kbullock's picture
Create README.md
ccb3b86 verified
metadata
datasets:
  - hieupth/cad
  - shreyanshu09/Block_Diagram
  - krowiemlekommm/PJN_CHARTS
  - corto-ai/handwritten-text
  - katanaml-org/invoices-donut-data-v1
  - mathieu1256/FATURA2-invoices
  - AjitRawat/invoice
  - HuggingFaceM4/DocumentVQA
  - ajaynmopidevi/DocumentIDEFICS_QA
  - daitavan/financial-documents
  - Anas989898/Vision-OCR-Financial-Reports-10k
  - dpdl-benchmark/places100-easy
  - xirigh/people
  - huggan/flowers-102-categories
  - iamkaikai/amazing_logos
  - iamkaikai/amazing_logos_v2
  - manelreghima/companies_logos
  - samp3209/logo-dataset
  - salmonhumorous/logo-blip-caption
  - dream-textures/textures-color-1k
  - GATE-engine/describable_textures
  - ppierzc/ios-app-icons
  - Lancelot53/android_icon_dataset
  - naxalpha/stable-icons-128
  - yaneivan/memes_caption
  - Bruece/office-home-clipart-caption
base_model:
  - timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k

fine_tuned_image_relevance_model

This model is a fine-tuned version of resnext50_32x4d.fb_swsl_ig1b_ft_in1k on an aggregated dataset of images that were classified as relevant (1.0) or irrelevant (0.0). It achieves the following results on the validation set:

  • Loss: 0.1032
  • Accuracy: 0.9936

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 4e-06
  • train_batch_size: 8
  • valid_batch_size: 8
  • seed: seed not explicitly set
  • optimizer: torch.optim.AdamW(resnet_model.parameters(), lr=lr, eps=0.000001)
  • lr_scheduler_type: OneCycleLR
  • num_epochs: 6

Training results

Training Loss Epoch Validation Loss Accuracy
0.5536 1 0.3270 0.9856
0.3176 2 0.1720 0.9922
0.1887 3 0.1332 0.9944
0.1280 4 0.1146 0.9938
0.1116 5 0.1236 0.9938
0.1016 6 0.1032 0.9936

Framework versions

  • timm 1.0.19
  • PyTorch 2.8.0+cpu
  • Datasets 4.0.0