Hugging Face's logo

MedicalVision
/
detr_nih_50ep_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 ] = 0.001
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.015
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.016
 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 ] = 0.016

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 ] = 0.015
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.004
 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 ] = 0.046
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.119
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.134
 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 ] = 0.144

Config

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

Logging

Training process 

{'validation_loss': tensor(6.1640, device='cuda:0'), 'validation_loss_ce': tensor(2.3579, device='cuda:0'), 'validation_loss_bbox': tensor(0.4592, device='cuda:0'), 'validation_loss_giou': tensor(0.7551, device='cuda:0'), 'validation_cardinality_error': tensor(99., device='cuda:0')}
{'training_loss': tensor(2.5012, device='cuda:0'), 'train_loss_ce': tensor(0.4724, device='cuda:0'), 'train_loss_bbox': tensor(0.2203, device='cuda:0'), 'train_loss_giou': tensor(0.4637, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5773, device='cuda:0'), 'validation_loss_ce': tensor(0.4940, device='cuda:0'), 'validation_loss_bbox': tensor(0.1985, device='cuda:0'), 'validation_loss_giou': tensor(0.5455, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5154, device='cuda:0'), 'train_loss_ce': tensor(0.5113, device='cuda:0'), 'train_loss_bbox': tensor(0.1683, device='cuda:0'), 'train_loss_giou': tensor(0.5813, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8801, device='cuda:0'), 'validation_loss_ce': tensor(0.5555, device='cuda:0'), 'validation_loss_bbox': tensor(0.2172, device='cuda:0'), 'validation_loss_giou': tensor(0.6192, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0469, device='cuda:0'), 'train_loss_ce': tensor(0.4756, device='cuda:0'), 'train_loss_bbox': tensor(0.1356, device='cuda:0'), 'train_loss_giou': tensor(0.4466, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2915, device='cuda:0'), 'validation_loss_ce': tensor(0.4524, device='cuda:0'), 'validation_loss_bbox': tensor(0.1640, device='cuda:0'), 'validation_loss_giou': tensor(0.5096, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3943, device='cuda:0'), 'train_loss_ce': tensor(0.4142, device='cuda:0'), 'train_loss_bbox': tensor(0.1636, device='cuda:0'), 'train_loss_giou': tensor(0.5811, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2868, device='cuda:0'), 'validation_loss_ce': tensor(0.4460, device='cuda:0'), 'validation_loss_bbox': tensor(0.1624, device='cuda:0'), 'validation_loss_giou': tensor(0.5145, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5273, device='cuda:0'), 'train_loss_ce': tensor(0.4767, device='cuda:0'), 'train_loss_bbox': tensor(0.1770, device='cuda:0'), 'train_loss_giou': tensor(0.5829, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2147, device='cuda:0'), 'validation_loss_ce': tensor(0.4427, device='cuda:0'), 'validation_loss_bbox': tensor(0.1484, device='cuda:0'), 'validation_loss_giou': tensor(0.5149, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4827, device='cuda:0'), 'train_loss_ce': tensor(0.4289, device='cuda:0'), 'train_loss_bbox': tensor(0.1703, device='cuda:0'), 'train_loss_giou': tensor(0.6011, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2678, device='cuda:0'), 'validation_loss_ce': tensor(0.4398, device='cuda:0'), 'validation_loss_bbox': tensor(0.1587, device='cuda:0'), 'validation_loss_giou': tensor(0.5174, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9188, device='cuda:0'), 'train_loss_ce': tensor(0.4719, device='cuda:0'), 'train_loss_bbox': tensor(0.1112, device='cuda:0'), 'train_loss_giou': tensor(0.4454, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1029, device='cuda:0'), 'validation_loss_ce': tensor(0.4342, device='cuda:0'), 'validation_loss_bbox': tensor(0.1393, device='cuda:0'), 'validation_loss_giou': tensor(0.4862, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1726, device='cuda:0'), 'train_loss_ce': tensor(0.3913, device='cuda:0'), 'train_loss_bbox': tensor(0.1488, device='cuda:0'), 'train_loss_giou': tensor(0.5187, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1978, device='cuda:0'), 'validation_loss_ce': tensor(0.4290, device='cuda:0'), 'validation_loss_bbox': tensor(0.1498, device='cuda:0'), 'validation_loss_giou': tensor(0.5099, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9089, device='cuda:0'), 'train_loss_ce': tensor(0.3796, device='cuda:0'), 'train_loss_bbox': tensor(0.1238, device='cuda:0'), 'train_loss_giou': tensor(0.4551, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1008, device='cuda:0'), 'validation_loss_ce': tensor(0.4223, device='cuda:0'), 'validation_loss_bbox': tensor(0.1397, device='cuda:0'), 'validation_loss_giou': tensor(0.4901, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5439, device='cuda:0'), 'train_loss_ce': tensor(0.4430, device='cuda:0'), 'train_loss_bbox': tensor(0.1633, device='cuda:0'), 'train_loss_giou': tensor(0.6422, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2259, device='cuda:0'), 'validation_loss_ce': tensor(0.4223, device='cuda:0'), 'validation_loss_bbox': tensor(0.1489, device='cuda:0'), 'validation_loss_giou': tensor(0.5297, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3302, device='cuda:0'), 'train_loss_ce': tensor(0.4776, device='cuda:0'), 'train_loss_bbox': tensor(0.1556, device='cuda:0'), 'train_loss_giou': tensor(0.5373, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1065, device='cuda:0'), 'validation_loss_ce': tensor(0.4252, device='cuda:0'), 'validation_loss_bbox': tensor(0.1390, device='cuda:0'), 'validation_loss_giou': tensor(0.4932, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1398, device='cuda:0'), 'train_loss_ce': tensor(0.5075, device='cuda:0'), 'train_loss_bbox': tensor(0.1335, device='cuda:0'), 'train_loss_giou': tensor(0.4824, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1445, device='cuda:0'), 'validation_loss_ce': tensor(0.4139, device='cuda:0'), 'validation_loss_bbox': tensor(0.1501, device='cuda:0'), 'validation_loss_giou': tensor(0.4900, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1887, device='cuda:0'), 'train_loss_ce': tensor(0.4217, device='cuda:0'), 'train_loss_bbox': tensor(0.1795, device='cuda:0'), 'train_loss_giou': tensor(0.4347, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3315, device='cuda:0'), 'validation_loss_ce': tensor(0.4187, device='cuda:0'), 'validation_loss_bbox': tensor(0.1654, device='cuda:0'), 'validation_loss_giou': tensor(0.5431, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2062, device='cuda:0'), 'train_loss_ce': tensor(0.4076, device='cuda:0'), 'train_loss_bbox': tensor(0.1169, device='cuda:0'), 'train_loss_giou': tensor(0.6070, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1468, device='cuda:0'), 'validation_loss_ce': tensor(0.3972, device='cuda:0'), 'validation_loss_bbox': tensor(0.1463, device='cuda:0'), 'validation_loss_giou': tensor(0.5090, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8832, device='cuda:0'), 'train_loss_ce': tensor(0.4271, device='cuda:0'), 'train_loss_bbox': tensor(0.1041, device='cuda:0'), 'train_loss_giou': tensor(0.4677, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0993, device='cuda:0'), 'validation_loss_ce': tensor(0.4163, device='cuda:0'), 'validation_loss_bbox': tensor(0.1366, device='cuda:0'), 'validation_loss_giou': tensor(0.4999, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4581, device='cuda:0'), 'train_loss_ce': tensor(0.4431, device='cuda:0'), 'train_loss_bbox': tensor(0.1646, device='cuda:0'), 'train_loss_giou': tensor(0.5961, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1039, device='cuda:0'), 'validation_loss_ce': tensor(0.4058, device='cuda:0'), 'validation_loss_bbox': tensor(0.1386, device='cuda:0'), 'validation_loss_giou': tensor(0.5025, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5800, device='cuda:0'), 'train_loss_ce': tensor(0.4083, device='cuda:0'), 'train_loss_bbox': tensor(0.1037, device='cuda:0'), 'train_loss_giou': tensor(0.3266, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2610, device='cuda:0'), 'validation_loss_ce': tensor(0.4097, device='cuda:0'), 'validation_loss_bbox': tensor(0.1609, device='cuda:0'), 'validation_loss_giou': tensor(0.5235, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1973, device='cuda:0'), 'train_loss_ce': tensor(0.3197, device='cuda:0'), 'train_loss_bbox': tensor(0.1813, device='cuda:0'), 'train_loss_giou': tensor(0.4854, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0723, device='cuda:0'), 'validation_loss_ce': tensor(0.4049, device='cuda:0'), 'validation_loss_bbox': tensor(0.1411, device='cuda:0'), 'validation_loss_giou': tensor(0.4810, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2071, device='cuda:0'), 'train_loss_ce': tensor(0.3585, device='cuda:0'), 'train_loss_bbox': tensor(0.1437, device='cuda:0'), 'train_loss_giou': tensor(0.5650, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0872, device='cuda:0'), 'validation_loss_ce': tensor(0.4076, device='cuda:0'), 'validation_loss_bbox': tensor(0.1370, device='cuda:0'), 'validation_loss_giou': tensor(0.4973, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0057, device='cuda:0'), 'train_loss_ce': tensor(0.3216, device='cuda:0'), 'train_loss_bbox': tensor(0.1447, device='cuda:0'), 'train_loss_giou': tensor(0.4802, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0882, device='cuda:0'), 'validation_loss_ce': tensor(0.3940, device='cuda:0'), 'validation_loss_bbox': tensor(0.1410, device='cuda:0'), 'validation_loss_giou': tensor(0.4947, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2207, device='cuda:0'), 'train_loss_ce': tensor(0.4783, device='cuda:0'), 'train_loss_bbox': tensor(0.1521, device='cuda:0'), 'train_loss_giou': tensor(0.4910, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0525, device='cuda:0'), 'validation_loss_ce': tensor(0.3939, device='cuda:0'), 'validation_loss_bbox': tensor(0.1337, device='cuda:0'), 'validation_loss_giou': tensor(0.4950, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0346, device='cuda:0'), 'train_loss_ce': tensor(0.3853, device='cuda:0'), 'train_loss_bbox': tensor(0.1412, device='cuda:0'), 'train_loss_giou': tensor(0.4717, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9823, device='cuda:0'), 'validation_loss_ce': tensor(0.3958, device='cuda:0'), 'validation_loss_bbox': tensor(0.1272, device='cuda:0'), 'validation_loss_giou': tensor(0.4752, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6690, device='cuda:0'), 'train_loss_ce': tensor(0.4342, device='cuda:0'), 'train_loss_bbox': tensor(0.1134, device='cuda:0'), 'train_loss_giou': tensor(0.3340, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9776, device='cuda:0'), 'validation_loss_ce': tensor(0.3931, device='cuda:0'), 'validation_loss_bbox': tensor(0.1266, device='cuda:0'), 'validation_loss_giou': tensor(0.4758, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3649, device='cuda:0'), 'train_loss_ce': tensor(0.4440, device='cuda:0'), 'train_loss_bbox': tensor(0.1662, device='cuda:0'), 'train_loss_giou': tensor(0.5448, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1280, device='cuda:0'), 'validation_loss_ce': tensor(0.3865, device='cuda:0'), 'validation_loss_bbox': tensor(0.1415, device='cuda:0'), 'validation_loss_giou': tensor(0.5171, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7902, device='cuda:0'), 