segformer-class-classWeights-augmentation

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1855
Accuracy: 0.9655
F1: 0.9647
Precision: 0.9674
Recall: 0.9655
Learning Rate: 0.0000

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: 5e-05
train_batch_size: 10
eval_batch_size: 10
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 40
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.89	6	0.1113	0.9655	0.9647	0.9674	0.9655
0.1153	1.93	13	0.0929	0.9655	0.9647	0.9674	0.9655
0.2246	2.96	20	0.1026	0.9655	0.9647	0.9674	0.9655
0.2246	4.0	27	0.0391	0.9655	0.9647	0.9674	0.9655
0.1433	4.89	33	0.0673	0.9655	0.9647	0.9674	0.9655
0.1816	5.93	40	0.0794	0.9655	0.9647	0.9674	0.9655
0.1816	6.96	47	0.0687	0.9655	0.9647	0.9674	0.9655
0.1448	8.0	54	0.1123	0.9655	0.9647	0.9674	0.9655
0.1124	8.89	60	0.1855	0.9655	0.9647	0.9674	0.9655

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

Loading…

usamaaleem99tech/segformer-class-classWeights-augmentation

segformer-class-classWeights-augmentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

segformer-class-classWeights-augmentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions