Hugging Face's logo

MedicalVision
/
detr_test_overfitting

Object Detection
Transformers
Safetensors
detr
Model card Files Community
detr_test_overfitting / README.md
npvinHnivqn's picture
npvinHnivqn
Update README file
cd44570 verified
preview code
|
raw
history blame
57.2 kB
metadata
library_name: transformers
tags: []

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

Config

  • dataset: NIH
  • original model: facebook/detr-resnet-50
  • lr: 0.0001
  • dropout_rate: 0.1
  • weight_decay: 0.0001
  • max_epochs: 100
  • train samples: 2

Logging

Training process 

{'validation_loss': tensor(5.6017, device='cuda:0'), 'validation_loss_ce': tensor(2.0849, device='cuda:0'), 'validation_loss_bbox': tensor(0.4302, device='cuda:0'), 'validation_loss_giou': tensor(0.6829, device='cuda:0'), 'validation_cardinality_error': tensor(87., device='cuda:0')}
{'training_loss': tensor(5.6017, device='cuda:0'), 'train_loss_ce': tensor(2.0849, device='cuda:0'), 'train_loss_bbox': tensor(0.4302, device='cuda:0'), 'train_loss_giou': tensor(0.6829, device='cuda:0'), 'train_cardinality_error': tensor(87., device='cuda:0'), 'validation_loss': tensor(6.3627, device='cuda:0'), 'validation_loss_ce': tensor(1.8613, device='cuda:0'), 'validation_loss_bbox': tensor(0.5789, device='cuda:0'), 'validation_loss_giou': tensor(0.8034, device='cuda:0'), 'validation_cardinality_error': tensor(43.5000, device='cuda:0')}
{'training_loss': tensor(6.3627, device='cuda:0'), 'train_loss_ce': tensor(1.8613, device='cuda:0'), 'train_loss_bbox': tensor(0.5789, device='cuda:0'), 'train_loss_giou': tensor(0.8034, device='cuda:0'), 'train_cardinality_error': tensor(43.5000, device='cuda:0'), 'validation_loss': tensor(7.0474, device='cuda:0'), 'validation_loss_ce': tensor(1.9586, device='cuda:0'), 'validation_loss_bbox': tensor(0.6317, device='cuda:0'), 'validation_loss_giou': tensor(0.9652, device='cuda:0'), 'validation_cardinality_error': tensor(73.5000, device='cuda:0')}
{'training_loss': tensor(7.0474, device='cuda:0'), 'train_loss_ce': tensor(1.9586, device='cuda:0'), 'train_loss_bbox': tensor(0.6317, device='cuda:0'), 'train_loss_giou': tensor(0.9652, device='cuda:0'), 'train_cardinality_error': tensor(73.5000, device='cuda:0'), 'validation_loss': tensor(6.2814, device='cuda:0'), 'validation_loss_ce': tensor(1.8006, device='cuda:0'), 'validation_loss_bbox': tensor(0.5896, device='cuda:0'), 'validation_loss_giou': tensor(0.7664, device='cuda:0'), 'validation_cardinality_error': tensor(25.5000, device='cuda:0')}
{'training_loss': tensor(6.2814, device='cuda:0'), 'train_loss_ce': tensor(1.8006, device='cuda:0'), 'train_loss_bbox': tensor(0.5896, device='cuda:0'), 'train_loss_giou': tensor(0.7664, device='cuda:0'), 'train_cardinality_error': tensor(25.5000, device='cuda:0'), 'validation_loss': tensor(5.7531, device='cuda:0'), 'validation_loss_ce': tensor(1.7510, device='cuda:0'), 'validation_loss_bbox': tensor(0.5194, device='cuda:0'), 'validation_loss_giou': tensor(0.7026, device='cuda:0'), 'validation_cardinality_error': tensor(5., device='cuda:0')}
{'training_loss': tensor(5.7531, device='cuda:0'), 'train_loss_ce': tensor(1.7510, device='cuda:0'), 'train_loss_bbox': tensor(0.5194, device='cuda:0'), 'train_loss_giou': tensor(0.7026, device='cuda:0'), 'train_cardinality_error': tensor(5., device='cuda:0'), 'validation_loss': tensor(5.7845, device='cuda:0'), 'validation_loss_ce': tensor(1.7435, device='cuda:0'), 'validation_loss_bbox': tensor(0.5269, device='cuda:0'), 'validation_loss_giou': tensor(0.7032, device='cuda:0'), 'validation_cardinality_error': tensor(5.5000, device='cuda:0')}
{'training_loss': tensor(5.7845, device='cuda:0'), 'train_loss_ce': tensor(1.7435, device='cuda:0'), 'train_loss_bbox': tensor(0.5269, device='cuda:0'), 'train_loss_giou': tensor(0.7032, device='cuda:0'), 'train_cardinality_error': tensor(5.5000, device='cuda:0'), 'validation_loss': tensor(5.2789, device='cuda:0'), 'validation_loss_ce': tensor(1.6650, device='cuda:0'), 'validation_loss_bbox': tensor(0.4057, device='cuda:0'), 'validation_loss_giou': tensor(0.7927, device='cuda:0'), 'validation_cardinality_error': tensor(2.5000, device='cuda:0')}
{'training_loss': tensor(5.2789, device='cuda:0'), 'train_loss_ce': tensor(1.6650, device='cuda:0'), 'train_loss_bbox': tensor(0.4057, device='cuda:0'), 'train_loss_giou': tensor(0.7927, device='cuda:0'), 'train_cardinality_error': tensor(2.5000, device='cuda:0'), 'validation_loss': tensor(4.2995, device='cuda:0'), 'validation_loss_ce': tensor(1.6013, device='cuda:0'), 'validation_loss_bbox': tensor(0.3041, device='cuda:0'), 'validation_loss_giou': tensor(0.5890, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(4.2995, device='cuda:0'), 'train_loss_ce': tensor(1.6013, device='cuda:0'), 'train_loss_bbox': tensor(0.3041, device='cuda:0'), 'train_loss_giou': tensor(0.5890, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(4.6465, device='cuda:0'), 'validation_loss_ce': tensor(1.5378, device='cuda:0'), 'validation_loss_bbox': tensor(0.3922, device='cuda:0'), 'validation_loss_giou': tensor(0.5738, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(4.6465, device='cuda:0'), 'train_loss_ce': tensor(1.5378, device='cuda:0'), 'train_loss_bbox': tensor(0.3922, device='cuda:0'), 'train_loss_giou': tensor(0.5738, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(4.6222, device='cuda:0'), 'validation_loss_ce': tensor(1.5296, device='cuda:0'), 'validation_loss_bbox': tensor(0.3489, device='cuda:0'), 'validation_loss_giou': tensor(0.6740, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(4.6222, device='cuda:0'), 'train_loss_ce': tensor(1.5296, device='cuda:0'), 'train_loss_bbox': tensor(0.3489, device='cuda:0'), 