'train_loss_ce': tensor(0.4198, device='cuda:0'), 'train_loss_bbox': tensor(0.1162, device='cuda:0'), 'train_loss_giou': tensor(0.3948, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0824, device='cuda:0'), 'validation_loss_ce': tensor(0.3995, device='cuda:0'), 'validation_loss_bbox': tensor(0.1363, device='cuda:0'), 'validation_loss_giou': tensor(0.5006, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6075, device='cuda:0'), 'train_loss_ce': tensor(0.3179, device='cuda:0'), 'train_loss_bbox': tensor(0.1335, device='cuda:0'), 'train_loss_giou': tensor(0.3111, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0013, device='cuda:0'), 'validation_loss_ce': tensor(0.3906, device='cuda:0'), 'validation_loss_bbox': tensor(0.1329, device='cuda:0'), 'validation_loss_giou': tensor(0.4732, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3555, device='cuda:0'), 'train_loss_ce': tensor(0.3328, device='cuda:0'), 'train_loss_bbox': tensor(0.1481, device='cuda:0'), 'train_loss_giou': tensor(0.6411, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4579, device='cuda:0'), 'validation_loss_ce': tensor(0.4127, device='cuda:0'), 'validation_loss_bbox': tensor(0.1690, device='cuda:0'), 'validation_loss_giou': tensor(0.6000, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1152, device='cuda:0'), 'train_loss_ce': tensor(0.3413, device='cuda:0'), 'train_loss_bbox': tensor(0.1326, device='cuda:0'), 'train_loss_giou': tensor(0.5554, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2993, device='cuda:0'), 'validation_loss_ce': tensor(0.4124, device='cuda:0'), 'validation_loss_bbox': tensor(0.1615, device='cuda:0'), 'validation_loss_giou': tensor(0.5396, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9825, device='cuda:0'), 'train_loss_ce': tensor(0.3400, device='cuda:0'), 'train_loss_bbox': tensor(0.1429, device='cuda:0'), 'train_loss_giou': tensor(0.4642, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2102, device='cuda:0'), 'validation_loss_ce': tensor(0.3878, device='cuda:0'), 'validation_loss_bbox': tensor(0.1523, device='cuda:0'), 'validation_loss_giou': tensor(0.5306, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6589, device='cuda:0'), 'train_loss_ce': tensor(0.3617, device='cuda:0'), 'train_loss_bbox': tensor(0.1531, device='cuda:0'), 'train_loss_giou': tensor(0.7660, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2398, device='cuda:0'), 'validation_loss_ce': tensor(0.3987, device='cuda:0'), 'validation_loss_bbox': tensor(0.1506, device='cuda:0'), 'validation_loss_giou': tensor(0.5440, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1258, device='cuda:0'), 'train_loss_ce': tensor(0.3308, device='cuda:0'), 'train_loss_bbox': tensor(0.1240, device='cuda:0'), 'train_loss_giou': tensor(0.5875, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2911, device='cuda:0'), 'validation_loss_ce': tensor(0.3962, device='cuda:0'), 'validation_loss_bbox': tensor(0.1593, device='cuda:0'), 'validation_loss_giou': tensor(0.5493, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5479, device='cuda:0'), 'train_loss_ce': tensor(0.3155, device='cuda:0'), 'train_loss_bbox': tensor(0.1927, device='cuda:0'), 'train_loss_giou': tensor(0.6345, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.3226, device='cuda:0'), 'validation_loss_ce': tensor(0.3773, device='cuda:0'), 'validation_loss_bbox': tensor(0.1629, device='cuda:0'), 'validation_loss_giou': tensor(0.5653, device='cuda:0'), 'validation_cardinality_error': tensor(0.5859, device='cuda:0')}
{'training_loss': tensor(2.5620, device='cuda:0'), 'train_loss_ce': tensor(0.4515, device='cuda:0'), 'train_loss_bbox': tensor(0.1527, device='cuda:0'), 'train_loss_giou': tensor(0.6736, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(2.1497, device='cuda:0'), 'validation_loss_ce': tensor(0.3689, device='cuda:0'), 'validation_loss_bbox': tensor(0.1470, device='cuda:0'), 'validation_loss_giou': tensor(0.5230, device='cuda:0'), 'validation_cardinality_error': tensor(0.4141, device='cuda:0')}
