detr-resnet-50-dc5-fashionpedia-finetuned

THIS IS JUST A TEST, THIS MODEL IS NOT GOOD

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: 6.9081
• eval_map: 0.0098
• eval_map_50: 0.0281
• eval_map_75: 0.0
• eval_map_small: 0.0
• eval_map_medium: 0.0
• eval_map_large: 0.0196
• eval_mar_1: 0.0083
• eval_mar_10: 0.0111
• eval_mar_100: 0.0111
• eval_mar_small: 0.0
• eval_mar_medium: 0.0
• eval_mar_large: 0.0222
• eval_map_shirt, blouse: 0.0
• eval_mar_100_shirt, blouse: 0.0
• eval_map_top, t-shirt, sweatshirt: 0.0
• eval_mar_100_top, t-shirt, sweatshirt: 0.0
• eval_map_sweater: -1.0
• eval_mar_100_sweater: -1.0
• eval_map_cardigan: -1.0
• eval_mar_100_cardigan: -1.0
• eval_map_jacket: 0.1767
• eval_mar_100_jacket: 0.2
• eval_map_vest: -1.0
• eval_mar_100_vest: -1.0
• 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_cape: -1.0
• eval_mar_100_cape: -1.0
• eval_map_glasses: 0.0
• eval_mar_100_glasses: 0.0
• eval_map_tie: -1.0
• eval_mar_100_tie: -1.0
• eval_map_glove: -1.0
• eval_mar_100_glove: -1.0
• eval_map_leg warmer: -1.0
• eval_mar_100_leg warmer: -1.0
• eval_map_tights, stockings: 0.0
• eval_mar_100_tights, stockings: 0.0
• eval_map_shoe: 0.0
• eval_mar_100_shoe: 0.0
• 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_applique: -1.0
• eval_mar_100_applique: -1.0
• eval_map_bead: -1.0
• eval_mar_100_bead: -1.0
• eval_map_bow: -1.0
• eval_mar_100_bow: -1.0
• 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_runtime: 4.5194
• eval_samples_per_second: 2.434
• eval_steps_per_second: 0.664
• epoch: 0.4386
• step: 50

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: 1000

Framework versions

• Transformers 4.50.3
• Pytorch 2.2.1
• Datasets 3.5.0
• Tokenizers 0.21.1