'train_loss_giou': tensor(0.6740, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(4.0194, device='cuda:0'), 'validation_loss_ce': tensor(1.5352, device='cuda:0'), 'validation_loss_bbox': tensor(0.2939, device='cuda:0'), 'validation_loss_giou': tensor(0.5074, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(4.0194, device='cuda:0'), 'train_loss_ce': tensor(1.5352, device='cuda:0'), 'train_loss_bbox': tensor(0.2939, device='cuda:0'), 'train_loss_giou': tensor(0.5074, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.5375, device='cuda:0'), 'validation_loss_ce': tensor(1.4859, device='cuda:0'), 'validation_loss_bbox': tensor(0.2289, device='cuda:0'), 'validation_loss_giou': tensor(0.4536, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.5375, device='cuda:0'), 'train_loss_ce': tensor(1.4859, device='cuda:0'), 'train_loss_bbox': tensor(0.2289, device='cuda:0'), 'train_loss_giou': tensor(0.4536, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(3.1891, device='cuda:0'), 'validation_loss_ce': tensor(1.3903, device='cuda:0'), 'validation_loss_bbox': tensor(0.1878, device='cuda:0'), 'validation_loss_giou': tensor(0.4300, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(3.1891, device='cuda:0'), 'train_loss_ce': tensor(1.3903, device='cuda:0'), 'train_loss_bbox': tensor(0.1878, device='cuda:0'), 'train_loss_giou': tensor(0.4300, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7035, device='cuda:0'), 'validation_loss_ce': tensor(1.3643, device='cuda:0'), 'validation_loss_bbox': tensor(0.1410, device='cuda:0'), 'validation_loss_giou': tensor(0.3170, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.7035, device='cuda:0'), 'train_loss_ce': tensor(1.3643, device='cuda:0'), 'train_loss_bbox': tensor(0.1410, device='cuda:0'), 'train_loss_giou': tensor(0.3170, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3029, device='cuda:0'), 'validation_loss_ce': tensor(1.3261, device='cuda:0'), 'validation_loss_bbox': tensor(0.0884, device='cuda:0'), 'validation_loss_giou': tensor(0.2675, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3029, device='cuda:0'), 'train_loss_ce': tensor(1.3261, device='cuda:0'), 'train_loss_bbox': tensor(0.0884, device='cuda:0'), 'train_loss_giou': tensor(0.2675, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7946, device='cuda:0'), 'validation_loss_ce': tensor(1.3143, device='cuda:0'), 'validation_loss_bbox': tensor(0.1497, device='cuda:0'), 'validation_loss_giou': tensor(0.3658, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.7946, device='cuda:0'), 'train_loss_ce': tensor(1.3143, device='cuda:0'), 'train_loss_bbox': tensor(0.1497, device='cuda:0'), 'train_loss_giou': tensor(0.3658, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5422, device='cuda:0'), 'validation_loss_ce': tensor(1.2696, device='cuda:0'), 'validation_loss_bbox': tensor(0.1339, device='cuda:0'), 'validation_loss_giou': tensor(0.3015, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5422, device='cuda:0'), 'train_loss_ce': tensor(1.2696, device='cuda:0'), 'train_loss_bbox': tensor(0.1339, device='cuda:0'), 'train_loss_giou': tensor(0.3015, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6529, device='cuda:0'), 'validation_loss_ce': tensor(1.2525, device='cuda:0'), 'validation_loss_bbox': tensor(0.1608, device='cuda:0'), 'validation_loss_giou': tensor(0.2982, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.6529, device='cuda:0'), 'train_loss_ce': tensor(1.2525, device='cuda:0'), 'train_loss_bbox': tensor(0.1608, device='cuda:0'), 'train_loss_giou': tensor(0.2982, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1509, device='cuda:0'), 'validation_loss_ce': tensor(1.1918, device='cuda:0'), 'validation_loss_bbox': tensor(0.0941, device='cuda:0'), 'validation_loss_giou': tensor(0.2443, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.1509, device='cuda:0'), 'train_loss_ce': tensor(1.1918, device='cuda:0'), 'train_loss_bbox': tensor(0.0941, device='cuda:0'), 'train_loss_giou': tensor(0.2443, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.6681, device='cuda:0'), 'validation_loss_ce': tensor(1.0913, device='cuda:0'), 'validation_loss_bbox': tensor(0.0635, device='cuda:0'), 'validation_loss_giou': tensor(0.1297, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6681, device='cuda:0'), 'train_loss_ce': tensor(1.0913, device='cuda:0'), 'train_loss_bbox': tensor(0.0635, device='cuda:0'), 'train_loss_giou': tensor(0.1297, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8172, device='cuda:0'), 'validation_loss_ce': tensor(1.0121, device='cuda:0'), 'validation_loss_bbox': tensor(0.0878, device='cuda:0'), 'validation_loss_giou': tensor(0.1830, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8172, device='cuda:0'), 'train_loss_ce': tensor(1.0121, device='cuda:0'), 'train_loss_bbox': tensor(0.0878, device='cuda:0'), 'train_loss_giou': tensor(0.1830, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7235, device='cuda:0'), 'validation_loss_ce': tensor(0.9522, device='cuda:0'), 'validation_loss_bbox': tensor(0.0711, device='cuda:0'), 'validation_loss_giou': tensor(0.2078, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7235, device='cuda:0'), 'train_loss_ce': tensor(0.9522, device='cuda:0'), 'train_loss_bbox': tensor(0.0711, device='cuda:0'), 'train_loss_giou': tensor(0.2078, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.5285, device='cuda:0'), 'validation_loss_ce': tensor(0.9022, device='cuda:0'), 'validation_loss_bbox': tensor(0.0596, device='cuda:0'), 'validation_loss_giou': tensor(0.1642, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5285, device='cuda:0'), 'train_loss_ce': tensor(0.9022, device='cuda:0'), 'train_loss_bbox': tensor(0.0596, device='cuda:0'), 'train_loss_giou': tensor(0.1642, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.2834, device='cuda:0'), 'validation_loss_ce': tensor(0.8606, device='cuda:0'), 'validation_loss_bbox': tensor(0.0364, device='cuda:0'), 'validation_loss_giou': tensor(0.1205, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2834, device='cuda:0'), 'train_loss_ce': tensor(0.8606, device='cuda:0'), 'train_loss_bbox': tensor(0.0364, device='cuda:0'), 'train_loss_giou': tensor(0.1205, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.3022, device='cuda:0'), 'validation_loss_ce': tensor(0.8215, device='cuda:0'), 'validation_loss_bbox': tensor(0.0422, device='cuda:0'), 'validation_loss_giou': tensor(0.1348, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3022, device='cuda:0'), 'train_loss_ce': tensor(0.8215, device='cuda:0'), 'train_loss_bbox': tensor(0.0422, device='cuda:0'), 'train_loss_giou': tensor(0.1348, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0249, device='cuda:0'), 'validation_loss_ce': tensor(0.7992, device='cuda:0'), 'validation_loss_bbox': tensor(0.0205, device='cuda:0'), 'validation_loss_giou': tensor(0.0614, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0249, device='cuda:0'), 'train_loss_ce': tensor(0.7992, device='cuda:0'), 'train_loss_bbox': tensor(0.0205, device='cuda:0'), 'train_loss_giou': tensor(0.0614, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0823, device='cuda:0'), 'validation_loss_ce': tensor(0.7821, device='cuda:0'), 'validation_loss_bbox': tensor(0.0313, device='cuda:0'), 'validation_loss_giou': tensor(0.0718, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0823, device='cuda:0'), 'train_loss_ce': tensor(0.7821, device='cuda:0'), 'train_loss_bbox': tensor(0.0313, device='cuda:0'), 'train_loss_giou': tensor(0.0718, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9961, device='cuda:0'), 'validation_loss_ce': tensor(0.7615, device='cuda:0'), 'validation_loss_bbox': tensor(0.0242, device='cuda:0'), 'validation_loss_giou': tensor(0.0567, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9961, device='cuda:0'), 'train_loss_ce': tensor(0.7615, device='cuda:0'), 'train_loss_bbox': tensor(0.0242, device='cuda:0'), 'train_loss_giou': tensor(0.0567, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9793, device='cuda:0'), 'validation_loss_ce': tensor(0.7294, device='cuda:0'), 'validation_loss_bbox': tensor(0.0255, device='cuda:0'), 'validation_loss_giou': tensor(0.0611, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9793, device='cuda:0'), 'train_loss_ce': tensor(0.7294, device='cuda:0'), 'train_loss_bbox': tensor(0.0255, device='cuda:0'), 'train_loss_giou': tensor(0.0611, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9178, device='cuda:0'), 'validation_loss_ce': tensor(0.7077, device='cuda:0'), 'validation_loss_bbox': tensor(0.0225, device='cuda:0'), 'validation_loss_giou': tensor(0.0488, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9178, device='cuda:0'), 'train_loss_ce': tensor(0.7077, device='cuda:0'), 'train_loss_bbox': tensor(0.0225, device='cuda:0'), 'train_loss_giou': tensor(0.0488, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8359, device='cuda:0'), 'validation_loss_ce': tensor(0.6958, device='cuda:0'), 'validation_loss_bbox': tensor(0.0142, device='cuda:0'), 'validation_loss_giou': tensor(0.0345, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8359, device='cuda:0'), 'train_loss_ce': tensor(0.6958, device='cuda:0'), 'train_loss_bbox': tensor(0.0142, device='cuda:0'), 'train_loss_giou': tensor(0.0345, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8585, device='cuda:0'), 'validation_loss_ce': tensor(0.6812, device='cuda:0'), 'validation_loss_bbox': tensor(0.0170, device='cuda:0'), 'validation_loss_giou': tensor(0.0462, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8585, device='cuda:0'), 'train_loss_ce': tensor(0.6812, device='cuda:0'), 'train_loss_bbox': tensor(0.0170, device='cuda:0'), 'train_loss_giou': tensor(0.0462, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7617, device='cuda:0'), 'validation_loss_ce': tensor(0.6592, device='cuda:0'), 'validation_loss_bbox': tensor(0.0102, device='cuda:0'), 'validation_loss_giou': tensor(0.0257, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7617, device='cuda:0'), 'train_loss_ce': tensor(0.6592, device='cuda:0'), 'train_loss_bbox': tensor(0.0102, device='cuda:0'), 'train_loss_giou': tensor(0.0257, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8044, device='cuda:0'), 'validation_loss_ce': tensor(0.6329, device='cuda:0'), 'validation_loss_bbox': tensor(0.0130, device='cuda:0'), 'validation_loss_giou': tensor(0.0533, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8044, device='cuda:0'), 'train_loss_ce': tensor(0.6329, device='cuda:0'), 'train_loss_bbox': tensor(0.0130, device='cuda:0'), 'train_loss_giou': tensor(0.0533, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8279, device='cuda:0'), 'validation_loss_ce': tensor(0.6079, device='cuda:0'), 'validation_loss_bbox': tensor(0.0221, device='cuda:0'), 'validation_loss_giou': tensor(0.0547, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8279, device='cuda:0'), 'train_loss_ce': tensor(0.6079, device='cuda:0'), 'train_loss_bbox': tensor(0.0221, device='cuda:0'), 'train_loss_giou': tensor(0.0547, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8013, device='cuda:0'), 'validation_loss_ce': tensor(0.5928, device='cuda:0'), 'validation_loss_bbox': tensor(0.0228, device='cuda:0'), 'validation_loss_giou': tensor(0.0472, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8013, device='cuda:0'), 'train_loss_ce': tensor(0.5928, device='cuda:0'), 'train_loss_bbox': tensor(0.0228, device='cuda:0'), 'train_loss_giou': tensor(0.0472, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7321, device='cuda:0'), 'validation_loss_ce': tensor(0.5778, device='cuda:0'), 'validation_loss_bbox': tensor(0.0156, device='cuda:0'), 'validation_loss_giou': tensor(0.0382, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7321, device='cuda:0'), 'train_loss_ce': tensor(0.5778, device='cuda:0'), 'train_loss_bbox': tensor(0.0156, device='cuda:0'), 'train_loss_giou': tensor(0.0382, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6580, device='cuda:0'), 'validation_loss_ce': tensor(0.5646, device='cuda:0'), 'validation_loss_bbox': tensor(0.0091, device='cuda:0'), 'validation_loss_giou': tensor(0.0239, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6580, device='cuda:0'), 'train_loss_ce': tensor(0.5646, device='cuda:0'), 'train_loss_bbox': tensor(0.0091, device='cuda:0'), 'train_loss_giou': tensor(0.0239, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6818, device='cuda:0'), 'validation_loss_ce': tensor(0.5514, device='cuda:0'), 'validation_loss_bbox': tensor(0.0147, device='cuda:0'), 'validation_loss_giou': tensor(0.0285, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6818, device='cuda:0'), 'train_loss_ce': tensor(0.5514, device='cuda:0'), 'train_loss_bbox': tensor(0.0147, device='cuda:0'), 'train_loss_giou': tensor(0.0285, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6764, device='cuda:0'), 'validation_loss_ce': tensor(0.5379, device='cuda:0'), 'validation_loss_bbox': tensor(0.0143, device='cuda:0'), 'validation_loss_giou': tensor(0.0334, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6764, device='cuda:0'), 'train_loss_ce': tensor(0.5379, device='cuda:0'), 'train_loss_bbox': tensor(0.0143, device='cuda:0'), 'train_loss_giou': tensor(0.0334, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6775, device='cuda:0'), 'validation_loss_ce': tensor(0.5208, device='cuda:0'), 'validation_loss_bbox': tensor(0.0129, device='cuda:0'), 'validation_loss_giou': tensor(0.0462, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6775, device='cuda:0'), 'train_loss_ce': tensor(0.5208, device='cuda:0'), 'train_loss_bbox': tensor(0.0129, device='cuda:0'), 'train_loss_giou': tensor(0.0462, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6520, device='cuda:0'), 'validation_loss_ce': tensor(0.5099, device='cuda:0'), 'validation_loss_bbox': tensor(0.0125, device='cuda:0'), 'validation_loss_giou': tensor(0.0399, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6520, device='cuda:0'), 'train_loss_ce': tensor(0.5099, device='cuda:0'), 'train_loss_bbox': tensor(0.0125, device='cuda:0'), 'train_loss_giou': tensor(0.0399, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6051, device='cuda:0'), 'validation_loss_ce': tensor(0.5030, device='cuda:0'), 'validation_loss_bbox': tensor(0.0071, device='cuda:0'), 'validation_loss_giou': tensor(0.0334, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6051, device='cuda:0'), 'train_loss_ce': tensor(0.5030, device='cuda:0'), 'train_loss_bbox': tensor(0.0071, device='cuda:0'), 'train_loss_giou': tensor(0.0334, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6969, device='cuda:0'), 'validation_loss_ce': tensor(0.4982, device='cuda:0'), 'validation_loss_bbox': tensor(0.0175, device='cuda:0'), 'validation_loss_giou': tensor(0.0556, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6969, device='cuda:0'), 'train_loss_ce': tensor(0.4982, device='cuda:0'), 'train_loss_bbox': tensor(0.0175, device='cuda:0'), 'train_loss_giou': tensor(0.0556, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6910, device='cuda:0'), 'validation_loss_ce': tensor(0.4916, device='cuda:0'), 'validation_loss_bbox': tensor(0.0197, device='cuda:0'), 'validation_loss_giou': tensor(0.0506, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6910, device='cuda:0'), 'train_loss_ce': tensor(0.4916, device='cuda:0'), 'train_loss_bbox': tensor(0.0197, device='cuda:0'), 'train_loss_giou': tensor(0.0506, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7090, device='cuda:0'), 'validation_loss_ce': tensor(0.4834, device='cuda:0'), 'validation_loss_bbox': tensor(0.0232, device='cuda:0'), 'validation_loss_giou': tensor(0.0549, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7090, device='cuda:0'), 'train_loss_ce': tensor(0.4834, device='cuda:0'), 'train_loss_bbox': tensor(0.0232, device='cuda:0'), 'train_loss_giou': tensor(0.0549, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7374, device='cuda:0'), 'validation_loss_ce': tensor(0.4753, device='cuda:0'), 'validation_loss_bbox': tensor(0.0242, device='cuda:0'), 'validation_loss_giou': tensor(0.0707, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7374, device='cuda:0'), 'train_loss_ce': tensor(0.4753, device='cuda:0'), 'train_loss_bbox': tensor(0.0242, device='cuda:0'), 'train_loss_giou': tensor(0.0707, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6690, device='cuda:0'), 'validation_loss_ce': tensor(0.4680, device='cuda:0'), 'validation_loss_bbox': tensor(0.0166, device='cuda:0'), 'validation_loss_giou': tensor(0.0589, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6690, device='cuda:0'), 'train_loss_ce': tensor(0.4680, device='cuda:0'), 'train_loss_bbox': tensor(0.0166, device='cuda:0'), 'train_loss_giou': tensor(0.0589, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6594, device='cuda:0'), 'validation_loss_ce': tensor(0.4621, device='cuda:0'), 'validation_loss_bbox': tensor(0.0226, device='cuda:0'), 'validation_loss_giou': tensor(0.0421, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6594, device='cuda:0'), 'train_loss_ce': tensor(0.4621, device='cuda:0'), 'train_loss_bbox': tensor(0.0226, device='cuda:0'), 'train_loss_giou': tensor(0.0421, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7248, device='cuda:0'), 'validation_loss_ce': tensor(0.4574, device='cuda:0'), 'validation_loss_bbox': tensor(0.0245, device='cuda:0'), 'validation_loss_giou': tensor(0.0726, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7248, device='cuda:0'), 'train_loss_ce': tensor(0.4574, device='cuda:0'), 'train_loss_bbox': tensor(0.0245, device='cuda:0'), 'train_loss_giou': tensor(0.0726, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7158, device='cuda:0'), 'validation_loss_ce': tensor(0.4522, device='cuda:0'), 'validation_loss_bbox': tensor(0.0206, device='cuda:0'), 'validation_loss_giou': tensor(0.0804, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7158, device='cuda:0'), 'train_loss_ce': tensor(0.4522, device='cuda:0'), 'train_loss_bbox': tensor(0.0206, device='cuda:0'), 'train_loss_giou': tensor(0.0804, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6459, device='cuda:0'), 'validation_loss_ce': tensor(0.4469, device='cuda:0'), 'validation_loss_bbox': tensor(0.0133, device='cuda:0'), 'validation_loss_giou': tensor(0.0662, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6459, device='cuda:0'), 'train_loss_ce': tensor(0.4469, device='cuda:0'), 'train_loss_bbox': tensor(0.0133, device='cuda:0'), 'train_loss_giou': tensor(0.0662, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5799, device='cuda:0'), 'validation_loss_ce': tensor(0.4413, device='cuda:0'), 'validation_loss_bbox': tensor(0.0099, device='cuda:0'), 'validation_loss_giou': tensor(0.0447, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5799, device='cuda:0'), 'train_loss_ce': tensor(0.4413, device='cuda:0'), 'train_loss_bbox': tensor(0.0099, device='cuda:0'), 'train_loss_giou': tensor(0.0447, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5798, device='cuda:0'), 'validation_loss_ce': tensor(0.4356, device='cuda:0'), 'validation_loss_bbox': tensor(0.0144, device='cuda:0'), 'validation_loss_giou': tensor(0.0361, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5798, device='cuda:0'), 'train_loss_ce': tensor(0.4356, device='cuda:0'), 'train_loss_bbox': tensor(0.0144, device='cuda:0'), 'train_loss_giou': tensor(0.0361, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6000, device='cuda:0'), 'validation_loss_ce': tensor(0.4313, device='cuda:0'), 'validation_loss_bbox': tensor(0.0143, device='cuda:0'), 'validation_loss_giou': tensor(0.0487, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6000, device='cuda:0'), 'train_loss_ce': tensor(0.4313, device='cuda:0'), 'train_loss_bbox': tensor(0.0143, device='cuda:0'), 'train_loss_giou': tensor(0.0487, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5141, device='cuda:0'), 'validation_loss_ce': tensor(0.4280, device='cuda:0'), 'validation_loss_bbox': tensor(0.0066, device='cuda:0'), 'validation_loss_giou': tensor(0.0265, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5141, device='cuda:0'), 'train_loss_ce': tensor(0.4280, device='cuda:0'), 'train_loss_bbox': tensor(0.0066, device='cuda:0'), 'train_loss_giou': tensor(0.0265, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5365, device='cuda:0'), 'validation_loss_ce': tensor(0.4249, device='cuda:0'), 'validation_loss_bbox': tensor(0.0093, device='cuda:0'), 'validation_loss_giou': tensor(0.0325, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5365, device='cuda:0'), 'train_loss_ce': tensor(0.4249, device='cuda:0'), 'train_loss_bbox': tensor(0.0093, device='cuda:0'), 'train_loss_giou': tensor(0.0325, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5261, device='cuda:0'), 'validation_loss_ce': tensor(0.4211, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0339, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5261, device='cuda:0'), 'train_loss_ce': tensor(0.4211, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0339, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4900, device='cuda:0'), 'validation_loss_ce': tensor(0.4172, device='cuda:0'), 'validation_loss_bbox': tensor(0.0063, device='cuda:0'), 'validation_loss_giou': tensor(0.0206, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4900, device='cuda:0'), 'train_loss_ce': tensor(0.4172, device='cuda:0'), 'train_loss_bbox': tensor(0.0063, device='cuda:0'), 'train_loss_giou': tensor(0.0206, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4777, device='cuda:0'), 'validation_loss_ce': tensor(0.4140, device='cuda:0'), 'validation_loss_bbox': tensor(0.0062, device='cuda:0'), 'validation_loss_giou': tensor(0.0164, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4777, device='cuda:0'), 'train_loss_ce': tensor(0.4140, device='cuda:0'), 'train_loss_bbox': tensor(0.0062, device='cuda:0'), 'train_loss_giou': tensor(0.0164, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4761, device='cuda:0'), 'validation_loss_ce': tensor(0.4111, device='cuda:0'), 'validation_loss_bbox': tensor(0.0055, device='cuda:0'), 'validation_loss_giou': tensor(0.0188, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4761, device='cuda:0'), 'train_loss_ce': tensor(0.4111, device='cuda:0'), 'train_loss_bbox': tensor(0.0055, device='cuda:0'), 'train_loss_giou': tensor(0.0188, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4847, device='cuda:0'), 'validation_loss_ce': tensor(0.4080, device='cuda:0'), 'validation_loss_bbox': tensor(0.0061, device='cuda:0'), 'validation_loss_giou': tensor(0.0230, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4847, device='cuda:0'), 'train_loss_ce': tensor(0.4080, device='cuda:0'), 'train_loss_bbox': tensor(0.0061, device='cuda:0'), 