Hugging Face's logo

MedicalVision
/
yolos_tiny_100ep

Object Detection
Transformers
Safetensors
yolos
Inference Endpoints
Model card Files Community

Original result 

IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000

After training result 

IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.002
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.009
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.003
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.004
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.033
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.054
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.056

Config

  • dataset: NIH
  • original model: hustvl/yolos-tiny
  • lr: 1e-06
  • dropout_rate: 0.1
  • weight_decay: 0.05
  • max_epochs: 100
  • train samples: 885

Logging

Training process 

{'validation_loss': tensor(7.4421, device='cuda:0'), 'validation_loss_ce': tensor(2.5115, device='cuda:0'), 'validation_loss_bbox': tensor(0.5845, device='cuda:0'), 'validation_loss_giou': tensor(1.0041, device='cuda:0'), 'validation_cardinality_error': tensor(98.9688, device='cuda:0')}
{'training_loss': tensor(5.3640, device='cuda:0'), 'train_loss_ce': tensor(2.2904, device='cuda:0'), 'train_loss_bbox': tensor(0.3264, device='cuda:0'), 'train_loss_giou': tensor(0.7207, device='cuda:0'), 'train_cardinality_error': tensor(99., device='cuda:0'), 'validation_loss': tensor(6.1285, device='cuda:0'), 'validation_loss_ce': tensor(2.2476, device='cuda:0'), 'validation_loss_bbox': tensor(0.4395, device='cuda:0'), 'validation_loss_giou': tensor(0.8417, device='cuda:0'), 'validation_cardinality_error': tensor(98.7273, device='cuda:0')}
{'training_loss': tensor(4.6269, device='cuda:0'), 'train_loss_ce': tensor(2.0755, device='cuda:0'), 'train_loss_bbox': tensor(0.2549, device='cuda:0'), 'train_loss_giou': tensor(0.6384, device='cuda:0'), 'train_cardinality_error': tensor(97.6000, device='cuda:0'), 'validation_loss': tensor(5.2690, device='cuda:0'), 'validation_loss_ce': tensor(2.0870, device='cuda:0'), 'validation_loss_bbox': tensor(0.3288, device='cuda:0'), 'validation_loss_giou': tensor(0.7689, device='cuda:0'), 'validation_cardinality_error': tensor(96.6364, device='cuda:0')}
{'training_loss': tensor(4.7931, device='cuda:0'), 'train_loss_ce': tensor(1.9471, device='cuda:0'), 'train_loss_bbox': tensor(0.2410, device='cuda:0'), 'train_loss_giou': tensor(0.8204, device='cuda:0'), 'train_cardinality_error': tensor(87.6000, device='cuda:0'), 'validation_loss': tensor(4.8855, device='cuda:0'), 'validation_loss_ce': tensor(1.9507, device='cuda:0'), 'validation_loss_bbox': tensor(0.2969, device='cuda:0'), 'validation_loss_giou': tensor(0.7252, device='cuda:0'), 'validation_cardinality_error': tensor(88.3535, device='cuda:0')}
{'training_loss': tensor(4.7517, device='cuda:0'), 'train_loss_ce': tensor(1.8214, device='cuda:0'), 'train_loss_bbox': tensor(0.2749, device='cuda:0'), 'train_loss_giou': tensor(0.7778, device='cuda:0'), 'train_cardinality_error': tensor(72.2000, device='cuda:0'), 'validation_loss': tensor(4.4990, device='cuda:0'), 'validation_loss_ce': tensor(1.8171, device='cuda:0'), 'validation_loss_bbox': tensor(0.2615, device='cuda:0'), 'validation_loss_giou': tensor(0.6871, device='cuda:0'), 'validation_cardinality_error': tensor(71.3535, device='cuda:0')}
{'training_loss': tensor(4.1045, device='cuda:0'), 'train_loss_ce': tensor(1.7791, device='cuda:0'), 'train_loss_bbox': tensor(0.1798, device='cuda:0'), 'train_loss_giou': tensor(0.7132, device='cuda:0'), 'train_cardinality_error': tensor(61.8000, device='cuda:0'), 'validation_loss': tensor(4.1904, device='cuda:0'), 'validation_loss_ce': tensor(1.6777, device='cuda:0'), 'validation_loss_bbox': tensor(0.2327, device='cuda:0'), 'validation_loss_giou': tensor(0.6746, device='cuda:0'), 'validation_cardinality_error': tensor(44.9495, device='cuda:0')}
{'training_loss': tensor(3.6955, device='cuda:0'), 'train_loss_ce': tensor(1.6416, device='cuda:0'), 'train_loss_bbox': tensor(0.1936, device='cuda:0'), 'train_loss_giou': tensor(0.5429, device='cuda:0'), 'train_cardinality_error': tensor(47.4000, device='cuda:0'), 'validation_loss': tensor(3.9828, device='cuda:0'), 'validation_loss_ce': tensor(1.5497, device='cuda:0'), 'validation_loss_bbox': tensor(0.2214, device='cuda:0'), 'validation_loss_giou': tensor(0.6631, device='cuda:0'), 'validation_cardinality_error': tensor(24.1818, device='cuda:0')}
{'training_loss': tensor(3.2076, device='cuda:0'), 'train_loss_ce': tensor(1.3885, device='cuda:0'), 'train_loss_bbox': tensor(0.1682, device='cuda:0'), 'train_loss_giou': tensor(0.4889, device='cuda:0'), 'train_cardinality_error': tensor(5.6000, device='cuda:0'), 'validation_loss': tensor(3.8317, device='cuda:0'), 'validation_loss_ce': tensor(1.4248, device='cuda:0'), 'validation_loss_bbox': tensor(0.2183, device='cuda:0'), 'validation_loss_giou': tensor(0.6578, device='cuda:0'), 'validation_cardinality_error': tensor(10.5152, device='cuda:0')}
{'training_loss': tensor(3.3197, device='cuda:0'), 'train_loss_ce': tensor(1.3421, device='cuda:0'), 'train_loss_bbox': tensor(0.1697, device='cuda:0'), 'train_loss_giou': tensor(0.5645, device='cuda:0'), 'train_cardinality_error': tensor(3.8000, device='cuda:0'), 'validation_loss': tensor(3.7097, device='cuda:0'), 'validation_loss_ce': tensor(1.3099, device='cuda:0'), 'validation_loss_bbox': tensor(0.2153, device='cuda:0'), 'validation_loss_giou': tensor(0.6616, device='cuda:0'), 'validation_cardinality_error': tensor(4.3535, device='cuda:0')}
