swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_09

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.2586
• Accuracy: 0.9077
• F1 Score: 0.9093
• Precision: 0.9184
• Sensitivity: 0.9071
• Specificity: 0.9766

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: 1e-05
• train_batch_size: 100
• eval_batch_size: 100
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 400
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Score	Precision	Sensitivity	Specificity
1.4243	0.99	19	1.2818	0.4124	0.3570	0.4910	0.4019	0.8403
1.1046	1.97	38	0.8873	0.6658	0.6584	0.7235	0.6608	0.9117
0.5232	2.96	57	0.5753	0.7671	0.7654	0.8063	0.7631	0.9395
0.3235	4.0	77	0.4476	0.8256	0.8272	0.8496	0.8228	0.9549
0.2586	4.99	96	0.3886	0.8590	0.8608	0.8764	0.8567	0.9638
0.1986	5.97	115	0.3538	0.8641	0.8663	0.8816	0.8624	0.9652
0.166	6.96	134	0.3543	0.8649	0.8668	0.8849	0.8637	0.9655
0.1345	8.0	154	0.3729	0.8586	0.8610	0.8837	0.8571	0.9640
0.1197	8.99	173	0.2879	0.8975	0.8987	0.9098	0.8961	0.9740
0.1033	9.97	192	0.2810	0.8998	0.9013	0.9128	0.8983	0.9746
0.0957	10.96	211	0.3239	0.8802	0.8818	0.8988	0.8795	0.9696
0.085	12.0	231	0.2586	0.9077	0.9093	0.9184	0.9071	0.9766
0.0769	12.99	250	0.2662	0.9018	0.9036	0.9149	0.9011	0.9751
0.0758	13.97	269	0.2830	0.8951	0.8970	0.9102	0.8945	0.9734
0.068	14.96	288	0.2757	0.8967	0.8986	0.9113	0.8960	0.9738
0.0641	16.0	308	0.2743	0.8991	0.9008	0.9136	0.8984	0.9744
0.0623	16.99	327	0.2713	0.8987	0.9001	0.9127	0.8982	0.9743
0.0542	17.97	346	0.2650	0.8987	0.9005	0.9128	0.8980	0.9743
0.0573	18.96	365	0.2709	0.8963	0.8981	0.9112	0.8957	0.9737
0.058	19.74	380	0.2778	0.8947	0.8965	0.9101	0.8942	0.9733

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3