README.md

metadata

license: apache-2.0
base_model: microsoft/resnet-50
tags:
  - code
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: my__model
    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: 0.44188861985472155
pipeline_tag: image-classification

my__model

This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. with specialised focus on kneeosteoarthritis data. It achieves the following results on the evaluation set:

• Loss: 1.3439
• Accuracy: 0.4419

Model description

model built to refine the classification with specialised focus on kneeosteoarthritis data. for medical data related to similar domains can use the same to finetune further.

Intended uses & limitations

More information needed

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3665	1.0	104	1.3439	0.4419

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1