Hugging Face's logo

MedicalVision
/
detr_nih_100ep_raise

Object Detection
Transformers
Safetensors
detr
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 ] = 0.011
 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 ] = 0.011

After training result 

IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.005
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.018
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.001
 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 ] = 0.005
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.036
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.131
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.141
 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 ] = 0.145

Config

  • dataset: NIH
  • original model: facebook/detr-resnet-50
  • lr: 0.0001
  • dropout_rate: 0.3
  • weight_decay: 0.01
  • max_epochs: 100

Logging

Training process 

{'validation_loss': tensor(5.9922, device='cuda:0'), 'validation_loss_ce': tensor(1.9217, device='cuda:0'), 'validation_loss_bbox': tensor(0.4632, device='cuda:0'), 'validation_loss_giou': tensor(0.8772, device='cuda:0'), 'validation_cardinality_error': tensor(40.3438, device='cuda:0')}
{'training_loss': tensor(3.1585, device='cuda:0'), 'train_loss_ce': tensor(0.5599, device='cuda:0'), 'train_loss_bbox': tensor(0.2764, device='cuda:0'), 'train_loss_giou': tensor(0.6083, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7145, device='cuda:0'), 'validation_loss_ce': tensor(0.5435, device='cuda:0'), 'validation_loss_bbox': tensor(0.1939, device='cuda:0'), 'validation_loss_giou': tensor(0.6009, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5024, device='cuda:0'), 'train_loss_ce': tensor(0.4082, device='cuda:0'), 'train_loss_bbox': tensor(0.1870, device='cuda:0'), 'train_loss_giou': tensor(0.5797, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3204, device='cuda:0'), 'validation_loss_ce': tensor(0.4753, device='cuda:0'), 'validation_loss_bbox': tensor(0.1581, device='cuda:0'), 'validation_loss_giou': tensor(0.5273, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9285, device='cuda:0'), 'train_loss_ce': tensor(0.4730, device='cuda:0'), 'train_loss_bbox': tensor(0.1512, device='cuda:0'), 'train_loss_giou': tensor(0.3496, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3177, device='cuda:0'), 'validation_loss_ce': tensor(0.4526, device='cuda:0'), 'validation_loss_bbox': tensor(0.1578, device='cuda:0'), 'validation_loss_giou': tensor(0.5381, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3199, device='cuda:0'), 'train_loss_ce': tensor(0.5028, device='cuda:0'), 'train_loss_bbox': tensor(0.1363, device='cuda:0'), 'train_loss_giou': tensor(0.5678, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3181, device='cuda:0'), 'validation_loss_ce': tensor(0.4481, device='cuda:0'), 'validation_loss_bbox': tensor(0.1617, device='cuda:0'), 'validation_loss_giou': tensor(0.5307, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1901, device='cuda:0'), 'train_loss_ce': tensor(0.4650, device='cuda:0'), 'train_loss_bbox': tensor(0.1622, device='cuda:0'), 'train_loss_giou': tensor(0.4570, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2432, device='cuda:0'), 'validation_loss_ce': tensor(0.4404, device='cuda:0'), 'validation_loss_bbox': tensor(0.1573, device='cuda:0'), 'validation_loss_giou': tensor(0.5082, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0616, device='cuda:0'), 'train_loss_ce': tensor(0.4577, device='cuda:0'), 'train_loss_bbox': tensor(0.1421, device='cuda:0'), 'train_loss_giou': tensor(0.4467, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2807, device='cuda:0'), 'validation_loss_ce': tensor(0.4421, device='cuda:0'), 'validation_loss_bbox': tensor(0.1580, device='cuda:0'), 'validation_loss_giou': tensor(0.5242, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2789, device='cuda:0'), 'train_loss_ce': tensor(0.4960, device='cuda:0'), 'train_loss_bbox': tensor(0.1681, device='cuda:0'), 'train_loss_giou': tensor(0.4712, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2138, device='cuda:0'), 'validation_loss_ce': tensor(0.4347, device='cuda:0'), 'validation_loss_bbox': tensor(0.1486, device='cuda:0'), 'validation_loss_giou': tensor(0.5181, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9775, device='cuda:0'), 'train_loss_ce': tensor(0.4219, device='cuda:0'), 'train_loss_bbox': tensor(0.1393, device='cuda:0'), 'train_loss_giou': tensor(0.4297, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3134, device='cuda:0'), 'validation_loss_ce': tensor(0.4302, device='cuda:0'), 'validation_loss_bbox': tensor(0.1644, device='cuda:0'), 'validation_loss_giou': tensor(0.5307, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7083, device='cuda:0'), 'train_loss_ce': tensor(0.4728, device='cuda:0'), 'train_loss_bbox': tensor(0.1055, device='cuda:0'), 'train_loss_giou': tensor(0.3539, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2964, device='cuda:0'), 'validation_loss_ce': tensor(0.4320, device='cuda:0'), 'validation_loss_bbox': tensor(0.1584, device='cuda:0'), 'validation_loss_giou': tensor(0.5362, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2199, device='cuda:0'), 'train_loss_ce': tensor(0.3609, device='cuda:0'), 'train_loss_bbox': tensor(0.1701, device='cuda:0'), 'train_loss_giou': tensor(0.5041, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2740, device='cuda:0'), 'validation_loss_ce': tensor(0.4260, device='cuda:0'), 'validation_loss_bbox': tensor(0.1623, device='cuda:0'), 'validation_loss_giou': tensor(0.5182, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5320, device='cuda:0'), 