{'training_loss': tensor(3.1406, device='cuda:0'), 'train_loss_ce': tensor(1.2408, device='cuda:0'), 'train_loss_bbox': tensor(0.1745, device='cuda:0'), 'train_loss_giou': tensor(0.5138, device='cuda:0'), 'train_cardinality_error': tensor(3.6000, device='cuda:0'), 'validation_loss': tensor(3.5652, device='cuda:0'), 'validation_loss_ce': tensor(1.1933, device='cuda:0'), 'validation_loss_bbox': tensor(0.2128, device='cuda:0'), 'validation_loss_giou': tensor(0.6538, device='cuda:0'), 'validation_cardinality_error': tensor(1.9394, device='cuda:0')}
{'training_loss': tensor(3.1124, device='cuda:0'), 'train_loss_ce': tensor(1.1540, device='cuda:0'), 'train_loss_bbox': tensor(0.1709, device='cuda:0'), 'train_loss_giou': tensor(0.5520, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.4331, device='cuda:0'), 'validation_loss_ce': tensor(1.0883, device='cuda:0'), 'validation_loss_bbox': tensor(0.2090, device='cuda:0'), 'validation_loss_giou': tensor(0.6499, device='cuda:0'), 'validation_cardinality_error': tensor(1.2828, device='cuda:0')}
{'training_loss': tensor(3.1652, device='cuda:0'), 'train_loss_ce': tensor(1.0350, device='cuda:0'), 'train_loss_bbox': tensor(0.2501, device='cuda:0'), 'train_loss_giou': tensor(0.4399, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.3208, device='cuda:0'), 'validation_loss_ce': tensor(0.9921, device='cuda:0'), 'validation_loss_bbox': tensor(0.2082, device='cuda:0'), 'validation_loss_giou': tensor(0.6439, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.7558, device='cuda:0'), 'train_loss_ce': tensor(0.8441, device='cuda:0'), 'train_loss_bbox': tensor(0.1465, device='cuda:0'), 'train_loss_giou': tensor(0.5895, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.2377, device='cuda:0'), 'validation_loss_ce': tensor(0.9079, device='cuda:0'), 'validation_loss_bbox': tensor(0.2120, device='cuda:0'), 'validation_loss_giou': tensor(0.6349, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.1056, device='cuda:0'), 'train_loss_ce': tensor(0.8188, device='cuda:0'), 'train_loss_bbox': tensor(0.2010, device='cuda:0'), 'train_loss_giou': tensor(0.6410, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.1547, device='cuda:0'), 'validation_loss_ce': tensor(0.8358, device='cuda:0'), 'validation_loss_bbox': tensor(0.2115, device='cuda:0'), 'validation_loss_giou': tensor(0.6307, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.3618, device='cuda:0'), 'train_loss_ce': tensor(0.8644, device='cuda:0'), 'train_loss_bbox': tensor(0.2050, device='cuda:0'), 'train_loss_giou': tensor(0.7361, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.0753, device='cuda:0'), 'validation_loss_ce': tensor(0.7736, device='cuda:0'), 'validation_loss_bbox': tensor(0.2098, device='cuda:0'), 'validation_loss_giou': tensor(0.6264, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3893, device='cuda:0'), 'train_loss_ce': tensor(0.7473, device='cuda:0'), 'train_loss_bbox': tensor(0.1331, device='cuda:0'), 'train_loss_giou': tensor(0.4883, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.0103, device='cuda:0'), 'validation_loss_ce': tensor(0.7209, device='cuda:0'), 'validation_loss_bbox': tensor(0.2076, device='cuda:0'), 'validation_loss_giou': tensor(0.6257, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5919, device='cuda:0'), 'train_loss_ce': tensor(0.6147, device='cuda:0'), 'train_loss_bbox': tensor(0.1713, device='cuda:0'), 'train_loss_giou': tensor(0.5603, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.9583, device='cuda:0'), 'validation_loss_ce': tensor(0.6792, device='cuda:0'), 'validation_loss_bbox': tensor(0.2056, device='cuda:0'), 'validation_loss_giou': tensor(0.6255, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.0810, device='cuda:0'), 'train_loss_ce': tensor(0.5400, device='cuda:0'), 'train_loss_bbox': tensor(0.2192, device='cuda:0'), 'train_loss_giou': tensor(0.7225, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.9196, device='cuda:0'), 'validation_loss_ce': tensor(0.6439, device='cuda:0'), 'validation_loss_bbox': tensor(0.2061, device='cuda:0'), 'validation_loss_giou': tensor(0.6227, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6011, device='cuda:0'), 'train_loss_ce': tensor(0.5601, device='cuda:0'), 'train_loss_bbox': tensor(0.1572, device='cuda:0'), 'train_loss_giou': tensor(0.6275, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8905, device='cuda:0'), 'validation_loss_ce': tensor(0.6165, device='cuda:0'), 'validation_loss_bbox': tensor(0.2054, device='cuda:0'), 'validation_loss_giou': tensor(0.6235, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.0947, device='cuda:0'), 'train_loss_ce': tensor(0.5913, device='cuda:0'), 'train_loss_bbox': tensor(0.2277, device='cuda:0'), 'train_loss_giou': tensor(0.6826, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8587, device='cuda:0'), 'validation_loss_ce': tensor(0.5922, device='cuda:0'), 'validation_loss_bbox': tensor(0.2026, device='cuda:0'), 'validation_loss_giou': tensor(0.6267, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5062, device='cuda:0'), 'train_loss_ce': tensor(0.5246, device='cuda:0'), 'train_loss_bbox': tensor(0.1848, device='cuda:0'), 'train_loss_giou': tensor(0.5288, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8384, device='cuda:0'), 'validation_loss_ce': tensor(0.5722, device='cuda:0'), 'validation_loss_bbox': tensor(0.2042, device='cuda:0'), 'validation_loss_giou': tensor(0.6225, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8459, device='cuda:0'), 'train_loss_ce': tensor(0.4725, device='cuda:0'), 'train_loss_bbox': tensor(0.1202, device='cuda:0'), 'train_loss_giou': tensor(0.3863, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8109, device='cuda:0'), 'validation_loss_ce': tensor(0.5569, device='cuda:0'), 'validation_loss_bbox': tensor(0.2019, device='cuda:0'), 'validation_loss_giou': tensor(0.6223, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1466, device='cuda:0'), 'train_loss_ce': tensor(0.5486, device='cuda:0'), 'train_loss_bbox': tensor(0.1195, device='cuda:0'), 