	0.5155	0.5520	0.7735	0.9149	0.5608	0.5653	0.5446	0.5330	0.5264	0.4943	0.4334	0.5497	0.4396	0.4336	0.4078	0.4455	0.5335	0.4221	0.4396	0.4033	0.8360
0.8173	14.6520	8000	0.7003	0.6217	0.7654	0.7838	0.7374	0.8480	0.8475	0.8334	0.7976	0.7906	0.6299	0.8280	0.7217	0.7784	0.7006	0.6688	0.7747	0.6278	0.7141	0.8217	0.8917	0.6370	0.6769	0.6321	0.6150	0.6458	0.6219	0.5592	0.6612	0.6041	0.5702	0.5712	0.5747	0.6088	0.5572	0.6203	0.5551	0.8579
0.5925	21.9780	12000	0.6862	0.6493	0.7872	0.8009	0.7349	0.8587	0.8745	0.8574	0.8111	0.7840	0.7200	0.8547	0.7256	0.7701	0.7584	0.7438	0.7938	0.6107	0.7748	0.8240	0.8854	0.6446	0.7452	0.6555	0.6208	0.6626	0.6337	0.6291	0.6654	0.6211	0.6548	0.6136	0.6445	0.6546	0.5548	0.6200	0.5612	0.8566
0.195	29.3040	16000	0.6138	0.6896	0.8165	0.8283	0.7908	0.8529	0.8958	0.8764	0.8675	0.8016	0.7888	0.8499	0.7803	0.8406	0.7975	0.8032	0.7908	0.7219	0.7600	0.7587	0.9039	0.7050	0.7237	0.6883	0.6719	0.7054	0.6607	0.6947	0.7173	0.6633	0.6986	0.6576	0.6643	0.6869	0.6407	0.6552	0.6147	0.8744
0.1056	36.6300	20000	0.6311	0.6911	0.8163	0.8286	0.7939	0.8321	0.8829	0.8507	0.8508	0.8123	0.7400	0.8753	0.8248	0.7955	0.8149	0.8180	0.8247	0.6637	0.7559	0.8296	0.9120	0.7079	0.7563	0.6888	0.6479	0.7244	0.6633	0.6849	0.7019	0.6984	0.6967	0.6674	0.6785	0.7044	0.6013	0.6736	0.5709	0.8820

Framework versions

Transformers 4.48.3
Pytorch 2.1.0
Datasets 3.2.0
Tokenizers 0.21.0

NICOPOI-9/segformer-b5-finetuned-ade20k-hgo-coord_40epochs_distortion_ver2_global_norm_with_void

segformer-b5-finetuned-ade20k-hgo-coord_40epochs_distortion_ver2_global_norm_with_void

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NICOPOI-9/
segformer-b5-finetuned-ade20k-hgo-coord_40epochs_distortion_ver2_global_norm_with_void