'train_loss_ce': tensor(0.3962, device='cuda:0'), 'train_loss_bbox': tensor(0.1901, device='cuda:0'), 'train_loss_giou': tensor(0.5926, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1716, device='cuda:0'), 'validation_loss_ce': tensor(0.4206, device='cuda:0'), 'validation_loss_bbox': tensor(0.1498, device='cuda:0'), 'validation_loss_giou': tensor(0.5009, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8947, device='cuda:0'), 'train_loss_ce': tensor(0.3639, device='cuda:0'), 'train_loss_bbox': tensor(0.1444, device='cuda:0'), 'train_loss_giou': tensor(0.4044, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2001, device='cuda:0'), 'validation_loss_ce': tensor(0.4262, device='cuda:0'), 'validation_loss_bbox': tensor(0.1507, device='cuda:0'), 'validation_loss_giou': tensor(0.5101, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1039, device='cuda:0'), 'train_loss_ce': tensor(0.4785, device='cuda:0'), 'train_loss_bbox': tensor(0.1239, device='cuda:0'), 'train_loss_giou': tensor(0.5030, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1841, device='cuda:0'), 'validation_loss_ce': tensor(0.4133, device='cuda:0'), 'validation_loss_bbox': tensor(0.1467, device='cuda:0'), 'validation_loss_giou': tensor(0.5186, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4880, device='cuda:0'), 'train_loss_ce': tensor(0.4607, device='cuda:0'), 'train_loss_bbox': tensor(0.1564, device='cuda:0'), 'train_loss_giou': tensor(0.6227, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3479, device='cuda:0'), 'validation_loss_ce': tensor(0.4191, device='cuda:0'), 'validation_loss_bbox': tensor(0.1716, device='cuda:0'), 'validation_loss_giou': tensor(0.5355, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0206, device='cuda:0'), 'train_loss_ce': tensor(0.3709, device='cuda:0'), 'train_loss_bbox': tensor(0.1387, device='cuda:0'), 'train_loss_giou': tensor(0.4780, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1861, device='cuda:0'), 'validation_loss_ce': tensor(0.4140, device='cuda:0'), 'validation_loss_bbox': tensor(0.1535, device='cuda:0'), 'validation_loss_giou': tensor(0.5023, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0864, device='cuda:0'), 'train_loss_ce': tensor(0.4814, device='cuda:0'), 'train_loss_bbox': tensor(0.1503, device='cuda:0'), 'train_loss_giou': tensor(0.4269, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2221, device='cuda:0'), 'validation_loss_ce': tensor(0.4118, device='cuda:0'), 'validation_loss_bbox': tensor(0.1502, device='cuda:0'), 'validation_loss_giou': tensor(0.5296, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2339, device='cuda:0'), 'train_loss_ce': tensor(0.2700, device='cuda:0'), 'train_loss_bbox': tensor(0.1505, device='cuda:0'), 'train_loss_giou': tensor(0.6056, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1954, device='cuda:0'), 'validation_loss_ce': tensor(0.4094, device='cuda:0'), 'validation_loss_bbox': tensor(0.1499, device='cuda:0'), 'validation_loss_giou': tensor(0.5183, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5445, device='cuda:0'), 'train_loss_ce': tensor(0.3648, device='cuda:0'), 'train_loss_bbox': tensor(0.0959, device='cuda:0'), 'train_loss_giou': tensor(0.3501, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2570, device='cuda:0'), 'validation_loss_ce': tensor(0.4029, device='cuda:0'), 'validation_loss_bbox': tensor(0.1562, device='cuda:0'), 'validation_loss_giou': tensor(0.5364, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1753, device='cuda:0'), 'train_loss_ce': tensor(0.3664, device='cuda:0'), 'train_loss_bbox': tensor(0.1394, device='cuda:0'), 'train_loss_giou': tensor(0.5559, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2393, device='cuda:0'), 'validation_loss_ce': tensor(0.4080, device='cuda:0'), 'validation_loss_bbox': tensor(0.1534, device='cuda:0'), 'validation_loss_giou': tensor(0.5322, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3731, device='cuda:0'), 'train_loss_ce': tensor(0.4317, device='cuda:0'), 'train_loss_bbox': tensor(0.1566, device='cuda:0'), 'train_loss_giou': tensor(0.5791, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2051, device='cuda:0'), 'validation_loss_ce': tensor(0.4055, device='cuda:0'), 'validation_loss_bbox': tensor(0.1489, device='cuda:0'), 'validation_loss_giou': tensor(0.5274, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4002, device='cuda:0'), 'train_loss_ce': tensor(0.4197, device='cuda:0'), 'train_loss_bbox': tensor(0.1609, device='cuda:0'), 'train_loss_giou': tensor(0.5880, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1683, device='cuda:0'), 'validation_loss_ce': tensor(0.3984, device='cuda:0'), 'validation_loss_bbox': tensor(0.1494, device='cuda:0'), 'validation_loss_giou': tensor(0.5114, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4413, device='cuda:0'), 'train_loss_ce': tensor(0.4171, device='cuda:0'), 'train_loss_bbox': tensor(0.1139, device='cuda:0'), 'train_loss_giou': tensor(0.7273, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1565, device='cuda:0'), 'validation_loss_ce': tensor(0.4021, device='cuda:0'), 'validation_loss_bbox': tensor(0.1477, device='cuda:0'), 'validation_loss_giou': tensor(0.5079, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0818, device='cuda:0'), 'train_loss_ce': tensor(0.4256, device='cuda:0'), 'train_loss_bbox': tensor(0.1373, device='cuda:0'), 'train_loss_giou': tensor(0.4847, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1993, device='cuda:0'), 'validation_loss_ce': tensor(0.3999, device='cuda:0'), 'validation_loss_bbox': tensor(0.1551, device='cuda:0'), 'validation_loss_giou': tensor(0.5118, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8499, device='cuda:0'), 'train_loss_ce': tensor(0.4293, device='cuda:0'), 'train_loss_bbox': tensor(0.1320, device='cuda:0'), 'train_loss_giou': tensor(0.3803, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2884, device='cuda:0'), 'validation_loss_ce': tensor(0.4017, device='cuda:0'), 'validation_loss_bbox': tensor(0.1593, device='cuda:0'), 'validation_loss_giou': tensor(0.5450, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8121, device='cuda:0'), 'train_loss_ce': tensor(0.3446, device='cuda:0'), 'train_loss_bbox': tensor(0.1191, device='cuda:0'), 'train_loss_giou': tensor(0.4360, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1234, device='cuda:0'), 'validation_loss_ce': tensor(0.3951, device='cuda:0'), 'validation_loss_bbox': tensor(0.1443, device='cuda:0'), 'validation_loss_giou': tensor(0.5035, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1141, device='cuda:0'), 'train_loss_ce': tensor(0.3000, device='cuda:0'), 'train_loss_bbox': tensor(0.1522, device='cuda:0'), 'train_loss_giou': tensor(0.5265, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1656, device='cuda:0'), 'validation_loss_ce': tensor(0.3921, device='cuda:0'), 'validation_loss_bbox': tensor(0.1466, device='cuda:0'), 'validation_loss_giou': tensor(0.5201, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9847, device='cuda:0'), 'train_loss_ce': tensor(0.3244, device='cuda:0'), 'train_loss_bbox': tensor(0.1367, device='cuda:0'), 'train_loss_giou': tensor(0.4884, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1330, device='cuda:0'), 'validation_loss_ce': tensor(0.3942, device='cuda:0'), 'validation_loss_bbox': tensor(0.1478, device='cuda:0'), 'validation_loss_giou': tensor(0.4998, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5460, device='cuda:0'), 'train_loss_ce': tensor(0.3988, device='cuda:0'), 'train_loss_bbox': tensor(0.1542, device='cuda:0'), 'train_loss_giou': tensor(0.6881, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1561, device='cuda:0'), 'validation_loss_ce': tensor(0.3935, device='cuda:0'), 'validation_loss_bbox': tensor(0.1469, device='cuda:0'), 'validation_loss_giou': tensor(0.5139, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8464, device='cuda:0'), 'train_loss_ce': tensor(0.2836, device='cuda:0'), 'train_loss_bbox': tensor(0.1276, device='cuda:0'), 'train_loss_giou': tensor(0.4623, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1226, device='cuda:0'), 'validation_loss_ce': tensor(0.3882, device='cuda:0'), 'validation_loss_bbox': tensor(0.1451, device='cuda:0'), 'validation_loss_giou': tensor(0.5043, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4527, device='cuda:0'), 'train_loss_ce': tensor(0.4172, device='cuda:0'), 'train_loss_bbox': tensor(0.1752, device='cuda:0'), 'train_loss_giou': tensor(0.5797, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1037, device='cuda:0'), 'validation_loss_ce': tensor(0.3896, device='cuda:0'), 'validation_loss_bbox': tensor(0.1421, device='cuda:0'), 'validation_loss_giou': tensor(0.5019, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8856, device='cuda:0'), 'train_loss_ce': tensor(0.3332, device='cuda:0'), 'train_loss_bbox': tensor(0.1328, device='cuda:0'), 'train_loss_giou': tensor(0.4441, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1537, device='cuda:0'), 'validation_loss_ce': tensor(0.3891, device='cuda:0'), 'validation_loss_bbox': tensor(0.1466, device='cuda:0'), 'validation_loss_giou': tensor(0.5159, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6333, device='cuda:0'), 'train_loss_ce': tensor(0.3565, device='cuda:0'), 'train_loss_bbox': tensor(0.1063, device='cuda:0'), 'train_loss_giou': tensor(0.3727, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0909, device='cuda:0'), 'validation_loss_ce': tensor(0.3881, device='cuda:0'), 'validation_loss_bbox': tensor(0.1418, device='cuda:0'), 'validation_loss_giou': tensor(0.4969, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3508, device='cuda:0'), 'train_loss_ce': tensor(0.4198, device='cuda:0'), 'train_loss_bbox': tensor(0.1620, device='cuda:0'), 'train_loss_giou': tensor(0.5604, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1124, device='cuda:0'), 'validation_loss_ce': tensor(0.3879, device='cuda:0'), 'validation_loss_bbox': tensor(0.1431, device='cuda:0'), 'validation_loss_giou': tensor(0.5046, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9618, device='cuda:0'), 'train_loss_ce': tensor(0.4041, device='cuda:0'), 'train_loss_bbox': tensor(0.1510, device='cuda:0'), 'train_loss_giou': tensor(0.4015, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0773, device='cuda:0'), 'validation_loss_ce': tensor(0.3807, device='cuda:0'), 'validation_loss_bbox': tensor(0.1397, device='cuda:0'), 'validation_loss_giou': tensor(0.4991, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7017, device='cuda:0'), 'train_loss_ce': tensor(0.4166, device='cuda:0'), 'train_loss_bbox': tensor(0.1304, device='cuda:0'), 'train_loss_giou': tensor(0.3166, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0984, device='cuda:0'), 'validation_loss_ce': tensor(0.3896, device='cuda:0'), 'validation_loss_bbox': tensor(0.1404, device='cuda:0'), 'validation_loss_giou': tensor(0.5034, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3735, device='cuda:0'), 'train_loss_ce': tensor(0.4548, device='cuda:0'), 'train_loss_bbox': tensor(0.1768, device='cuda:0'), 'train_loss_giou': tensor(0.5173, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3632, device='cuda:0'), 'validation_loss_ce': tensor(0.3965, device='cuda:0'), 'validation_loss_bbox': tensor(0.1657, device='cuda:0'), 'validation_loss_giou': tensor(0.5690, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3079, device='cuda:0'), 'train_loss_ce': tensor(0.2706, device='cuda:0'), 'train_loss_bbox': tensor(0.0826, device='cuda:0'), 'train_loss_giou': tensor(0.3122, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2601, device='cuda:0'), 'validation_loss_ce': tensor(0.3922, device='cuda:0'), 'validation_loss_bbox': tensor(0.1548, device='cuda:0'), 'validation_loss_giou': tensor(0.5470, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.8252, device='cuda:0'), 'train_loss_ce': tensor(0.3762, device='cuda:0'), 'train_loss_bbox': tensor(0.2220, device='cuda:0'), 'train_loss_giou': tensor(0.6695, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2968, device='cuda:0'), 'validation_loss_ce': tensor(0.3830, device='cuda:0'), 'validation_loss_bbox': tensor(0.1612, device='cuda:0'), 'validation_loss_giou': tensor(0.5540, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8611, device='cuda:0'), 'train_loss_ce': tensor(0.3391, device='cuda:0'), 'train_loss_bbox': tensor(0.1060, device='cuda:0'), 'train_loss_giou': tensor(0.4961, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2591, device='cuda:0'), 'validation_loss_ce': tensor(0.3903, device='cuda:0'), 'validation_loss_bbox': tensor(0.1556, device='cuda:0'), 'validation_loss_giou': tensor(0.5455, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1597, device='cuda:0'), 'train_loss_ce': tensor(0.3436, device='cuda:0'), 'train_loss_bbox': tensor(0.1736, device='cuda:0'), 'train_loss_giou': tensor(0.4740, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3239, device='cuda:0'), 'validation_loss_ce': tensor(0.3910, device='cuda:0'), 'validation_loss_bbox': tensor(0.1690, device='cuda:0'), 'validation_loss_giou': tensor(0.5441, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1617, device='cuda:0'), 'train_loss_ce': tensor(0.3271, device='cuda:0'), 'train_loss_bbox': tensor(0.1527, device='cuda:0'), 'train_loss_giou': tensor(0.5356, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2507, device='cuda:0'), 'validation_loss_ce': tensor(0.3840, device='cuda:0'), 'validation_loss_bbox': tensor(0.1617, device='cuda:0'), 'validation_loss_giou': tensor(0.5291, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7241, device='cuda:0'), 'train_loss_ce': tensor(0.3539, device='cuda:0'), 'train_loss_bbox': tensor(0.1142, device='cuda:0'), 'train_loss_giou': tensor(0.3996, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2363, device='cuda:0'), 'validation_loss_ce': tensor(0.3952, device='cuda:0'), 'validation_loss_bbox': tensor(0.1550, device='cuda:0'), 'validation_loss_giou': tensor(0.5330, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0634, device='cuda:0'), 'train_loss_ce': tensor(0.4071, device='cuda:0'), 'train_loss_bbox': tensor(0.1248, device='cuda:0'), 'train_loss_giou': tensor(0.5162, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1644, device='cuda:0'), 'validation_loss_ce': tensor(0.3900, device='cuda:0'), 'validation_loss_bbox': tensor(0.1508, device='cuda:0'), 'validation_loss_giou': tensor(0.5103, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6997, device='cuda:0'), 'train_loss_ce': tensor(0.4129, device='cuda:0'), 'train_loss_bbox': tensor(0.1807, device='cuda:0'), 'train_loss_giou': tensor(0.6917, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2791, device='cuda:0'), 'validation_loss_ce': tensor(0.4049, device='cuda:0'), 'validation_loss_bbox': tensor(0.1665, device='cuda:0'), 'validation_loss_giou': tensor(0.5209, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9458, device='cuda:0'), 'train_loss_ce': tensor(0.3765, device='cuda:0'), 'train_loss_bbox': tensor(0.1404, device='cuda:0'), 'train_loss_giou': tensor(0.4336, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1931, device='cuda:0'), 'validation_loss_ce': tensor(0.3904, device='cuda:0'), 'validation_loss_bbox': tensor(0.1503, device='cuda:0'), 'validation_loss_giou': tensor(0.5257, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9269, device='cuda:0'), 'train_loss_ce': tensor(0.4099, device='cuda:0'), 'train_loss_bbox': tensor(0.1275, device='cuda:0'), 'train_loss_giou': tensor(0.4397, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1903, device='cuda:0'), 'validation_loss_ce': tensor(0.3879, device='cuda:0'), 'validation_loss_bbox': tensor(0.1489, device='cuda:0'), 'validation_loss_giou': tensor(0.5290, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9057, device='cuda:0'), 'train_loss_ce': tensor(0.4524, device='cuda:0'), 'train_loss_bbox': tensor(0.1142, device='cuda:0'), 'train_loss_giou': tensor(0.4411, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0911, device='cuda:0'), 'validation_loss_ce': tensor(0.3805, device='cuda:0'), 'validation_loss_bbox': tensor(0.1396, device='cuda:0'), 'validation_loss_giou': tensor(0.5063, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0923, device='cuda:0'), 'train_loss_ce': tensor(0.4072, device='cuda:0'), 'train_loss_bbox': tensor(0.1287, device='cuda:0'), 'train_loss_giou': tensor(0.5208, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1969, device='cuda:0'), 'validation_loss_ce': tensor(0.3828, device='cuda:0'), 'validation_loss_bbox': tensor(0.1566, device='cuda:0'), 'validation_loss_giou': tensor(0.5156, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4672, device='cuda:0'), 'train_loss_ce': tensor(0.5280, device='cuda:0'), 'train_loss_bbox': tensor(0.1690, device='cuda:0'), 'train_loss_giou': tensor(0.5471, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0974, device='cuda:0'), 'validation_loss_ce': tensor(0.3946, device='cuda:0'), 'validation_loss_bbox': tensor(0.1437, device='cuda:0'), 'validation_loss_giou': tensor(0.4922, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5963, device='cuda:0'), 'train_loss_ce': tensor(0.4014, device='cuda:0'), 'train_loss_bbox': tensor(0.1816, device='cuda:0'), 'train_loss_giou': tensor(0.6435, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1513, device='cuda:0'), 'validation_loss_ce': tensor(0.3863, device='cuda:0'), 'validation_loss_bbox': tensor(0.1443, device='cuda:0'), 'validation_loss_giou': tensor(0.5216, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9654, device='cuda:0'), 'train_loss_ce': tensor(0.3026, device='cuda:0'), 'train_loss_bbox': tensor(0.1365, device='cuda:0'), 'train_loss_giou': tensor(0.4902, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2314, device='cuda:0'), 'validation_loss_ce': tensor(0.3877, device='cuda:0'), 'validation_loss_bbox': tensor(0.1528, device='cuda:0'), 'validation_loss_giou': tensor(0.5398, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9687, device='cuda:0'), 'train_loss_ce': tensor(0.3729, device='cuda:0'), 'train_loss_bbox': tensor(0.1622, device='cuda:0'), 'train_loss_giou': tensor(0.3923, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1475, device='cuda:0'), 'validation_loss_ce': tensor(0.3767, device='cuda:0'), 'validation_loss_bbox': tensor(0.1491, device='cuda:0'), 'validation_loss_giou': tensor(0.5126, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4296, device='cuda:0'), 'train_loss_ce': tensor(0.2140, device='cuda:0'), 'train_loss_bbox': tensor(0.1756, device='cuda:0'), 'train_loss_giou': tensor(0.6689, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1328, device='cuda:0'), 'validation_loss_ce': tensor(0.3888, device='cuda:0'), 'validation_loss_bbox': tensor(0.1481, device='cuda:0'), 'validation_loss_giou': tensor(0.5019, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8702, device='cuda:0'), 'train_loss_ce': tensor(0.2695, device='cuda:0'), 'train_loss_bbox': tensor(0.1544, device='cuda:0'), 'train_loss_giou': tensor(0.4144, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1586, device='cuda:0'), 'validation_loss_ce': tensor(0.3828, device='cuda:0'), 'validation_loss_bbox': tensor(0.1482, device='cuda:0'), 'validation_loss_giou': tensor(0.5174, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0132, device='cuda:0'), 'train_loss_ce': tensor(0.3941, device='cuda:0'), 'train_loss_bbox': tensor(0.1352, device='cuda:0'), 'train_loss_giou': tensor(0.4715, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1175, device='cuda:0'), 'validation_loss_ce': tensor(0.3849, device='cuda:0'), 'validation_loss_bbox': tensor(0.1429, device='cuda:0'), 'validation_loss_giou': tensor(0.5089, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6630, device='cuda:0'), 'train_loss_ce': tensor(0.3180, device='cuda:0'), 'train_loss_bbox': tensor(0.1049, device='cuda:0'), 'train_loss_giou': tensor(0.4103, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1341, device='cuda:0'), 'validation_loss_ce': tensor(0.3842, device='cuda:0'), 'validation_loss_bbox': tensor(0.1491, device='cuda:0'), 'validation_loss_giou': tensor(0.5022, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9227, device='cuda:0'), 'train_loss_ce': tensor(0.4113, device='cuda:0'), 'train_loss_bbox': tensor(0.1152, device='cuda:0'), 'train_loss_giou': tensor(0.4676, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0356, device='cuda:0'), 'validation_loss_ce': tensor(0.3717, device='cuda:0'), 'validation_loss_bbox': tensor(0.1374, device='cuda:0'), 'validation_loss_giou': tensor(0.4884, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3076, device='cuda:0'), 'train_loss_ce': tensor(0.3604, device='cuda:0'), 'train_loss_bbox': tensor(0.1494, device='cuda:0'), 'train_loss_giou': tensor(0.6001, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1031, device='cuda:0'), 'validation_loss_ce': tensor(0.3780, device='cuda:0'), 'validation_loss_bbox': tensor(0.1395, device='cuda:0'), 'validation_loss_giou': tensor(0.5138, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9373, device='cuda:0'), 'train_loss_ce': tensor(0.3131, device='cuda:0'), 'train_loss_bbox': tensor(0.1459, device='cuda:0'), 'train_loss_giou': tensor(0.4473, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0742, device='cuda:0'), 'validation_loss_ce': tensor(0.3749, device='cuda:0'), 'validation_loss_bbox': tensor(0.1400, device='cuda:0'), 'validation_loss_giou': tensor(0.4996, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8095, device='cuda:0'), 'train_loss_ce': tensor(0.3213, device='cuda:0'), 'train_loss_bbox': tensor(0.1515, device='cuda:0'), 'train_loss_giou': tensor(0.3653, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1071, device='cuda:0'), 'validation_loss_ce': tensor(0.3784, device='cuda:0'), 'validation_loss_bbox': tensor(0.1437, device='cuda:0'), 'validation_loss_giou': tensor(0.5051, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6178, device='cuda:0'), 'train_loss_ce': tensor(0.4203, device='cuda:0'), 'train_loss_bbox': tensor(0.1502, device='cuda:0'), 'train_loss_giou': tensor(0.7231, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0622, device='cuda:0'), 'validation_loss_ce': tensor(0.3770, device='cuda:0'), 'validation_loss_bbox': tensor(0.1399, device='cuda:0'), 'validation_loss_giou': tensor(0.4929, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9998, device='cuda:0'), 'train_loss_ce': tensor(0.3468, device='cuda:0'), 'train_loss_bbox': tensor(0.1001, device='cuda:0'), 'train_loss_giou': tensor(0.5764, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1441, device='cuda:0'), 'validation_loss_ce': tensor(0.3831, device='cuda:0'), 