'train_loss_giou': tensor(0.5003, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7918, device='cuda:0'), 'validation_loss_ce': tensor(0.5419, device='cuda:0'), 'validation_loss_bbox': tensor(0.2015, device='cuda:0'), 'validation_loss_giou': tensor(0.6213, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8757, device='cuda:0'), 'train_loss_ce': tensor(0.5642, device='cuda:0'), 'train_loss_bbox': tensor(0.1445, device='cuda:0'), 'train_loss_giou': tensor(0.2944, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7745, device='cuda:0'), 'validation_loss_ce': tensor(0.5278, device='cuda:0'), 'validation_loss_bbox': tensor(0.2026, device='cuda:0'), 'validation_loss_giou': tensor(0.6169, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6128, device='cuda:0'), 'train_loss_ce': tensor(0.4974, device='cuda:0'), 'train_loss_bbox': tensor(0.1414, device='cuda:0'), 'train_loss_giou': tensor(0.7041, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7593, device='cuda:0'), 'validation_loss_ce': tensor(0.5189, device='cuda:0'), 'validation_loss_bbox': tensor(0.2021, device='cuda:0'), 'validation_loss_giou': tensor(0.6150, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7824, device='cuda:0'), 'train_loss_ce': tensor(0.4890, device='cuda:0'), 'train_loss_bbox': tensor(0.1042, device='cuda:0'), 'train_loss_giou': tensor(0.3861, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7412, device='cuda:0'), 'validation_loss_ce': tensor(0.5102, device='cuda:0'), 'validation_loss_bbox': tensor(0.2015, device='cuda:0'), 'validation_loss_giou': tensor(0.6118, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9606, device='cuda:0'), 'train_loss_ce': tensor(0.5061, device='cuda:0'), 'train_loss_bbox': tensor(0.1328, device='cuda:0'), 'train_loss_giou': tensor(0.3954, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7341, device='cuda:0'), 'validation_loss_ce': tensor(0.5061, device='cuda:0'), 'validation_loss_bbox': tensor(0.1992, device='cuda:0'), 'validation_loss_giou': tensor(0.6160, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.8304, device='cuda:0'), 'train_loss_ce': tensor(0.5065, device='cuda:0'), 'train_loss_bbox': tensor(0.2069, device='cuda:0'), 'train_loss_giou': tensor(0.6447, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7390, device='cuda:0'), 'validation_loss_ce': tensor(0.5002, device='cuda:0'), 'validation_loss_bbox': tensor(0.2018, device='cuda:0'), 'validation_loss_giou': tensor(0.6148, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6329, device='cuda:0'), 'train_loss_ce': tensor(0.4457, device='cuda:0'), 'train_loss_bbox': tensor(0.1868, device='cuda:0'), 'train_loss_giou': tensor(0.6266, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7249, device='cuda:0'), 'validation_loss_ce': tensor(0.4955, device='cuda:0'), 'validation_loss_bbox': tensor(0.1999, device='cuda:0'), 'validation_loss_giou': tensor(0.6150, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.9033, device='cuda:0'), 'train_loss_ce': tensor(0.4851, device='cuda:0'), 'train_loss_bbox': tensor(0.2238, device='cuda:0'), 'train_loss_giou': tensor(0.6495, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7176, device='cuda:0'), 'validation_loss_ce': tensor(0.4911, device='cuda:0'), 'validation_loss_bbox': tensor(0.2013, device='cuda:0'), 'validation_loss_giou': tensor(0.6099, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.9650, device='cuda:0'), 'train_loss_ce': tensor(0.5187, device='cuda:0'), 'train_loss_bbox': tensor(0.2221, device='cuda:0'), 'train_loss_giou': tensor(0.6678, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7125, device='cuda:0'), 'validation_loss_ce': tensor(0.4864, device='cuda:0'), 'validation_loss_bbox': tensor(0.1995, device='cuda:0'), 'validation_loss_giou': tensor(0.6143, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.9593, device='cuda:0'), 'train_loss_ce': tensor(0.4404, device='cuda:0'), 'train_loss_bbox': tensor(0.1834, device='cuda:0'), 'train_loss_giou': tensor(0.8008, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7055, device='cuda:0'), 'validation_loss_ce': tensor(0.4840, device='cuda:0'), 'validation_loss_bbox': tensor(0.2003, device='cuda:0'), 'validation_loss_giou': tensor(0.6100, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.1896, device='cuda:0'), 'train_loss_ce': tensor(0.4241, device='cuda:0'), 'train_loss_bbox': tensor(0.0758, device='cuda:0'), 'train_loss_giou': tensor(0.1933, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6971, device='cuda:0'), 'validation_loss_ce': tensor(0.4806, device='cuda:0'), 'validation_loss_bbox': tensor(0.2012, device='cuda:0'), 'validation_loss_giou': tensor(0.6053, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9310, device='cuda:0'), 'train_loss_ce': tensor(0.4291, device='cuda:0'), 'train_loss_bbox': tensor(0.1107, device='cuda:0'), 'train_loss_giou': tensor(0.4743, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6835, device='cuda:0'), 'validation_loss_ce': tensor(0.4779, device='cuda:0'), 'validation_loss_bbox': tensor(0.1983, device='cuda:0'), 'validation_loss_giou': tensor(0.6070, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8326, device='cuda:0'), 'train_loss_ce': tensor(0.4910, device='cuda:0'), 'train_loss_bbox': tensor(0.1155, device='cuda:0'), 'train_loss_giou': tensor(0.3822, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6924, device='cuda:0'), 'validation_loss_ce': tensor(0.4747, device='cuda:0'), 'validation_loss_bbox': tensor(0.1989, device='cuda:0'), 'validation_loss_giou': tensor(0.6115, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1651, device='cuda:0'), 'train_loss_ce': tensor(0.4247, device='cuda:0'), 'train_loss_bbox': tensor(0.1594, device='cuda:0'), 'train_loss_giou': tensor(0.4716, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6750, device='cuda:0'), 'validation_loss_ce': tensor(0.4747, device='cuda:0'), 