{'training_loss': tensor(2.5146, device='cuda:0'), 'train_loss_ce': tensor(0.3962, device='cuda:0'), 'train_loss_bbox': tensor(0.1918, device='cuda:0'), 'train_loss_giou': tensor(0.5796, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5146, device='cuda:0'), 'validation_loss_ce': tensor(0.3989, device='cuda:0'), 'validation_loss_bbox': tensor(0.1821, device='cuda:0'), 'validation_loss_giou': tensor(0.6027, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8231, device='cuda:0'), 'train_loss_ce': tensor(0.4103, device='cuda:0'), 'train_loss_bbox': tensor(0.1066, device='cuda:0'), 'train_loss_giou': tensor(0.4399, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2608, device='cuda:0'), 'validation_loss_ce': tensor(0.3951, device='cuda:0'), 'validation_loss_bbox': tensor(0.1601, device='cuda:0'), 'validation_loss_giou': tensor(0.5325, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0888, device='cuda:0'), 'train_loss_ce': tensor(0.4642, device='cuda:0'), 'train_loss_bbox': tensor(0.1357, device='cuda:0'), 'train_loss_giou': tensor(0.4729, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2711, device='cuda:0'), 'validation_loss_ce': tensor(0.3976, device='cuda:0'), 'validation_loss_bbox': tensor(0.1558, device='cuda:0'), 'validation_loss_giou': tensor(0.5472, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0932, device='cuda:0'), 'train_loss_ce': tensor(0.3924, device='cuda:0'), 'train_loss_bbox': tensor(0.1468, device='cuda:0'), 'train_loss_giou': tensor(0.4834, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3666, device='cuda:0'), 'validation_loss_ce': tensor(0.3975, device='cuda:0'), 'validation_loss_bbox': tensor(0.1651, device='cuda:0'), 'validation_loss_giou': tensor(0.5717, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0294, device='cuda:0'), 'train_loss_ce': tensor(0.3249, device='cuda:0'), 'train_loss_bbox': tensor(0.1636, device='cuda:0'), 'train_loss_giou': tensor(0.4433, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2411, device='cuda:0'), 'validation_loss_ce': tensor(0.3884, device='cuda:0'), 'validation_loss_bbox': tensor(0.1540, device='cuda:0'), 'validation_loss_giou': tensor(0.5413, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0426, device='cuda:0'), 'train_loss_ce': tensor(0.3186, device='cuda:0'), 'train_loss_bbox': tensor(0.1670, device='cuda:0'), 'train_loss_giou': tensor(0.4445, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2531, device='cuda:0'), 'validation_loss_ce': tensor(0.3957, device='cuda:0'), 'validation_loss_bbox': tensor(0.1546, device='cuda:0'), 'validation_loss_giou': tensor(0.5422, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4282, device='cuda:0'), 'train_loss_ce': tensor(0.4977, device='cuda:0'), 'train_loss_bbox': tensor(0.1670, device='cuda:0'), 'train_loss_giou': tensor(0.5478, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2792, device='cuda:0'), 'validation_loss_ce': tensor(0.3941, device='cuda:0'), 'validation_loss_bbox': tensor(0.1566, device='cuda:0'), 'validation_loss_giou': tensor(0.5510, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2052, device='cuda:0'), 'train_loss_ce': tensor(0.3754, device='cuda:0'), 'train_loss_bbox': tensor(0.1486, device='cuda:0'), 'train_loss_giou': tensor(0.5433, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1271, device='cuda:0'), 'validation_loss_ce': tensor(0.3892, device='cuda:0'), 'validation_loss_bbox': tensor(0.1433, device='cuda:0'), 'validation_loss_giou': tensor(0.5106, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2586, device='cuda:0'), 'train_loss_ce': tensor(0.4292, device='cuda:0'), 'train_loss_bbox': tensor(0.1760, device='cuda:0'), 'train_loss_giou': tensor(0.4746, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1532, device='cuda:0'), 