'validation_loss_bbox': tensor(0.1456, device='cuda:0'), 'validation_loss_giou': tensor(0.5164, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9782, device='cuda:0'), 'train_loss_ce': tensor(0.4054, device='cuda:0'), 'train_loss_bbox': tensor(0.1321, device='cuda:0'), 'train_loss_giou': tensor(0.4561, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1425, device='cuda:0'), 'validation_loss_ce': tensor(0.3847, device='cuda:0'), 'validation_loss_bbox': tensor(0.1464, device='cuda:0'), 'validation_loss_giou': tensor(0.5129, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9136, device='cuda:0'), 'train_loss_ce': tensor(0.4279, device='cuda:0'), 'train_loss_bbox': tensor(0.1374, device='cuda:0'), 'train_loss_giou': tensor(0.3995, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1101, device='cuda:0'), 'validation_loss_ce': tensor(0.3910, device='cuda:0'), 'validation_loss_bbox': tensor(0.1424, device='cuda:0'), 'validation_loss_giou': tensor(0.5036, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8926, device='cuda:0'), 'train_loss_ce': tensor(0.3420, device='cuda:0'), 'train_loss_bbox': tensor(0.1447, device='cuda:0'), 'train_loss_giou': tensor(0.4135, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1459, device='cuda:0'), 'validation_loss_ce': tensor(0.3866, device='cuda:0'), 'validation_loss_bbox': tensor(0.1443, device='cuda:0'), 'validation_loss_giou': tensor(0.5188, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0064, device='cuda:0'), 'train_loss_ce': tensor(0.3268, device='cuda:0'), 'train_loss_bbox': tensor(0.1296, device='cuda:0'), 'train_loss_giou': tensor(0.5159, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2298, device='cuda:0'), 'validation_loss_ce': tensor(0.3862, device='cuda:0'), 'validation_loss_bbox': tensor(0.1531, device='cuda:0'), 'validation_loss_giou': tensor(0.5390, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7424, device='cuda:0'), 'train_loss_ce': tensor(0.3838, device='cuda:0'), 'train_loss_bbox': tensor(0.1051, device='cuda:0'), 'train_loss_giou': tensor(0.4167, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1152, device='cuda:0'), 'validation_loss_ce': tensor(0.3900, device='cuda:0'), 'validation_loss_bbox': tensor(0.1398, device='cuda:0'), 'validation_loss_giou': tensor(0.5131, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3007, device='cuda:0'), 'train_loss_ce': tensor(0.3842, device='cuda:0'), 'train_loss_bbox': tensor(0.1599, device='cuda:0'), 'train_loss_giou': tensor(0.5585, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0910, device='cuda:0'), 'validation_loss_ce': tensor(0.3870, device='cuda:0'), 'validation_loss_bbox': tensor(0.1410, device='cuda:0'), 'validation_loss_giou': tensor(0.4994, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7670, device='cuda:0'), 'train_loss_ce': tensor(0.4240, device='cuda:0'), 'train_loss_bbox': tensor(0.1228, device='cuda:0'), 'train_loss_giou': tensor(0.3645, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1181, device='cuda:0'), 'validation_loss_ce': tensor(0.3888, device='cuda:0'), 'validation_loss_bbox': tensor(0.1418, device='cuda:0'), 'validation_loss_giou': tensor(0.5101, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7135, device='cuda:0'), 'train_loss_ce': tensor(0.3542, device='cuda:0'), 'train_loss_bbox': tensor(0.1194, device='cuda:0'), 'train_loss_giou': tensor(0.3813, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1441, device='cuda:0'), 'validation_loss_ce': tensor(0.3948, device='cuda:0'), 'validation_loss_bbox': tensor(0.1464, device='cuda:0'), 'validation_loss_giou': tensor(0.5087, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0617, device='cuda:0'), 'train_loss_ce': tensor(0.3049, device='cuda:0'), 'train_loss_bbox': tensor(0.1232, device='cuda:0'), 'train_loss_giou': tensor(0.5704, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0647, device='cuda:0'), 'validation_loss_ce': tensor(0.3746, device='cuda:0'), 'validation_loss_bbox': tensor(0.1383, device='cuda:0'), 'validation_loss_giou': tensor(0.4995, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3113, device='cuda:0'), 'train_loss_ce': tensor(0.3726, device='cuda:0'), 'train_loss_bbox': tensor(0.1478, device='cuda:0'), 'train_loss_giou': tensor(0.5998, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0895, device='cuda:0'), 'validation_loss_ce': tensor(0.3840, device='cuda:0'), 'validation_loss_bbox': tensor(0.1399, device='cuda:0'), 'validation_loss_giou': tensor(0.5030, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6955, device='cuda:0'), 'train_loss_ce': tensor(0.3359, device='cuda:0'), 'train_loss_bbox': tensor(0.1047, device='cuda:0'), 'train_loss_giou': tensor(0.4181, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0781, device='cuda:0'), 'validation_loss_ce': tensor(0.3824, device='cuda:0'), 'validation_loss_bbox': tensor(0.1402, device='cuda:0'), 'validation_loss_giou': tensor(0.4973, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0612, device='cuda:0'), 'train_loss_ce': tensor(0.4501, device='cuda:0'), 'train_loss_bbox': tensor(0.1447, device='cuda:0'), 'train_loss_giou': tensor(0.4437, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0666, device='cuda:0'), 'validation_loss_ce': tensor(0.3823, device='cuda:0'), 'validation_loss_bbox': tensor(0.1380, device='cuda:0'), 'validation_loss_giou': tensor(0.4971, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1554, device='cuda:0'), 'train_loss_ce': tensor(0.3281, device='cuda:0'), 'train_loss_bbox': tensor(0.1632, device='cuda:0'), 'train_loss_giou': tensor(0.5056, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0265, device='cuda:0'), 