Edit model card

swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification

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

  • Loss: 0.2418
  • Accuracy: 0.9148

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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.4375 0.9836 30 0.4385 0.8564
0.3408 2.0 61 0.2872 0.8978
0.3106 2.9836 91 0.2598 0.9100
0.3167 4.0 122 0.2609 0.9124
0.2533 4.9836 152 0.2426 0.9075
0.256 6.0 183 0.2372 0.9075
0.2492 6.9836 213 0.2418 0.9148
0.2364 8.0 244 0.2352 0.9051
0.2301 8.9836 274 0.2348 0.9075
0.2255 9.8361 300 0.2350 0.8978

Framework versions

  • Transformers 4.42.3
  • Pytorch 1.12.1+cu113
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
24
Safetensors
Model size
27.6M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for djbp/swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification

Finetuned
(469)
this model

Evaluation results