detr-resnet-50-dc5-fashionpedia-finetuned

This model is a fine-tuned version of facebook/detr-resnet-50-dc5 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 4.9164
• eval_map: 0.0135
• eval_map_50: 0.0332
• eval_map_75: 0.0009
• eval_map_small: 0.0421
• eval_map_medium: 0.0229
• eval_map_large: 0.0056
• eval_mar_1: 0.0139
• eval_mar_10: 0.0241
• eval_mar_100: 0.0241
• eval_mar_small: 0.0417
• eval_mar_medium: 0.0341
• eval_mar_large: 0.0185
• eval_map_shirt, blouse: 0.0
• eval_mar_100_shirt, blouse: 0.0
• eval_map_top, t-shirt, sweatshirt: 0.0163
• eval_mar_100_top, t-shirt, sweatshirt: 0.1
• eval_map_cardigan: -1.0
• eval_mar_100_cardigan: -1.0
• eval_map_jacket: 0.0
• eval_mar_100_jacket: 0.0
• eval_map_pants: 0.0
• eval_mar_100_pants: 0.0
• eval_map_shorts: 0.0
• eval_mar_100_shorts: 0.0
• eval_map_skirt: 0.0
• eval_mar_100_skirt: 0.0
• eval_map_coat: 0.0
• eval_mar_100_coat: 0.0
• eval_map_dress: 0.0
• eval_mar_100_dress: 0.0
• eval_map_glasses: 0.0
• eval_mar_100_glasses: 0.0
• eval_map_hat: -1.0
• eval_mar_100_hat: -1.0
• eval_map_glove: -1.0
• eval_mar_100_glove: -1.0
• eval_map_belt: -1.0
• eval_mar_100_belt: -1.0
• eval_map_tights, stockings: 0.0
• eval_mar_100_tights, stockings: 0.0
• eval_map_shoe: 0.2259
• eval_mar_100_shoe: 0.3333
• eval_map_bag, wallet: -1.0
• eval_mar_100_bag, wallet: -1.0
• eval_map_scarf: -1.0
• eval_mar_100_scarf: -1.0
• eval_map_umbrella: 0.0
• eval_mar_100_umbrella: 0.0
• eval_map_hood: -1.0
• eval_mar_100_hood: -1.0
• eval_map_collar: 0.0
• eval_mar_100_collar: 0.0
• eval_map_lapel: 0.0
• eval_mar_100_lapel: 0.0
• eval_map_sleeve: 0.0
• eval_mar_100_sleeve: 0.0
• eval_map_pocket: 0.0
• eval_mar_100_pocket: 0.0
• eval_map_neckline: 0.0
• eval_mar_100_neckline: 0.0
• eval_map_buckle: -1.0
• eval_mar_100_buckle: -1.0
• eval_map_zipper: 0.0
• eval_mar_100_zipper: 0.0
• eval_map_fringe: -1.0
• eval_mar_100_fringe: -1.0
• eval_map_ribbon: -1.0
• eval_mar_100_ribbon: -1.0
• eval_map_rivet: -1.0
• eval_mar_100_rivet: -1.0
• eval_map_tassel: -1.0
• eval_mar_100_tassel: -1.0
• eval_runtime: 1.7311
• eval_samples_per_second: 6.354
• eval_steps_per_second: 1.733
• epoch: 1.3158
• step: 150

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 10000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.46.3
• Pytorch 1.12.1+cu116
• Datasets 3.1.0
• Tokenizers 0.20.3