'validation_loss_ce': tensor(0.3866, device='cuda:0'), 'validation_loss_bbox': tensor(0.1341, device='cuda:0'), 'validation_loss_giou': tensor(0.4847, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1641, device='cuda:0'), 'train_loss_ce': tensor(0.2473, device='cuda:0'), 'train_loss_bbox': tensor(0.1654, device='cuda:0'), 'train_loss_giou': tensor(0.5449, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1640, device='cuda:0'), 'validation_loss_ce': tensor(0.3883, device='cuda:0'), 'validation_loss_bbox': tensor(0.1466, device='cuda:0'), 'validation_loss_giou': tensor(0.5214, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4207, device='cuda:0'), 'train_loss_ce': tensor(0.4055, device='cuda:0'), 'train_loss_bbox': tensor(0.1700, device='cuda:0'), 'train_loss_giou': tensor(0.5826, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1271, device='cuda:0'), 'validation_loss_ce': tensor(0.3914, device='cuda:0'), 'validation_loss_bbox': tensor(0.1436, device='cuda:0'), 'validation_loss_giou': tensor(0.5087, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7412, device='cuda:0'), 'train_loss_ce': tensor(0.3063, device='cuda:0'), 'train_loss_bbox': tensor(0.1244, device='cuda:0'), 'train_loss_giou': tensor(0.4065, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1272, device='cuda:0'), 'validation_loss_ce': tensor(0.3834, device='cuda:0'), 'validation_loss_bbox': tensor(0.1448, device='cuda:0'), 'validation_loss_giou': tensor(0.5098, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9508, device='cuda:0'), 'train_loss_ce': tensor(0.3791, device='cuda:0'), 'train_loss_bbox': tensor(0.1437, device='cuda:0'), 'train_loss_giou': tensor(0.4267, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1190, device='cuda:0'), 'validation_loss_ce': tensor(0.3838, device='cuda:0'), 'validation_loss_bbox': tensor(0.1432, device='cuda:0'), 'validation_loss_giou': tensor(0.5095, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2006, device='cuda:0'), 'train_loss_ce': tensor(0.3864, device='cuda:0'), 'train_loss_bbox': tensor(0.1780, device='cuda:0'), 'train_loss_giou': tensor(0.4620, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1253, device='cuda:0'), 'validation_loss_ce': tensor(0.3810, device='cuda:0'), 'validation_loss_bbox': tensor(0.1439, device='cuda:0'), 'validation_loss_giou': tensor(0.5124, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4256, device='cuda:0'), 'train_loss_ce': tensor(0.5020, device='cuda:0'), 'train_loss_bbox': tensor(0.1734, device='cuda:0'), 'train_loss_giou': tensor(0.5282, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0987, device='cuda:0'), 'validation_loss_ce': tensor(0.3872, device='cuda:0'), 'validation_loss_bbox': tensor(0.1418, device='cuda:0'), 'validation_loss_giou': tensor(0.5012, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2453, device='cuda:0'), 'train_loss_ce': tensor(0.4289, device='cuda:0'), 'train_loss_bbox': tensor(0.1498, device='cuda:0'), 'train_loss_giou': tensor(0.5338, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0983, device='cuda:0'), 'validation_loss_ce': tensor(0.3799, device='cuda:0'), 'validation_loss_bbox': tensor(0.1412, device='cuda:0'), 'validation_loss_giou': tensor(0.5062, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4796, device='cuda:0'), 'train_loss_ce': tensor(0.2681, device='cuda:0'), 'train_loss_bbox': tensor(0.1205, device='cuda:0'), 'train_loss_giou': tensor(0.3044, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1008, device='cuda:0'), 'validation_loss_ce': tensor(0.3861, device='cuda:0'), 'validation_loss_bbox': tensor(0.1391, device='cuda:0'), 'validation_loss_giou': tensor(0.5096, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3822, device='cuda:0'), 'train_loss_ce': tensor(0.3696, device='cuda:0'), 'train_loss_bbox': tensor(0.0844, device='cuda:0'), 'train_loss_giou': tensor(0.2953, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1172, device='cuda:0'), 'validation_loss_ce': tensor(0.3801, device='cuda:0'), 'validation_loss_bbox': tensor(0.1435, device='cuda:0'), 'validation_loss_giou': tensor(0.5099, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.1159, device='cuda:0'), 'train_loss_ce': tensor(0.2532, device='cuda:0'), 'train_loss_bbox': tensor(0.0669, device='cuda:0'), 'train_loss_giou': tensor(0.2641, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0887, device='cuda:0'), 'validation_loss_ce': tensor(0.3829, device='cuda:0'), 'validation_loss_bbox': tensor(0.1407, device='cuda:0'), 'validation_loss_giou': tensor(0.5012, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.8004, device='cuda:0'), 'train_loss_ce': tensor(0.4254, device='cuda:0'), 'train_loss_bbox': tensor(0.2034, device='cuda:0'), 'train_loss_giou': tensor(0.6789, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2491, device='cuda:0'), 'validation_loss_ce': tensor(0.3978, device='cuda:0'), 'validation_loss_bbox': tensor(0.1568, device='cuda:0'), 'validation_loss_giou': tensor(0.5335, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8112, device='cuda:0'), 'train_loss_ce': tensor(0.3750, device='cuda:0'), 'train_loss_bbox': tensor(0.1182, device='cuda:0'), 'train_loss_giou': tensor(0.4225, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1480, device='cuda:0'), 'validation_loss_ce': tensor(0.3834, device='cuda:0'), 'validation_loss_bbox': tensor(0.1427, device='cuda:0'), 'validation_loss_giou': tensor(0.5256, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4008, device='cuda:0'), 'train_loss_ce': tensor(0.3449, device='cuda:0'), 'train_loss_bbox': tensor(0.1503, device='cuda:0'), 