learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 16
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

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Shirt, blouse	Mar 100 Shirt, blouse	Map Top, t-shirt, sweatshirt	Mar 100 Top, t-shirt, sweatshirt	Map Sweater	Mar 100 Sweater	Map Cardigan	Mar 100 Cardigan	Map Jacket	Mar 100 Jacket	Map Vest	Mar 100 Vest	Map Pants	Mar 100 Pants	Map Shorts	Mar 100 Shorts	Map Skirt	Mar 100 Skirt	Map Coat	Mar 100 Coat	Map Dress	Mar 100 Dress	Map Jumpsuit	Mar 100 Jumpsuit	Map Cape	Mar 100 Cape	Map Glasses	Mar 100 Glasses	Map Hat	Mar 100 Hat	Map Headband, head covering, hair accessory	Mar 100 Headband, head covering, hair accessory	Map Tie	Mar 100 Tie	Map Glove	Mar 100 Glove	Map Watch	Mar 100 Watch	Map Belt	Mar 100 Belt	Map Leg warmer	Mar 100 Leg warmer	Map Tights, stockings	Mar 100 Tights, stockings	Map Sock	Mar 100 Sock	Map Shoe	Mar 100 Shoe	Map Bag, wallet	Mar 100 Bag, wallet	Map Scarf	Mar 100 Scarf	Map Umbrella	Mar 100 Umbrella	Map Hood	Mar 100 Hood	Map Collar	Mar 100 Collar	Map Lapel	Mar 100 Lapel	Map Epaulette	Mar 100 Epaulette	Map Sleeve	Mar 100 Sleeve	Map Pocket	Mar 100 Pocket	Map Neckline	Mar 100 Neckline	Map Buckle	Mar 100 Buckle	Map Zipper	Mar 100 Zipper	Map Applique	Mar 100 Applique	Map Bead	Mar 100 Bead	Map Bow	Mar 100 Bow	Map Flower	Mar 100 Flower	Map Fringe	Mar 100 Fringe	Map Ribbon	Mar 100 Ribbon	Map Rivet	Mar 100 Rivet	Map Ruffle	Mar 100 Ruffle	Map Sequin	Mar 100 Sequin	Map Tassel	Mar 100 Tassel
2.3489	0.4384	5000	2.5424	0.0078	0.0164	0.0067	0.004	0.0111	0.0068	0.0264	0.053	0.0564	0.0202	0.0517	0.0671	0.0	0.0	0.0185	0.1932	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0497	0.5615	0.0	0.0	0.0	0.0	0.0	0.0	0.089	0.6732	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1391	0.4866	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0384	0.417	0.0001	0.0289	0.0232	0.2333	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3.1423	0.8767	10000	2.3991	0.0109	0.0212	0.0099	0.0052	0.0152	0.0094	0.0333	0.0612	0.0641	0.0219	0.0593	0.0779	0.0	0.0	0.0267	0.3125	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0805	0.6679	0.0	0.0	0.0099	0.0063	0.0	0.0	0.1037	0.7209	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1858	0.4936	0.0003	0.0023	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0607	0.4527	0.0001	0.0437	0.0348	0.2492	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

Framework versions

Transformers 4.49.0
Pytorch 2.7.0+cu126
Datasets 3.3.2
Tokenizers 0.21.0

YANG-12/detr-resnet-50-dc5-fashionpedia-finetuned

detr-resnet-50-dc5-fashionpedia-finetuned

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

YANG-12/
detr-resnet-50-dc5-fashionpedia-finetuned