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: 2.8759
• eval_map: 0.004
• eval_map_50: 0.0097
• eval_map_75: 0.0027
• eval_map_small: 0.0029
• eval_map_medium: 0.0049
• eval_map_large: 0.0018
• eval_mar_1: 0.0097
• eval_mar_10: 0.0225
• eval_mar_100: 0.0289
• eval_mar_small: 0.0163
• eval_mar_medium: 0.0303
• eval_mar_large: 0.0376
• eval_map_shirt, blouse: 0.0
• eval_mar_100_shirt, blouse: 0.0
• eval_map_top, t-shirt, sweatshirt: 0.0009
• eval_mar_100_top, t-shirt, sweatshirt: 0.0029
• eval_map_sweater: 0.0
• eval_mar_100_sweater: 0.0
• eval_map_cardigan: 0.0
• eval_mar_100_cardigan: 0.0
• eval_map_jacket: 0.0
• eval_mar_100_jacket: 0.0
• eval_map_vest: 0.0
• eval_mar_100_vest: 0.0
• eval_map_pants: 0.0053
• eval_mar_100_pants: 0.0325
• 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: 0.0311
• eval_mar_100_dress: 0.2667
• eval_map_jumpsuit: 0.0
• eval_mar_100_jumpsuit: 0.0
• eval_map_cape: 0.0
• eval_mar_100_cape: 0.0
• eval_map_glasses: 0.0
• eval_mar_100_glasses: 0.0
• eval_map_hat: 0.0
• eval_mar_100_hat: 0.0
• eval_map_headband, head covering, hair accessory: 0.0
• eval_mar_100_headband, head covering, hair accessory: 0.0
• eval_map_tie: 0.0
• eval_mar_100_tie: 0.0
• eval_map_glove: 0.0
• eval_mar_100_glove: 0.0
• eval_map_watch: 0.0
• eval_mar_100_watch: 0.0
• eval_map_belt: 0.0
• eval_mar_100_belt: 0.0
• eval_map_leg warmer: 0.0
• eval_mar_100_leg warmer: 0.0
• eval_map_tights, stockings: 0.0
• eval_mar_100_tights, stockings: 0.0
• eval_map_sock: 0.0
• eval_mar_100_sock: 0.0
• eval_map_shoe: 0.1184
• eval_mar_100_shoe: 0.4574
• eval_map_bag, wallet: 0.0
• eval_mar_100_bag, wallet: 0.0
• eval_map_scarf: 0.0
• eval_mar_100_scarf: 0.0
• eval_map_umbrella: 0.0
• eval_mar_100_umbrella: 0.0
• eval_map_hood: 0.0
• eval_mar_100_hood: 0.0
• eval_map_collar: 0.0
• eval_mar_100_collar: 0.0
• eval_map_lapel: 0.0
• eval_mar_100_lapel: 0.0
• eval_map_epaulette: 0.0
• eval_mar_100_epaulette: 0.0
• eval_map_sleeve: 0.0091
• eval_mar_100_sleeve: 0.3887
• eval_map_pocket: 0.0
• eval_mar_100_pocket: 0.0
• eval_map_neckline: 0.018
• eval_mar_100_neckline: 0.1796
• eval_map_buckle: 0.0
• eval_mar_100_buckle: 0.0
• eval_map_zipper: 0.0
• eval_mar_100_zipper: 0.0
• eval_map_applique: 0.0
• eval_mar_100_applique: 0.0
• eval_map_bead: 0.0
• eval_mar_100_bead: 0.0
• eval_map_bow: 0.0
• eval_mar_100_bow: 0.0
• eval_map_flower: 0.0
• eval_mar_100_flower: 0.0
• eval_map_fringe: 0.0
• eval_mar_100_fringe: 0.0
• eval_map_ribbon: 0.0
• eval_mar_100_ribbon: 0.0
• eval_map_rivet: 0.0
• eval_mar_100_rivet: 0.0
• eval_map_ruffle: 0.0
• eval_mar_100_ruffle: 0.0
• eval_map_sequin: 0.0
• eval_mar_100_sequin: 0.0
• eval_map_tassel: 0.0
• eval_mar_100_tassel: 0.0
• eval_runtime: 235.9187
• eval_samples_per_second: 4.908
• eval_steps_per_second: 1.229
• epoch: 0.1622
• step: 1850

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 OptimizerNames.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 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0