'train_loss_giou': tensor(0.6523, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0899, device='cuda:0'), 'validation_loss_ce': tensor(0.3876, device='cuda:0'), 'validation_loss_bbox': tensor(0.1400, device='cuda:0'), 'validation_loss_giou': tensor(0.5012, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.1745, device='cuda:0'), 'train_loss_ce': tensor(0.4971, device='cuda:0'), 'train_loss_bbox': tensor(0.2124, device='cuda:0'), 'train_loss_giou': tensor(0.8078, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1329, device='cuda:0'), 'validation_loss_ce': tensor(0.3873, device='cuda:0'), 'validation_loss_bbox': tensor(0.1438, device='cuda:0'), 'validation_loss_giou': tensor(0.5133, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0606, device='cuda:0'), 'train_loss_ce': tensor(0.3543, device='cuda:0'), 'train_loss_bbox': tensor(0.1164, device='cuda:0'), 'train_loss_giou': tensor(0.5622, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1552, device='cuda:0'), 'validation_loss_ce': tensor(0.3898, device='cuda:0'), 'validation_loss_bbox': tensor(0.1427, device='cuda:0'), 'validation_loss_giou': tensor(0.5259, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9711, device='cuda:0'), 'train_loss_ce': tensor(0.4405, device='cuda:0'), 'train_loss_bbox': tensor(0.1290, device='cuda:0'), 'train_loss_giou': tensor(0.4428, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0661, device='cuda:0'), 'validation_loss_ce': tensor(0.3795, device='cuda:0'), 'validation_loss_bbox': tensor(0.1382, device='cuda:0'), 'validation_loss_giou': tensor(0.4979, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5544, device='cuda:0'), 'train_loss_ce': tensor(0.3512, device='cuda:0'), 'train_loss_bbox': tensor(0.0953, device='cuda:0'), 'train_loss_giou': tensor(0.3635, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1638, device='cuda:0'), 'validation_loss_ce': tensor(0.3920, device='cuda:0'), 'validation_loss_bbox': tensor(0.1418, device='cuda:0'), 'validation_loss_giou': tensor(0.5314, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8749, device='cuda:0'), 'train_loss_ce': tensor(0.2948, device='cuda:0'), 'train_loss_bbox': tensor(0.1171, device='cuda:0'), 'train_loss_giou': tensor(0.4974, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1265, device='cuda:0'), 'validation_loss_ce': tensor(0.3888, device='cuda:0'), 'validation_loss_bbox': tensor(0.1444, device='cuda:0'), 'validation_loss_giou': tensor(0.5078, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1892, device='cuda:0'), 'train_loss_ce': tensor(0.4731, device='cuda:0'), 'train_loss_bbox': tensor(0.1667, device='cuda:0'), 'train_loss_giou': tensor(0.4413, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1397, device='cuda:0'), 'validation_loss_ce': tensor(0.3913, device='cuda:0'), 'validation_loss_bbox': tensor(0.1409, device='cuda:0'), 'validation_loss_giou': tensor(0.5219, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6873, device='cuda:0'), 'train_loss_ce': tensor(0.2624, device='cuda:0'), 'train_loss_bbox': tensor(0.0988, device='cuda:0'), 'train_loss_giou': tensor(0.4655, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1196, device='cuda:0'), 'validation_loss_ce': tensor(0.3859, device='cuda:0'), 'validation_loss_bbox': tensor(0.1396, device='cuda:0'), 'validation_loss_giou': tensor(0.5178, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6725, device='cuda:0'), 'train_loss_ce': tensor(0.2990, device='cuda:0'), 'train_loss_bbox': tensor(0.1056, device='cuda:0'), 'train_loss_giou': tensor(0.4227, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0944, device='cuda:0'), 'validation_loss_ce': tensor(0.3873, device='cuda:0'), 'validation_loss_bbox': tensor(0.1395, device='cuda:0'), 'validation_loss_giou': tensor(0.5047, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9737, device='cuda:0'), 'train_loss_ce': tensor(0.3862, device='cuda:0'), 'train_loss_bbox': tensor(0.1393, device='cuda:0'), 'train_loss_giou': tensor(0.4454, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1188, device='cuda:0'), 'validation_loss_ce': tensor(0.3850, device='cuda:0'), 'validation_loss_bbox': tensor(0.1409, device='cuda:0'), 'validation_loss_giou': tensor(0.5148, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9090, device='cuda:0'), 'train_loss_ce': tensor(0.3899, device='cuda:0'), 'train_loss_bbox': tensor(0.1334, device='cuda:0'), 'train_loss_giou': tensor(0.4259, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1303, device='cuda:0'), 'validation_loss_ce': tensor(0.3922, device='cuda:0'), 'validation_loss_bbox': tensor(0.1415, device='cuda:0'), 'validation_loss_giou': tensor(0.5154, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7123, device='cuda:0'), 'train_loss_ce': tensor(0.3532, device='cuda:0'), 'train_loss_bbox': tensor(0.1297, device='cuda:0'), 'train_loss_giou': tensor(0.3552, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1428, device='cuda:0'), 'validation_loss_ce': tensor(0.3844, device='cuda:0'), 'validation_loss_bbox': tensor(0.1410, device='cuda:0'), 'validation_loss_giou': tensor(0.5268, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5493, device='cuda:0'), 'train_loss_ce': tensor(0.3313, device='cuda:0'), 'train_loss_bbox': tensor(0.1282, device='cuda:0'), 'train_loss_giou': tensor(0.2885, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1454, device='cuda:0'), 'validation_loss_ce': tensor(0.3884, device='cuda:0'), 'validation_loss_bbox': tensor(0.1415, device='cuda:0'), 'validation_loss_giou': tensor(0.5247, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
Downloads last month
5
Safetensors
Model size
41.6M 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.