'validation_loss_bbox': tensor(0.1977, device='cuda:0'), 'validation_loss_giou': tensor(0.6059, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0874, device='cuda:0'), 'train_loss_ce': tensor(0.4776, device='cuda:0'), 'train_loss_bbox': tensor(0.1475, device='cuda:0'), 'train_loss_giou': tensor(0.4363, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6784, device='cuda:0'), 'validation_loss_ce': tensor(0.4713, device='cuda:0'), 'validation_loss_bbox': tensor(0.1979, device='cuda:0'), 'validation_loss_giou': tensor(0.6088, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9946, device='cuda:0'), 'train_loss_ce': tensor(0.4626, device='cuda:0'), 'train_loss_bbox': tensor(0.1389, device='cuda:0'), 'train_loss_giou': tensor(0.4188, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6744, device='cuda:0'), 'validation_loss_ce': tensor(0.4698, device='cuda:0'), 'validation_loss_bbox': tensor(0.1988, device='cuda:0'), 'validation_loss_giou': tensor(0.6054, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0583, device='cuda:0'), 'train_loss_ce': tensor(0.4076, device='cuda:0'), 'train_loss_bbox': tensor(0.1304, device='cuda:0'), 'train_loss_giou': tensor(0.4993, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6416, device='cuda:0'), 'validation_loss_ce': tensor(0.4677, device='cuda:0'), 'validation_loss_bbox': tensor(0.1947, device='cuda:0'), 'validation_loss_giou': tensor(0.6002, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6100, device='cuda:0'), 'train_loss_ce': tensor(0.4910, device='cuda:0'), 'train_loss_bbox': tensor(0.0847, device='cuda:0'), 'train_loss_giou': tensor(0.3478, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6569, device='cuda:0'), 'validation_loss_ce': tensor(0.4668, device='cuda:0'), 'validation_loss_bbox': tensor(0.1978, device='cuda:0'), 'validation_loss_giou': tensor(0.6005, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9128, device='cuda:0'), 'train_loss_ce': tensor(0.4083, device='cuda:0'), 'train_loss_bbox': tensor(0.1298, device='cuda:0'), 'train_loss_giou': tensor(0.4278, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6522, device='cuda:0'), 'validation_loss_ce': tensor(0.4649, device='cuda:0'), 'validation_loss_bbox': tensor(0.1968, device='cuda:0'), 'validation_loss_giou': tensor(0.6016, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6468, device='cuda:0'), 'train_loss_ce': tensor(0.4145, device='cuda:0'), 'train_loss_bbox': tensor(0.1012, device='cuda:0'), 'train_loss_giou': tensor(0.3631, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6414, device='cuda:0'), 'validation_loss_ce': tensor(0.4628, device='cuda:0'), 'validation_loss_bbox': tensor(0.1959, device='cuda:0'), 'validation_loss_giou': tensor(0.5997, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1550, device='cuda:0'), 'train_loss_ce': tensor(0.4127, device='cuda:0'), 'train_loss_bbox': tensor(0.1374, device='cuda:0'), 'train_loss_giou': tensor(0.5277, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6425, device='cuda:0'), 'validation_loss_ce': tensor(0.4617, device='cuda:0'), 'validation_loss_bbox': tensor(0.1981, device='cuda:0'), 'validation_loss_giou': tensor(0.5951, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6485, device='cuda:0'), 'train_loss_ce': tensor(0.4828, device='cuda:0'), 'train_loss_bbox': tensor(0.1050, device='cuda:0'), 'train_loss_giou': tensor(0.3204, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6531, device='cuda:0'), 'validation_loss_ce': tensor(0.4611, device='cuda:0'), 'validation_loss_bbox': tensor(0.1969, device='cuda:0'), 'validation_loss_giou': tensor(0.6039, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2124, device='cuda:0'), 'train_loss_ce': tensor(0.4464, device='cuda:0'), 'train_loss_bbox': tensor(0.1366, device='cuda:0'), 'train_loss_giou': tensor(0.5415, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6317, device='cuda:0'), 'validation_loss_ce': tensor(0.4610, device='cuda:0'), 'validation_loss_bbox': tensor(0.1945, device='cuda:0'), 'validation_loss_giou': tensor(0.5992, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0973, device='cuda:0'), 'train_loss_ce': tensor(0.5066, device='cuda:0'), 'train_loss_bbox': tensor(0.1410, device='cuda:0'), 'train_loss_giou': tensor(0.4428, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6351, device='cuda:0'), 'validation_loss_ce': tensor(0.4587, device='cuda:0'), 'validation_loss_bbox': tensor(0.1964, device='cuda:0'), 'validation_loss_giou': tensor(0.5973, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.0631, device='cuda:0'), 'train_loss_ce': tensor(0.4982, device='cuda:0'), 'train_loss_bbox': tensor(0.2281, device='cuda:0'), 'train_loss_giou': tensor(0.7121, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6270, device='cuda:0'), 'validation_loss_ce': tensor(0.4579, device='cuda:0'), 'validation_loss_bbox': tensor(0.1950, device='cuda:0'), 'validation_loss_giou': tensor(0.5970, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8231, device='cuda:0'), 'train_loss_ce': tensor(0.4370, device='cuda:0'), 'train_loss_bbox': tensor(0.1023, device='cuda:0'), 'train_loss_giou': tensor(0.4374, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6277, device='cuda:0'), 'validation_loss_ce': tensor(0.4557, device='cuda:0'), 'validation_loss_bbox': tensor(0.1953, device='cuda:0'), 'validation_loss_giou': tensor(0.5978, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.8109, device='cuda:0'), 'train_loss_ce': tensor(0.4927, device='cuda:0'), 'train_loss_bbox': tensor(0.2012, device='cuda:0'), 'train_loss_giou': tensor(0.6562, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6170, device='cuda:0'), 'validation_loss_ce': tensor(0.4545, device='cuda:0'), 'validation_loss_bbox': tensor(0.1947, device='cuda:0'), 'validation_loss_giou': tensor(0.5945, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6291, device='cuda:0'), 'train_loss_ce': tensor(0.4953, device='cuda:0'), 'train_loss_bbox': tensor(0.1611, device='cuda:0'), 'train_loss_giou': tensor(0.6643, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6084, device='cuda:0'), 'validation_loss_ce': tensor(0.4543, device='cuda:0'), 'validation_loss_bbox': tensor(0.1929, device='cuda:0'), 'validation_loss_giou': tensor(0.5948, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5380, device='cuda:0'), 'train_loss_ce': tensor(0.4861, device='cuda:0'), 'train_loss_bbox': tensor(0.1045, device='cuda:0'), 'train_loss_giou': tensor(0.2647, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6087, device='cuda:0'), 'validation_loss_ce': tensor(0.4521, device='cuda:0'), 'validation_loss_bbox': tensor(0.1949, device='cuda:0'), 'validation_loss_giou': tensor(0.5911, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9147, device='cuda:0'), 'train_loss_ce': tensor(0.4746, device='cuda:0'), 'train_loss_bbox': tensor(0.1096, device='cuda:0'), 'train_loss_giou': tensor(0.4460, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6031, device='cuda:0'), 'validation_loss_ce': tensor(0.4519, device='cuda:0'), 'validation_loss_bbox': tensor(0.1924, device='cuda:0'), 'validation_loss_giou': tensor(0.5946, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4415, device='cuda:0'), 'train_loss_ce': tensor(0.4633, device='cuda:0'), 'train_loss_bbox': tensor(0.1337, device='cuda:0'), 'train_loss_giou': tensor(0.6547, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5929, device='cuda:0'), 'validation_loss_ce': tensor(0.4506, device='cuda:0'), 'validation_loss_bbox': tensor(0.1925, device='cuda:0'), 'validation_loss_giou': tensor(0.5898, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3528, device='cuda:0'), 'train_loss_ce': tensor(0.4787, device='cuda:0'), 'train_loss_bbox': tensor(0.0845, device='cuda:0'), 'train_loss_giou': tensor(0.2259, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5939, device='cuda:0'), 'validation_loss_ce': tensor(0.4496, device='cuda:0'), 'validation_loss_bbox': tensor(0.1925, device='cuda:0'), 'validation_loss_giou': tensor(0.5908, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3855, device='cuda:0'), 'train_loss_ce': tensor(0.4904, device='cuda:0'), 'train_loss_bbox': tensor(0.1708, device='cuda:0'), 'train_loss_giou': tensor(0.5206, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5926, device='cuda:0'), 'validation_loss_ce': tensor(0.4489, device='cuda:0'), 'validation_loss_bbox': tensor(0.1923, device='cuda:0'), 'validation_loss_giou': tensor(0.5911, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9941, device='cuda:0'), 'train_loss_ce': tensor(0.4179, device='cuda:0'), 'train_loss_bbox': tensor(0.1169, device='cuda:0'), 'train_loss_giou': tensor(0.4957, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6010, device='cuda:0'), 'validation_loss_ce': tensor(0.4481, device='cuda:0'), 'validation_loss_bbox': tensor(0.1929, device='cuda:0'), 'validation_loss_giou': tensor(0.5941, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3430, device='cuda:0'), 'train_loss_ce': tensor(0.4101, device='cuda:0'), 'train_loss_bbox': tensor(0.1676, device='cuda:0'), 'train_loss_giou': tensor(0.5475, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5848, device='cuda:0'), 'validation_loss_ce': tensor(0.4476, device='cuda:0'), 'validation_loss_bbox': tensor(0.1902, device='cuda:0'), 'validation_loss_giou': tensor(0.5930, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0356, device='cuda:0'), 'train_loss_ce': tensor(0.3885, device='cuda:0'), 'train_loss_bbox': tensor(0.0528, device='cuda:0'), 'train_loss_giou': tensor(0.1914, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5917, device='cuda:0'), 'validation_loss_ce': tensor(0.4471, device='cuda:0'), 'validation_loss_bbox': tensor(0.1912, device='cuda:0'), 'validation_loss_giou': tensor(0.5943, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.1007, device='cuda:0'), 'train_loss_ce': tensor(0.3253, device='cuda:0'), 'train_loss_bbox': tensor(0.0563, device='cuda:0'), 'train_loss_giou': tensor(0.2470, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5969, device='cuda:0'), 'validation_loss_ce': tensor(0.4461, device='cuda:0'), 'validation_loss_bbox': tensor(0.1943, device='cuda:0'), 'validation_loss_giou': tensor(0.5897, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8121, device='cuda:0'), 'train_loss_ce': tensor(0.3974, device='cuda:0'), 'train_loss_bbox': tensor(0.0934, device='cuda:0'), 'train_loss_giou': tensor(0.4737, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5796, device='cuda:0'), 'validation_loss_ce': tensor(0.4455, device='cuda:0'), 'validation_loss_bbox': tensor(0.1896, device='cuda:0'), 'validation_loss_giou': tensor(0.5930, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0623, device='cuda:0'), 'train_loss_ce': tensor(0.3080, device='cuda:0'), 'train_loss_bbox': tensor(0.1189, device='cuda:0'), 'train_loss_giou': tensor(0.5798, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5785, device='cuda:0'), 'validation_loss_ce': tensor(0.4440, device='cuda:0'), 'validation_loss_bbox': tensor(0.1901, device='cuda:0'), 'validation_loss_giou': tensor(0.5921, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6082, device='cuda:0'), 'train_loss_ce': tensor(0.4056, device='cuda:0'), 'train_loss_bbox': tensor(0.1185, device='cuda:0'), 'train_loss_giou': tensor(0.3051, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5693, device='cuda:0'), 'validation_loss_ce': tensor(0.4425, device='cuda:0'), 'validation_loss_bbox': tensor(0.1886, device='cuda:0'), 'validation_loss_giou': tensor(0.5918, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4199, device='cuda:0'), 'train_loss_ce': tensor(0.4382, device='cuda:0'), 