metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: efficientnet-b5-Brain_Tumors_Image_Classification
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8020304568527918

efficientnet-b5-Brain_Tumors_Image_Classification

This model is a fine-tuned version of google/efficientnet-b5.

It achieves the following results on the evaluation set:

Loss: 0.9410
Accuracy: 0.8020
F1
- Weighted: 0.7736
- Micro: 0.8020
- Macro: 0.7802
Recall
- Weighted: 0.8020
- Micro: 0.8020
- Macro: 0.7977
Precision
- Weighted: 0.8535
- Micro: 0.8020
- Macro: 0.8682

Model Description

Click here for the code that I used to create this model.

This project is part of a comparison of seventeen (17) transformers. Click here to see the README markdown file for the full project

Intended Uses & Limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training & Evaluation Data

Brain Tumor Image Classification Dataset

Sample Images

Class Distribution of Training Dataset

Class Distribution of Evaluation Dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Weighted F1	Micro F1	Macro F1	Weighted Recall	Micro Recall	Macro Recall	Weighted Precision	Micro Precision	Macro Precision
1.3872	1.0	180	1.0601	0.6853	0.6485	0.6853	0.6550	0.6853	0.6853	0.6802	0.8177	0.6853	0.8330
1.3872	2.0	360	0.9533	0.7843	0.7483	0.7843	0.7548	0.7843	0.7843	0.7819	0.8354	0.7843	0.8471
0.8186	3.0	540	0.9410	0.8020	0.7736	0.8020	0.7802	0.8020	0.8020	0.7977	0.8535	0.8020	0.8682

Framework versions

Transformers 4.28.1
Pytorch 2.0.0
Datasets 2.11.0
Tokenizers 0.13.3