SkinCancerClassifier_smote-V0

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

SkinCancerClassifier_smote-V0

This model is a fine-tuned version of google/efficientnet-b0 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.6170
• Accuracy: 0.8042

Model description

This model is designed for the classification of skin cancer images and was trained using the SMOTE technique to handle class imbalance. The dataset used for training is from the ISIC 2024 - Skin Cancer Detection with 3D-TBP competition.

Intended uses & limitations

This model is intended for educational purposes and research in skin cancer detection. It should not be used for actual medical diagnosis or treatment planning. Further validation on clinical data is required before any real-world application.

Training and evaluation data

The model was trained on the ISIC 2024 dataset, which contains a diverse set of skin images labeled with different types of skin cancer. The training data was augmented using the SMOTE technique to address class imbalance.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-06
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2000

Training results

The model card is truncated. Read the rest on Hugging Face.