'train_loss_bbox': tensor(0.1484, device='cuda:0'), 'train_loss_giou': tensor(0.6199, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5728, device='cuda:0'), 'validation_loss_ce': tensor(0.4417, device='cuda:0'), 'validation_loss_bbox': tensor(0.1904, device='cuda:0'), 'validation_loss_giou': tensor(0.5896, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4047, device='cuda:0'), 'train_loss_ce': tensor(0.3788, device='cuda:0'), 'train_loss_bbox': tensor(0.1592, device='cuda:0'), 'train_loss_giou': tensor(0.6149, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5722, device='cuda:0'), 'validation_loss_ce': tensor(0.4420, device='cuda:0'), 'validation_loss_bbox': tensor(0.1896, device='cuda:0'), 'validation_loss_giou': tensor(0.5912, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9535, device='cuda:0'), 'train_loss_ce': tensor(0.4432, device='cuda:0'), 'train_loss_bbox': tensor(0.1193, device='cuda:0'), 'train_loss_giou': tensor(0.4570, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5639, device='cuda:0'), 'validation_loss_ce': tensor(0.4427, device='cuda:0'), 'validation_loss_bbox': tensor(0.1875, device='cuda:0'), 'validation_loss_giou': tensor(0.5918, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0176, device='cuda:0'), 'train_loss_ce': tensor(0.4873, device='cuda:0'), 'train_loss_bbox': tensor(0.1339, device='cuda:0'), 'train_loss_giou': tensor(0.4305, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5706, device='cuda:0'), 'validation_loss_ce': tensor(0.4407, device='cuda:0'), 'validation_loss_bbox': tensor(0.1889, device='cuda:0'), 'validation_loss_giou': tensor(0.5928, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0423, device='cuda:0'), 'train_loss_ce': tensor(0.4026, device='cuda:0'), 'train_loss_bbox': tensor(0.1162, device='cuda:0'), 'train_loss_giou': tensor(0.5294, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5695, device='cuda:0'), 'validation_loss_ce': tensor(0.4393, device='cuda:0'), 'validation_loss_bbox': tensor(0.1894, device='cuda:0'), 'validation_loss_giou': tensor(0.5916, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5977, device='cuda:0'), 'train_loss_ce': tensor(0.5043, device='cuda:0'), 'train_loss_bbox': tensor(0.2092, device='cuda:0'), 'train_loss_giou': tensor(0.5237, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5655, device='cuda:0'), 'validation_loss_ce': tensor(0.4399, device='cuda:0'), 'validation_loss_bbox': tensor(0.1883, device='cuda:0'), 'validation_loss_giou': tensor(0.5920, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7494, device='cuda:0'), 'train_loss_ce': tensor(0.3655, device='cuda:0'), 'train_loss_bbox': tensor(0.1080, device='cuda:0'), 'train_loss_giou': tensor(0.4219, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5542, device='cuda:0'), 'validation_loss_ce': tensor(0.4394, device='cuda:0'), 'validation_loss_bbox': tensor(0.1872, device='cuda:0'), 'validation_loss_giou': tensor(0.5894, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7155, device='cuda:0'), 'train_loss_ce': tensor(0.3842, device='cuda:0'), 'train_loss_bbox': tensor(0.1178, device='cuda:0'), 'train_loss_giou': tensor(0.3711, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5515, device='cuda:0'), 'validation_loss_ce': tensor(0.4396, device='cuda:0'), 'validation_loss_bbox': tensor(0.1865, device='cuda:0'), 'validation_loss_giou': tensor(0.5896, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5134, device='cuda:0'), 'train_loss_ce': tensor(0.4339, device='cuda:0'), 'train_loss_bbox': tensor(0.0862, device='cuda:0'), 'train_loss_giou': tensor(0.3242, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5449, device='cuda:0'), 'validation_loss_ce': tensor(0.4382, device='cuda:0'), 'validation_loss_bbox': tensor(0.1860, device='cuda:0'), 'validation_loss_giou': tensor(0.5882, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1454, device='cuda:0'), 'train_loss_ce': tensor(0.4427, device='cuda:0'), 'train_loss_bbox': tensor(0.1563, device='cuda:0'), 'train_loss_giou': tensor(0.4606, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5667, device='cuda:0'), 'validation_loss_ce': tensor(0.4387, device='cuda:0'), 'validation_loss_bbox': tensor(0.1888, device='cuda:0'), 'validation_loss_giou': tensor(0.5920, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1418, device='cuda:0'), 'train_loss_ce': tensor(0.4907, device='cuda:0'), 'train_loss_bbox': tensor(0.1390, device='cuda:0'), 'train_loss_giou': tensor(0.4781, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5471, device='cuda:0'), 'validation_loss_ce': tensor(0.4371, device='cuda:0'), 'validation_loss_bbox': tensor(0.1864, device='cuda:0'), 'validation_loss_giou': tensor(0.5891, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6641, device='cuda:0'), 'train_loss_ce': tensor(0.4517, device='cuda:0'), 'train_loss_bbox': tensor(0.1113, device='cuda:0'), 'train_loss_giou': tensor(0.3280, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5497, device='cuda:0'), 'validation_loss_ce': tensor(0.4370, device='cuda:0'), 'validation_loss_bbox': tensor(0.1869, device='cuda:0'), 'validation_loss_giou': tensor(0.5891, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0588, device='cuda:0'), 'train_loss_ce': tensor(0.4640, device='cuda:0'), 'train_loss_bbox': tensor(0.1414, device='cuda:0'), 'train_loss_giou': tensor(0.4440, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5494, device='cuda:0'), 'validation_loss_ce': tensor(0.4363, device='cuda:0'), 'validation_loss_bbox': tensor(0.1860, device='cuda:0'), 'validation_loss_giou': tensor(0.5916, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4668, device='cuda:0'), 'train_loss_ce': tensor(0.4662, device='cuda:0'), 'train_loss_bbox': tensor(0.0906, device='cuda:0'), 'train_loss_giou': tensor(0.2739, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5355, device='cuda:0'), 