Brain Tumor CNN Model
This model is a Convolutional Neural Network (CNN) trained to classify brain MRI images into two classes: "yes" (tumor present) and "no" (no tumor). It was trained on the Brain MRI Images for Brain Tumor Detection dataset from Kaggle.
Model Description
This model is a custom CNN built from scratch using PyTorch. It consists of two convolutional layers followed by max-pooling layers and two fully connected layers. The model was trained for 10 epochs with a learning rate of 0.001 using the Adam optimizer.
Intended Uses & Limitations
- Intended Use: This model is intended for educational and research purposes to classify brain MRI images into tumor or no tumor.
- Limitations: The model may not generalize well to MRI images from different sources or with different preprocessing.
Training and Evaluation Data
- Training Data: 70% of the dataset (approximately 2100 images).
- Validation Data: 15% of the dataset (approximately 450 images).
- Test Data: 15% of the dataset (approximately 450 images).
Training Procedure
Training Hyperparameters
- Learning Rate: 0.001
- Batch Size: 32
- Epochs: 10
- Optimizer: Adam
- Loss Function: CrossEntropyLoss
Framework Versions
- PyTorch: 2.0.1
- Transformers: 4.33.1
- Datasets: 2.14.5
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.