'train_loss_giou': tensor(0.0230, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4779, device='cuda:0'), 'validation_loss_ce': tensor(0.4051, device='cuda:0'), 'validation_loss_bbox': tensor(0.0056, device='cuda:0'), 'validation_loss_giou': tensor(0.0224, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4779, device='cuda:0'), 'train_loss_ce': tensor(0.4051, device='cuda:0'), 'train_loss_bbox': tensor(0.0056, device='cuda:0'), 'train_loss_giou': tensor(0.0224, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4429, device='cuda:0'), 'validation_loss_ce': tensor(0.4020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0031, device='cuda:0'), 'validation_loss_giou': tensor(0.0126, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4429, device='cuda:0'), 'train_loss_ce': tensor(0.4020, device='cuda:0'), 'train_loss_bbox': tensor(0.0031, device='cuda:0'), 'train_loss_giou': tensor(0.0126, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4499, device='cuda:0'), 'validation_loss_ce': tensor(0.3991, device='cuda:0'), 'validation_loss_bbox': tensor(0.0042, device='cuda:0'), 'validation_loss_giou': tensor(0.0148, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4499, device='cuda:0'), 'train_loss_ce': tensor(0.3991, device='cuda:0'), 'train_loss_bbox': tensor(0.0042, device='cuda:0'), 'train_loss_giou': tensor(0.0148, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4548, device='cuda:0'), 'validation_loss_ce': tensor(0.3966, device='cuda:0'), 'validation_loss_bbox': tensor(0.0055, device='cuda:0'), 'validation_loss_giou': tensor(0.0153, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4548, device='cuda:0'), 'train_loss_ce': tensor(0.3966, device='cuda:0'), 'train_loss_bbox': tensor(0.0055, device='cuda:0'), 'train_loss_giou': tensor(0.0153, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4586, device='cuda:0'), 'validation_loss_ce': tensor(0.3941, device='cuda:0'), 'validation_loss_bbox': tensor(0.0055, device='cuda:0'), 'validation_loss_giou': tensor(0.0184, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4586, device='cuda:0'), 'train_loss_ce': tensor(0.3941, device='cuda:0'), 'train_loss_bbox': tensor(0.0055, device='cuda:0'), 'train_loss_giou': tensor(0.0184, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4583, device='cuda:0'), 'validation_loss_ce': tensor(0.3914, device='cuda:0'), 'validation_loss_bbox': tensor(0.0063, device='cuda:0'), 'validation_loss_giou': tensor(0.0178, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4583, device='cuda:0'), 'train_loss_ce': tensor(0.3914, device='cuda:0'), 'train_loss_bbox': tensor(0.0063, device='cuda:0'), 'train_loss_giou': tensor(0.0178, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4632, device='cuda:0'), 'validation_loss_ce': tensor(0.3887, device='cuda:0'), 'validation_loss_bbox': tensor(0.0076, device='cuda:0'), 'validation_loss_giou': tensor(0.0182, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4632, device='cuda:0'), 'train_loss_ce': tensor(0.3887, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0182, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4547, device='cuda:0'), 'validation_loss_ce': tensor(0.3862, device='cuda:0'), 'validation_loss_bbox': tensor(0.0067, device='cuda:0'), 'validation_loss_giou': tensor(0.0174, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4547, device='cuda:0'), 'train_loss_ce': tensor(0.3862, device='cuda:0'), 'train_loss_bbox': tensor(0.0067, device='cuda:0'), 'train_loss_giou': tensor(0.0174, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4658, device='cuda:0'), 'validation_loss_ce': tensor(0.3836, device='cuda:0'), 'validation_loss_bbox': tensor(0.0068, device='cuda:0'), 'validation_loss_giou': tensor(0.0241, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4658, device='cuda:0'), 'train_loss_ce': tensor(0.3836, device='cuda:0'), 'train_loss_bbox': tensor(0.0068, device='cuda:0'), 'train_loss_giou': tensor(0.0241, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4300, device='cuda:0'), 'validation_loss_ce': tensor(0.3811, device='cuda:0'), 'validation_loss_bbox': tensor(0.0034, device='cuda:0'), 'validation_loss_giou': tensor(0.0161, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4300, device='cuda:0'), 'train_loss_ce': tensor(0.3811, device='cuda:0'), 'train_loss_bbox': tensor(0.0034, device='cuda:0'), 'train_loss_giou': tensor(0.0161, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4717, device='cuda:0'), 'validation_loss_ce': tensor(0.3787, device='cuda:0'), 'validation_loss_bbox': tensor(0.0076, device='cuda:0'), 'validation_loss_giou': tensor(0.0275, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4717, device='cuda:0'), 'train_loss_ce': tensor(0.3787, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0275, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4389, device='cuda:0'), 'validation_loss_ce': tensor(0.3766, device='cuda:0'), 'validation_loss_bbox': tensor(0.0055, device='cuda:0'), 'validation_loss_giou': tensor(0.0173, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4389, device='cuda:0'), 'train_loss_ce': tensor(0.3766, device='cuda:0'), 'train_loss_bbox': tensor(0.0055, device='cuda:0'), 'train_loss_giou': tensor(0.0173, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4551, device='cuda:0'), 'validation_loss_ce': tensor(0.3746, device='cuda:0'), 'validation_loss_bbox': tensor(0.0055, device='cuda:0'), 'validation_loss_giou': tensor(0.0265, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4551, device='cuda:0'), 'train_loss_ce': tensor(0.3746, device='cuda:0'), 'train_loss_bbox': tensor(0.0055, device='cuda:0'), 'train_loss_giou': tensor(0.0265, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4469, device='cuda:0'), 