'validation_loss_ce': tensor(0.4356, device='cuda:0'), 'validation_loss_bbox': tensor(0.1840, device='cuda:0'), 'validation_loss_giou': tensor(0.5900, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5525, device='cuda:0'), 'train_loss_ce': tensor(0.4230, device='cuda:0'), 'train_loss_bbox': tensor(0.0795, device='cuda:0'), 'train_loss_giou': tensor(0.3660, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5437, device='cuda:0'), 'validation_loss_ce': tensor(0.4360, device='cuda:0'), 'validation_loss_bbox': tensor(0.1872, device='cuda:0'), 'validation_loss_giou': tensor(0.5859, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0347, device='cuda:0'), 'train_loss_ce': tensor(0.3822, device='cuda:0'), 'train_loss_bbox': tensor(0.1549, device='cuda:0'), 'train_loss_giou': tensor(0.4391, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5326, device='cuda:0'), 'validation_loss_ce': tensor(0.4352, device='cuda:0'), 'validation_loss_bbox': tensor(0.1859, device='cuda:0'), 'validation_loss_giou': tensor(0.5838, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6319, device='cuda:0'), 'train_loss_ce': tensor(0.4843, device='cuda:0'), 'train_loss_bbox': tensor(0.0757, device='cuda:0'), 'train_loss_giou': tensor(0.3845, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5430, device='cuda:0'), 'validation_loss_ce': tensor(0.4347, device='cuda:0'), 'validation_loss_bbox': tensor(0.1858, device='cuda:0'), 'validation_loss_giou': tensor(0.5896, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2715, device='cuda:0'), 'train_loss_ce': tensor(0.4234, device='cuda:0'), 'train_loss_bbox': tensor(0.0752, device='cuda:0'), 'train_loss_giou': tensor(0.2360, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5396, device='cuda:0'), 'validation_loss_ce': tensor(0.4339, device='cuda:0'), 'validation_loss_bbox': tensor(0.1871, device='cuda:0'), 'validation_loss_giou': tensor(0.5852, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0096, device='cuda:0'), 'train_loss_ce': tensor(0.3640, device='cuda:0'), 'train_loss_bbox': tensor(0.1264, device='cuda:0'), 'train_loss_giou': tensor(0.5067, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5445, device='cuda:0'), 'validation_loss_ce': tensor(0.4326, device='cuda:0'), 'validation_loss_bbox': tensor(0.1859, device='cuda:0'), 'validation_loss_giou': tensor(0.5912, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4542, device='cuda:0'), 'train_loss_ce': tensor(0.3515, device='cuda:0'), 'train_loss_bbox': tensor(0.1006, device='cuda:0'), 'train_loss_giou': tensor(0.2998, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5331, device='cuda:0'), 'validation_loss_ce': tensor(0.4338, device='cuda:0'), 'validation_loss_bbox': tensor(0.1851, device='cuda:0'), 'validation_loss_giou': tensor(0.5870, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4403, device='cuda:0'), 'train_loss_ce': tensor(0.2866, device='cuda:0'), 'train_loss_bbox': tensor(0.0839, device='cuda:0'), 'train_loss_giou': tensor(0.3673, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5408, device='cuda:0'), 'validation_loss_ce': tensor(0.4336, device='cuda:0'), 'validation_loss_bbox': tensor(0.1854, device='cuda:0'), 'validation_loss_giou': tensor(0.5901, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3805, device='cuda:0'), 'train_loss_ce': tensor(0.3999, device='cuda:0'), 'train_loss_bbox': tensor(0.1305, device='cuda:0'), 'train_loss_giou': tensor(0.6641, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5276, device='cuda:0'), 'validation_loss_ce': tensor(0.4311, device='cuda:0'), 'validation_loss_bbox': tensor(0.1828, device='cuda:0'), 'validation_loss_giou': tensor(0.5913, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4951, device='cuda:0'), 'train_loss_ce': tensor(0.4566, device='cuda:0'), 'train_loss_bbox': tensor(0.1746, device='cuda:0'), 'train_loss_giou': tensor(0.5827, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5454, device='cuda:0'), 'validation_loss_ce': tensor(0.4331, device='cuda:0'), 'validation_loss_bbox': tensor(0.1866, device='cuda:0'), 'validation_loss_giou': tensor(0.5897, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8686, device='cuda:0'), 'train_loss_ce': tensor(0.4667, device='cuda:0'), 'train_loss_bbox': tensor(0.1072, device='cuda:0'), 'train_loss_giou': tensor(0.4330, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5325, device='cuda:0'), 'validation_loss_ce': tensor(0.4310, device='cuda:0'), 'validation_loss_bbox': tensor(0.1854, device='cuda:0'), 'validation_loss_giou': tensor(0.5873, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4417, device='cuda:0'), 'train_loss_ce': tensor(0.4591, device='cuda:0'), 'train_loss_bbox': tensor(0.0979, device='cuda:0'), 'train_loss_giou': tensor(0.2466, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5337, device='cuda:0'), 'validation_loss_ce': tensor(0.4309, device='cuda:0'), 'validation_loss_bbox': tensor(0.1859, device='cuda:0'), 'validation_loss_giou': tensor(0.5867, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8012, device='cuda:0'), 'train_loss_ce': tensor(0.4728, device='cuda:0'), 'train_loss_bbox': tensor(0.1020, device='cuda:0'), 'train_loss_giou': tensor(0.4092, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5271, device='cuda:0'), 'validation_loss_ce': tensor(0.4309, device='cuda:0'), 'validation_loss_bbox': tensor(0.1841, device='cuda:0'), 'validation_loss_giou': tensor(0.5878, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2664, device='cuda:0'), 'train_loss_ce': tensor(0.4616, device='cuda:0'), 'train_loss_bbox': tensor(0.1533, device='cuda:0'), 'train_loss_giou': tensor(0.5191, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5326, device='cuda:0'), 'validation_loss_ce': tensor(0.4308, device='cuda:0'), 