'validation_loss_ce': tensor(0.3864, device='cuda:0'), 'validation_loss_bbox': tensor(0.1486, device='cuda:0'), 'validation_loss_giou': tensor(0.5119, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0014, device='cuda:0'), 'train_loss_ce': tensor(0.3572, device='cuda:0'), 'train_loss_bbox': tensor(0.1214, device='cuda:0'), 'train_loss_giou': tensor(0.5187, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2039, device='cuda:0'), 'validation_loss_ce': tensor(0.3885, device='cuda:0'), 'validation_loss_bbox': tensor(0.1511, device='cuda:0'), 'validation_loss_giou': tensor(0.5298, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3735, device='cuda:0'), 'train_loss_ce': tensor(0.2071, device='cuda:0'), 'train_loss_bbox': tensor(0.1674, device='cuda:0'), 'train_loss_giou': tensor(0.6646, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2320, device='cuda:0'), 'validation_loss_ce': tensor(0.3813, device='cuda:0'), 'validation_loss_bbox': tensor(0.1592, device='cuda:0'), 'validation_loss_giou': tensor(0.5275, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3102, device='cuda:0'), 'train_loss_ce': tensor(0.3596, device='cuda:0'), 'train_loss_bbox': tensor(0.2168, device='cuda:0'), 'train_loss_giou': tensor(0.4333, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1842, device='cuda:0'), 'validation_loss_ce': tensor(0.3829, device='cuda:0'), 'validation_loss_bbox': tensor(0.1542, device='cuda:0'), 'validation_loss_giou': tensor(0.5153, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0276, device='cuda:0'), 'train_loss_ce': tensor(0.3274, device='cuda:0'), 'train_loss_bbox': tensor(0.1404, device='cuda:0'), 'train_loss_giou': tensor(0.4991, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1944, device='cuda:0'), 'validation_loss_ce': tensor(0.3800, device='cuda:0'), 'validation_loss_bbox': tensor(0.1547, device='cuda:0'), 'validation_loss_giou': tensor(0.5204, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1904, device='cuda:0'), 'train_loss_ce': tensor(0.3682, device='cuda:0'), 'train_loss_bbox': tensor(0.1408, device='cuda:0'), 'train_loss_giou': tensor(0.5591, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2061, device='cuda:0'), 'validation_loss_ce': tensor(0.3785, device='cuda:0'), 'validation_loss_bbox': tensor(0.1545, device='cuda:0'), 'validation_loss_giou': tensor(0.5276, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2407, device='cuda:0'), 'train_loss_ce': tensor(0.2918, device='cuda:0'), 'train_loss_bbox': tensor(0.1871, device='cuda:0'), 'train_loss_giou': tensor(0.5066, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1732, device='cuda:0'), 'validation_loss_ce': tensor(0.3773, device='cuda:0'), 'validation_loss_bbox': tensor(0.1579, device='cuda:0'), 'validation_loss_giou': tensor(0.5032, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.0560, device='cuda:0'), 'train_loss_ce': tensor(0.3344, device='cuda:0'), 'train_loss_bbox': tensor(0.1066, device='cuda:0'), 'train_loss_giou': tensor(0.5942, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(2.1830, device='cuda:0'), 'validation_loss_ce': tensor(0.3757, device='cuda:0'), 'validation_loss_bbox': tensor(0.1534, device='cuda:0'), 'validation_loss_giou': tensor(0.5201, device='cuda:0'), 'validation_cardinality_error': tensor(0.0303, device='cuda:0')}
{'training_loss': tensor(2.3304, device='cuda:0'), 'train_loss_ce': tensor(0.4064, device='cuda:0'), 'train_loss_bbox': tensor(0.1459, device='cuda:0'), 'train_loss_giou': tensor(0.5972, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2106, device='cuda:0'), 'validation_loss_ce': tensor(0.3762, device='cuda:0'), 'validation_loss_bbox': tensor(0.1587, device='cuda:0'), 'validation_loss_giou': tensor(0.5205, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
Downloads last month
2
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.