'validation_loss_ce': tensor(0.3724, device='cuda:0'), 'validation_loss_bbox': tensor(0.0053, device='cuda:0'), 'validation_loss_giou': tensor(0.0241, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4469, device='cuda:0'), 'train_loss_ce': tensor(0.3724, device='cuda:0'), 'train_loss_bbox': tensor(0.0053, device='cuda:0'), 'train_loss_giou': tensor(0.0241, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4077, device='cuda:0'), 'validation_loss_ce': tensor(0.3700, device='cuda:0'), 'validation_loss_bbox': tensor(0.0032, device='cuda:0'), 'validation_loss_giou': tensor(0.0107, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4077, device='cuda:0'), 'train_loss_ce': tensor(0.3700, device='cuda:0'), 'train_loss_bbox': tensor(0.0032, device='cuda:0'), 'train_loss_giou': tensor(0.0107, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4331, device='cuda:0'), 'validation_loss_ce': tensor(0.3681, device='cuda:0'), 'validation_loss_bbox': tensor(0.0058, device='cuda:0'), 'validation_loss_giou': tensor(0.0181, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4331, device='cuda:0'), 'train_loss_ce': tensor(0.3681, device='cuda:0'), 'train_loss_bbox': tensor(0.0058, device='cuda:0'), 'train_loss_giou': tensor(0.0181, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4463, device='cuda:0'), 'validation_loss_ce': tensor(0.3662, device='cuda:0'), 'validation_loss_bbox': tensor(0.0077, device='cuda:0'), 'validation_loss_giou': tensor(0.0208, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4463, device='cuda:0'), 'train_loss_ce': tensor(0.3662, device='cuda:0'), 'train_loss_bbox': tensor(0.0077, device='cuda:0'), 'train_loss_giou': tensor(0.0208, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4259, device='cuda:0'), 'validation_loss_ce': tensor(0.3639, device='cuda:0'), 'validation_loss_bbox': tensor(0.0058, device='cuda:0'), 'validation_loss_giou': tensor(0.0165, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4259, device='cuda:0'), 'train_loss_ce': tensor(0.3639, device='cuda:0'), 'train_loss_bbox': tensor(0.0058, device='cuda:0'), 'train_loss_giou': tensor(0.0165, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4593, device='cuda:0'), 'validation_loss_ce': tensor(0.3618, device='cuda:0'), 'validation_loss_bbox': tensor(0.0071, device='cuda:0'), 'validation_loss_giou': tensor(0.0310, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4593, device='cuda:0'), 'train_loss_ce': tensor(0.3618, device='cuda:0'), 'train_loss_bbox': tensor(0.0071, device='cuda:0'), 'train_loss_giou': tensor(0.0310, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4432, device='cuda:0'), 'validation_loss_ce': tensor(0.3599, device='cuda:0'), 'validation_loss_bbox': tensor(0.0076, device='cuda:0'), 'validation_loss_giou': tensor(0.0227, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4432, device='cuda:0'), 'train_loss_ce': tensor(0.3599, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0227, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4709, device='cuda:0'), 'validation_loss_ce': tensor(0.3582, device='cuda:0'), 'validation_loss_bbox': tensor(0.0087, device='cuda:0'), 'validation_loss_giou': tensor(0.0345, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4709, device='cuda:0'), 'train_loss_ce': tensor(0.3582, device='cuda:0'), 'train_loss_bbox': tensor(0.0087, device='cuda:0'), 'train_loss_giou': tensor(0.0345, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5017, device='cuda:0'), 'validation_loss_ce': tensor(0.3562, device='cuda:0'), 'validation_loss_bbox': tensor(0.0117, device='cuda:0'), 'validation_loss_giou': tensor(0.0435, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5017, device='cuda:0'), 'train_loss_ce': tensor(0.3562, device='cuda:0'), 'train_loss_bbox': tensor(0.0117, device='cuda:0'), 'train_loss_giou': tensor(0.0435, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4748, device='cuda:0'), 'validation_loss_ce': tensor(0.3539, device='cuda:0'), 'validation_loss_bbox': tensor(0.0120, device='cuda:0'), 'validation_loss_giou': tensor(0.0304, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4748, device='cuda:0'), 'train_loss_ce': tensor(0.3539, device='cuda:0'), 'train_loss_bbox': tensor(0.0120, device='cuda:0'), 'train_loss_giou': tensor(0.0304, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4469, device='cuda:0'), 'validation_loss_ce': tensor(0.3517, device='cuda:0'), 'validation_loss_bbox': tensor(0.0061, device='cuda:0'), 'validation_loss_giou': tensor(0.0324, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4469, device='cuda:0'), 'train_loss_ce': tensor(0.3517, device='cuda:0'), 'train_loss_bbox': tensor(0.0061, device='cuda:0'), 'train_loss_giou': tensor(0.0324, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4906, device='cuda:0'), 'validation_loss_ce': tensor(0.3500, device='cuda:0'), 'validation_loss_bbox': tensor(0.0099, device='cuda:0'), 'validation_loss_giou': tensor(0.0456, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4906, device='cuda:0'), 'train_loss_ce': tensor(0.3500, device='cuda:0'), 'train_loss_bbox': tensor(0.0099, device='cuda:0'), 'train_loss_giou': tensor(0.0456, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4591, device='cuda:0'), 'validation_loss_ce': tensor(0.3482, device='cuda:0'), 'validation_loss_bbox': tensor(0.0088, device='cuda:0'), 'validation_loss_giou': tensor(0.0335, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4591, device='cuda:0'), 'train_loss_ce': tensor(0.3482, device='cuda:0'), 'train_loss_bbox': tensor(0.0088, device='cuda:0'), 'train_loss_giou': tensor(0.0335, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4272, device='cuda:0'), 