Fashion Clothing Decade

This model predicts what decade clothing is from. It takes an image and outputs one of the following labels: 1910s, 1920s, 1930s, 1940s, 1950s, 1960s, 1970s, 1980s, 1990s, 2000s

Try the demo!

How to use

from transformers import pipeline

pipe = pipeline("image-classification", model="tonyassi/fashion-clothing-decade")
result = pipe('image.png')

print(result)

Dataset

Trained on a total of 2500 images. ~250 images from each label.

1910s

image/jpeg

1920s

image/jpeg

1930s

image/jpeg

1940s

image/jpeg

1950s

image/jpeg

1960s

image/jpeg

1970s

image/jpeg

1980s

image/jpeg

1990s

image/jpeg

2000s

image/jpeg

Model description

This model is a fine-tuned version of google/vit-base-patch16-224-in21k.

Training and evaluation data

  • Loss: 0.8707
  • Accuracy: 0.7505

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • 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

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
23
Safetensors
Model size
85.8M params
Tensor type
F32
Β·
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.

Finetuned from

Spaces using tonyassi/fashion-clothing-decade 3