'validation_loss_bbox': tensor(0.1855, device='cuda:0'), 'validation_loss_giou': tensor(0.5870, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6760, device='cuda:0'), 'train_loss_ce': tensor(0.3843, device='cuda:0'), 'train_loss_bbox': tensor(0.1065, device='cuda:0'), 'train_loss_giou': tensor(0.3796, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5274, device='cuda:0'), 'validation_loss_ce': tensor(0.4312, device='cuda:0'), 'validation_loss_bbox': tensor(0.1832, device='cuda:0'), 'validation_loss_giou': tensor(0.5902, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9554, device='cuda:0'), 'train_loss_ce': tensor(0.3618, device='cuda:0'), 'train_loss_bbox': tensor(0.1362, device='cuda:0'), 'train_loss_giou': tensor(0.4562, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5353, device='cuda:0'), 'validation_loss_ce': tensor(0.4288, device='cuda:0'), 'validation_loss_bbox': tensor(0.1856, device='cuda:0'), 'validation_loss_giou': tensor(0.5893, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3378, device='cuda:0'), 'train_loss_ce': tensor(0.3755, device='cuda:0'), 'train_loss_bbox': tensor(0.0839, device='cuda:0'), 'train_loss_giou': tensor(0.2715, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5284, device='cuda:0'), 'validation_loss_ce': tensor(0.4289, device='cuda:0'), 'validation_loss_bbox': tensor(0.1861, device='cuda:0'), 'validation_loss_giou': tensor(0.5844, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8531, device='cuda:0'), 'train_loss_ce': tensor(0.4023, device='cuda:0'), 'train_loss_bbox': tensor(0.1025, device='cuda:0'), 'train_loss_giou': tensor(0.4693, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5285, device='cuda:0'), 'validation_loss_ce': tensor(0.4299, device='cuda:0'), 'validation_loss_bbox': tensor(0.1845, device='cuda:0'), 'validation_loss_giou': tensor(0.5881, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5323, device='cuda:0'), 'train_loss_ce': tensor(0.3935, device='cuda:0'), 'train_loss_bbox': tensor(0.0904, device='cuda:0'), 'train_loss_giou': tensor(0.3433, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5246, device='cuda:0'), 'validation_loss_ce': tensor(0.4286, device='cuda:0'), 'validation_loss_bbox': tensor(0.1843, device='cuda:0'), 'validation_loss_giou': tensor(0.5872, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5760, device='cuda:0'), 'train_loss_ce': tensor(0.4108, device='cuda:0'), 'train_loss_bbox': tensor(0.1176, device='cuda:0'), 'train_loss_giou': tensor(0.2887, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5271, device='cuda:0'), 'validation_loss_ce': tensor(0.4282, device='cuda:0'), 'validation_loss_bbox': tensor(0.1860, device='cuda:0'), 'validation_loss_giou': tensor(0.5845, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5995, device='cuda:0'), 'train_loss_ce': tensor(0.4539, device='cuda:0'), 'train_loss_bbox': tensor(0.0965, device='cuda:0'), 'train_loss_giou': tensor(0.3315, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5257, device='cuda:0'), 'validation_loss_ce': tensor(0.4284, device='cuda:0'), 'validation_loss_bbox': tensor(0.1853, device='cuda:0'), 'validation_loss_giou': tensor(0.5854, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0778, device='cuda:0'), 'train_loss_ce': tensor(0.3774, device='cuda:0'), 'train_loss_bbox': tensor(0.1422, device='cuda:0'), 'train_loss_giou': tensor(0.4945, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5161, device='cuda:0'), 'validation_loss_ce': tensor(0.4269, device='cuda:0'), 'validation_loss_bbox': tensor(0.1839, device='cuda:0'), 'validation_loss_giou': tensor(0.5849, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0061, device='cuda:0'), 'train_loss_ce': tensor(0.3836, device='cuda:0'), 'train_loss_bbox': tensor(0.1675, device='cuda:0'), 'train_loss_giou': tensor(0.3924, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5247, device='cuda:0'), 'validation_loss_ce': tensor(0.4271, device='cuda:0'), 'validation_loss_bbox': tensor(0.1854, device='cuda:0'), 'validation_loss_giou': tensor(0.5853, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4839, device='cuda:0'), 'train_loss_ce': tensor(0.2162, device='cuda:0'), 'train_loss_bbox': tensor(0.1028, device='cuda:0'), 'train_loss_giou': tensor(0.3769, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5184, device='cuda:0'), 'validation_loss_ce': tensor(0.4272, device='cuda:0'), 'validation_loss_bbox': tensor(0.1824, device='cuda:0'), 'validation_loss_giou': tensor(0.5895, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3401, device='cuda:0'), 'train_loss_ce': tensor(0.3501, device='cuda:0'), 'train_loss_bbox': tensor(0.0873, device='cuda:0'), 'train_loss_giou': tensor(0.2767, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5114, device='cuda:0'), 'validation_loss_ce': tensor(0.4268, device='cuda:0'), 'validation_loss_bbox': tensor(0.1842, device='cuda:0'), 'validation_loss_giou': tensor(0.5817, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3274, device='cuda:0'), 'train_loss_ce': tensor(0.4181, device='cuda:0'), 'train_loss_bbox': tensor(0.0620, device='cuda:0'), 'train_loss_giou': tensor(0.2997, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5149, device='cuda:0'), 'validation_loss_ce': tensor(0.4258, device='cuda:0'), 'validation_loss_bbox': tensor(0.1843, device='cuda:0'), 'validation_loss_giou': tensor(0.5838, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}

Examples

{'size': tensor([512, 512]), 'image_id': tensor([1]), 'class_labels': tensor([4]), 'boxes': tensor([[0.2622, 0.5729, 0.0847, 0.0773]]), 'area': tensor([1717.9431]), 'iscrowd': tensor([0]), 'orig_size': tensor([1024, 1024])}

Example

Downloads last month
8
Safetensors
Model size
6.47M params
Tensor type
F32
·
Inference Examples
Object Detection
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.