'validation_loss_ce': tensor(0.3466, device='cuda:0'), 'validation_loss_bbox': tensor(0.0064, device='cuda:0'), 'validation_loss_giou': tensor(0.0242, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4272, device='cuda:0'), 'train_loss_ce': tensor(0.3466, device='cuda:0'), 'train_loss_bbox': tensor(0.0064, device='cuda:0'), 'train_loss_giou': tensor(0.0242, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4671, device='cuda:0'), 'validation_loss_ce': tensor(0.3447, device='cuda:0'), 'validation_loss_bbox': tensor(0.0106, device='cuda:0'), 'validation_loss_giou': tensor(0.0348, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4671, device='cuda:0'), 'train_loss_ce': tensor(0.3447, device='cuda:0'), 'train_loss_bbox': tensor(0.0106, device='cuda:0'), 'train_loss_giou': tensor(0.0348, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4188, device='cuda:0'), 'validation_loss_ce': tensor(0.3429, device='cuda:0'), 'validation_loss_bbox': tensor(0.0088, device='cuda:0'), 'validation_loss_giou': tensor(0.0160, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4188, device='cuda:0'), 'train_loss_ce': tensor(0.3429, device='cuda:0'), 'train_loss_bbox': tensor(0.0088, device='cuda:0'), 'train_loss_giou': tensor(0.0160, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4382, device='cuda:0'), 'validation_loss_ce': tensor(0.3411, device='cuda:0'), 'validation_loss_bbox': tensor(0.0072, device='cuda:0'), 'validation_loss_giou': tensor(0.0306, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4382, device='cuda:0'), 'train_loss_ce': tensor(0.3411, device='cuda:0'), 'train_loss_bbox': tensor(0.0072, device='cuda:0'), 'train_loss_giou': tensor(0.0306, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4394, device='cuda:0'), 'validation_loss_ce': tensor(0.3396, device='cuda:0'), 'validation_loss_bbox': tensor(0.0085, device='cuda:0'), 'validation_loss_giou': tensor(0.0286, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4394, device='cuda:0'), 'train_loss_ce': tensor(0.3396, device='cuda:0'), 'train_loss_bbox': tensor(0.0085, device='cuda:0'), 'train_loss_giou': tensor(0.0286, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4583, device='cuda:0'), 'validation_loss_ce': tensor(0.3380, device='cuda:0'), 'validation_loss_bbox': tensor(0.0111, device='cuda:0'), 'validation_loss_giou': tensor(0.0323, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4583, device='cuda:0'), 'train_loss_ce': tensor(0.3380, device='cuda:0'), 'train_loss_bbox': tensor(0.0111, device='cuda:0'), 'train_loss_giou': tensor(0.0323, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5158, device='cuda:0'), 'validation_loss_ce': tensor(0.3363, device='cuda:0'), 'validation_loss_bbox': tensor(0.0167, device='cuda:0'), 'validation_loss_giou': tensor(0.0480, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5158, device='cuda:0'), 'train_loss_ce': tensor(0.3363, device='cuda:0'), 'train_loss_bbox': tensor(0.0167, device='cuda:0'), 'train_loss_giou': tensor(0.0480, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4768, device='cuda:0'), 'validation_loss_ce': tensor(0.3341, device='cuda:0'), 'validation_loss_bbox': tensor(0.0148, device='cuda:0'), 'validation_loss_giou': tensor(0.0342, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4768, device='cuda:0'), 'train_loss_ce': tensor(0.3341, device='cuda:0'), 'train_loss_bbox': tensor(0.0148, device='cuda:0'), 'train_loss_giou': tensor(0.0342, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4106, device='cuda:0'), 'validation_loss_ce': tensor(0.3318, device='cuda:0'), 'validation_loss_bbox': tensor(0.0076, device='cuda:0'), 'validation_loss_giou': tensor(0.0206, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4106, device='cuda:0'), 'train_loss_ce': tensor(0.3318, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0206, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3909, device='cuda:0'), 'validation_loss_ce': tensor(0.3296, device='cuda:0'), 'validation_loss_bbox': tensor(0.0057, device='cuda:0'), 'validation_loss_giou': tensor(0.0164, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3909, device='cuda:0'), 'train_loss_ce': tensor(0.3296, device='cuda:0'), 'train_loss_bbox': tensor(0.0057, device='cuda:0'), 'train_loss_giou': tensor(0.0164, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4470, device='cuda:0'), 'validation_loss_ce': tensor(0.3276, device='cuda:0'), 'validation_loss_bbox': tensor(0.0112, device='cuda:0'), 'validation_loss_giou': tensor(0.0316, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4470, device='cuda:0'), 'train_loss_ce': tensor(0.3276, device='cuda:0'), 'train_loss_bbox': tensor(0.0112, device='cuda:0'), 'train_loss_giou': tensor(0.0316, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4419, device='cuda:0'), 'validation_loss_ce': tensor(0.3257, device='cuda:0'), 'validation_loss_bbox': tensor(0.0101, device='cuda:0'), 'validation_loss_giou': tensor(0.0328, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4419, device='cuda:0'), 'train_loss_ce': tensor(0.3257, device='cuda:0'), 'train_loss_bbox': tensor(0.0101, device='cuda:0'), 'train_loss_giou': tensor(0.0328, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4000, device='cuda:0'), 'validation_loss_ce': tensor(0.3241, device='cuda:0'), 'validation_loss_bbox': tensor(0.0051, device='cuda:0'), 'validation_loss_giou': tensor(0.0252, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}

Examples

{'size': tensor([800, 800]), 'image_id': tensor([282]), 'class_labels': tensor([6]), 'boxes': tensor([[0.5497, 0.6339, 0.5344, 0.4466]]), 'area': tensor([152728.5312]), 'iscrowd': tensor([0]), 'orig_size': tensor([1024, 1024])}

Example