benjamintli/rt-detr-v2_coco2017-5k

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

rt-detr-v2_coco2017-5k

This model is a fine-tuned version of PekingU/rtdetr_v2_r101vd on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 9.3999
• —Map: 0.5327
• —Map 50: 0.6888
• —Map 75: 0.5731
• —Map Small: 0.2833
• —Map Medium: 0.4621
• —Map Large: 0.687
• —Mar 1: 0.4388
• —Mar 10: 0.6686
• —Mar 100: 0.7222
• —Mar Small: 0.4796
• —Mar Medium: 0.6884
• —Mar Large: 0.8249
• —Map Person: 0.5836
• —Mar 100 Person: 0.707
• —Map Bicycle: 0.2904
• —Mar 100 Bicycle: 0.54
• —Map Car: 0.5271
• —Mar 100 Car: 0.6508
• —Map Motorcycle: 0.448
• —Mar 100 Motorcycle: 0.5857
• —Map Airplane: 0.84
• —Mar 100 Airplane: 0.9143
• —Map Bus: 0.8964
• —Mar 100 Bus: 0.925
• —Map Train: 0.7502
• —Mar 100 Train: 0.8
• —Map Truck: 0.4752
• —Mar 100 Truck: 0.775
• —Map Boat: 0.296
• —Mar 100 Boat: 0.5673
• —Map Traffic light: 0.3745
• —Mar 100 Traffic light: 0.5104
• —Map Fire hydrant: -1.0
• —Mar 100 Fire hydrant: -1.0
• —Map Stop sign: 0.8178
• —Mar 100 Stop sign: 0.8375
• —Map Parking meter: 0.1125
• —Mar 100 Parking meter: 0.9
• —Map Bench: 0.4415
• —Mar 100 Bench: 0.7
• —Map Bird: 1.0
• —Mar 100 Bird: 1.0
• —Map Cat: 0.8285
• —Mar 100 Cat: 0.8769
• —Map Dog: 0.9249
• —Mar 100 Dog: 0.9273
• —Map Horse: 0.9026
• —Mar 100 Horse: 0.94
• —Map Sheep: 0.7792
• —Mar 100 Sheep: 0.8143
• —Map Cow: 0.7586
• —Mar 100 Cow: 0.8667
• —Map Elephant: 0.508
• —Mar 100 Elephant: 0.7778
• —Map Bear: 0.9337
• —Mar 100 Bear: 0.9333
• —Map Zebra: 0.6353
• —Mar 100 Zebra: 0.7636
• —Map Giraffe: 0.875
• —Mar 100 Giraffe: 0.9
• —Map Backpack: 0.2317
• —Mar 100 Backpack: 0.4111
• —Map Umbrella: 0.5165
• —Mar 100 Umbrella: 0.7882
• —Map Handbag: 0.2554
• —Mar 100 Handbag: 0.536
• —Map Tie: 0.2376
• —Mar 100 Tie: 0.32
• —Map Suitcase: 0.5525
• —Mar 100 Suitcase: 0.7437
• —Map Frisbee: 0.9554
• —Mar 100 Frisbee: 0.9667
• —Map Skis: 0.3611
• —Mar 100 Skis: 0.6125
• —Map Snowboard: 0.467
• —Mar 100 Snowboard: 0.7714
• —Map Sports ball: 0.3292
• —Mar 100 Sports ball: 0.4636
• —Map Kite: 0.4922
• —Mar 100 Kite: 0.7278
• —Map Baseball bat: 0.6464
• —Mar 100 Baseball bat: 0.85
• —Map Baseball glove: 0.3074
• —Mar 100 Baseball glove: 0.4187
• —Map Skateboard: 0.8671
• —Mar 100 Skateboard: 0.9
• —Map Surfboard: 0.4045
• —Mar 100 Surfboard: 0.6273
• —Map Tennis racket: 0.5949
• —Mar 100 Tennis racket: 0.7111
• —Map Bottle: 0.4412
• —Mar 100 Bottle: 0.6444
• —Map Wine glass: 0.6175
• —Mar 100 Wine glass: 0.75
• —Map Cup: 0.6221
• —Mar 100 Cup: 0.8314
• —Map Fork: 0.7218
• —Mar 100 Fork: 0.7714
• —Map Knife: 0.6039
• —Mar 100 Knife: 0.8556
• —Map Spoon: 0.1839
• —Mar 100 Spoon: 0.44
• —Map Bowl: 0.5203
• —Mar 100 Bowl: 0.816
• —Map Banana: 0.2206
• —Mar 100 Banana: 0.7318
• —Map Apple: 0.1947
• —Mar 100 Apple: 0.5643
• —Map Sandwich: 0.4644
• —Mar 100 Sandwich: 0.7455
• —Map Orange: 0.2901
• —Mar 100 Orange: 0.6211
• —Map Broccoli: 0.5369
• —Mar 100 Broccoli: 0.7357
• —Map Carrot: 0.5171
• —Mar 100 Carrot: 0.8
• —Map Hot dog: 0.3502
• —Mar 100 Hot dog: 0.5556
• —Map Pizza: 0.9161
• —Mar 100 Pizza: 0.94
• —Map Donut: -1.0
• —Mar 100 Donut: -1.0
• —Map Cake: 0.7348
• —Mar 100 Cake: 0.85
• —Map Chair: 0.4139
• —Mar 100 Chair: 0.6271
• —Map Couch: 0.4798
• —Mar 100 Couch: 0.8636
• —Map Potted plant: 0.22
• —Mar 100 Potted plant: 0.51
• —Map Bed: 0.4983
• —Mar 100 Bed: 0.9167
• —Map Dining table: 0.3962
• —Mar 100 Dining table: 0.6281
• —Map Toilet: 0.422
• —Mar 100 Toilet: 0.6765
• —Map Tv: 0.82
• —Mar 100 Tv: 0.9077
• —Map Laptop: 0.7589
• —Mar 100 Laptop: 0.8556
• —Map Mouse: 0.7566
• —Mar 100 Mouse: 0.8
• —Map Remote: 0.5195
• —Mar 100 Remote: 0.7476
• —Map Keyboard: 0.7419
• —Mar 100 Keyboard: 0.875
• —Map Cell phone: 0.2701
• —Mar 100 Cell phone: 0.4895
• —Map Microwave: 0.6594
• —Mar 100 Microwave: 0.8
• —Map Oven: 0.5557
• —Mar 100 Oven: 0.8333
• —Map Toaster: -1.0
• —Mar 100 Toaster: -1.0
• —Map Sink: 0.6079
• —Mar 100 Sink: 0.63
• —Map Refrigerator: 0.6643
• —Mar 100 Refrigerator: 0.8714
• —Map Book: 0.11
• —Mar 100 Book: 0.4355
• —Map Clock: 0.3861
• —Mar 100 Clock: 0.5706
• —Map Vase: 0.4955
• —Mar 100 Vase: 0.7722
• —Map Scissors: 0.4891
• —Mar 100 Scissors: 0.5667
• —Map Teddy bear: 0.0662
• —Mar 100 Teddy bear: 0.8
• —Map Hair drier: -1.0
• —Mar 100 Hair drier: -1.0
• —Map Toothbrush: 0.0
• —Mar 100 Toothbrush: 0.0

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: 5e-05
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 300
• —num_epochs: 5
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.57.3
• —Pytorch 2.9.0+cu126
• —Datasets 4.4.2
• —Tokenizers 0.22.1