Update README file

README.md

@@ -23,18 +23,18 @@ IoU metric: bbox
 ## After training result
 ```
 IoU metric: bbox
- Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.004
- Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.011
- Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.002
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.053
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.096
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.063
  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 ] = 0.004
- 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 ] = 0.092
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.107
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.053
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.100
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.179
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.211
  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 ] = 0.108
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.232
 ```
 
 ## Config
@@ -42,44 +42,44 @@ IoU metric: bbox
 - original model: hustvl/yolos-tiny
 - lr: 0.0001
 - dropout_rate: 0.1
-- weight_decay: 5.0
+- weight_decay: 0.05
 - max_epochs: 30
 - train samples: 885
 
 ## Logging
 ### Training process
 ```
-{'validation_loss': tensor(6.5564, device='cuda:0'), 'validation_loss_ce': tensor(2.0633, device='cuda:0'), 'validation_loss_bbox': tensor(0.5405, device='cuda:0'), 'validation_loss_giou': tensor(0.8954, device='cuda:0'), 'validation_cardinality_error': tensor(92.5312, device='cuda:0')}
-{'training_loss': tensor(3.7441, device='cuda:0'), 'train_loss_ce': tensor(0.4851, device='cuda:0'), 'train_loss_bbox': tensor(0.2741, device='cuda:0'), 'train_loss_giou': tensor(0.9444, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8539, device='cuda:0'), 'validation_loss_ce': tensor(0.4760, device='cuda:0'), 'validation_loss_bbox': tensor(0.2163, device='cuda:0'), 'validation_loss_giou': tensor(0.6482, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.7504, device='cuda:0'), 'train_loss_ce': tensor(0.5047, device='cuda:0'), 'train_loss_bbox': tensor(0.1953, device='cuda:0'), 'train_loss_giou': tensor(0.6345, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6948, device='cuda:0'), 'validation_loss_ce': tensor(0.4437, device='cuda:0'), 'validation_loss_bbox': tensor(0.2097, device='cuda:0'), 'validation_loss_giou': tensor(0.6013, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.0392, device='cuda:0'), 'train_loss_ce': tensor(0.4076, device='cuda:0'), 'train_loss_bbox': tensor(0.1439, device='cuda:0'), 'train_loss_giou': tensor(0.4562, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4453, device='cuda:0'), 'validation_loss_ce': tensor(0.4250, device='cuda:0'), 'validation_loss_bbox': tensor(0.1845, device='cuda:0'), 'validation_loss_giou': tensor(0.5490, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2227, device='cuda:0'), 'train_loss_ce': tensor(0.4271, device='cuda:0'), 'train_loss_bbox': tensor(0.1462, device='cuda:0'), 'train_loss_giou': tensor(0.5323, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4683, device='cuda:0'), 'validation_loss_ce': tensor(0.4277, device='cuda:0'), 'validation_loss_bbox': tensor(0.1854, device='cuda:0'), 'validation_loss_giou': tensor(0.5569, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.3469, device='cuda:0'), 'train_loss_ce': tensor(0.4323, device='cuda:0'), 'train_loss_bbox': tensor(0.1472, device='cuda:0'), 'train_loss_giou': tensor(0.5894, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4288, device='cuda:0'), 'validation_loss_ce': tensor(0.4206, device='cuda:0'), 'validation_loss_bbox': tensor(0.1770, device='cuda:0'), 'validation_loss_giou': tensor(0.5616, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.7726, device='cuda:0'), 'train_loss_ce': tensor(0.4058, device='cuda:0'), 'train_loss_bbox': tensor(0.2171, device='cuda:0'), 'train_loss_giou': tensor(0.6406, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4031, device='cuda:0'), 'validation_loss_ce': tensor(0.4243, device='cuda:0'), 'validation_loss_bbox': tensor(0.1760, device='cuda:0'), 'validation_loss_giou': tensor(0.5495, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4850, device='cuda:0'), 'train_loss_ce': tensor(0.4841, device='cuda:0'), 'train_loss_bbox': tensor(0.1897, device='cuda:0'), 'train_loss_giou': tensor(0.5262, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3094, device='cuda:0'), 'validation_loss_ce': tensor(0.4155, device='cuda:0'), 'validation_loss_bbox': tensor(0.1648, device='cuda:0'), 'validation_loss_giou': tensor(0.5348, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.7707, device='cuda:0'), 'train_loss_ce': tensor(0.4562, device='cuda:0'), 'train_loss_bbox': tensor(0.0906, device='cuda:0'), 'train_loss_giou': tensor(0.4307, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3606, device='cuda:0'), 'validation_loss_ce': tensor(0.4136, device='cuda:0'), 'validation_loss_bbox': tensor(0.1676, device='cuda:0'), 'validation_loss_giou': tensor(0.5546, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.8267, device='cuda:0'), 'train_loss_ce': tensor(0.4556, device='cuda:0'), 'train_loss_bbox': tensor(0.1383, device='cuda:0'), 'train_loss_giou': tensor(0.3398, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3544, device='cuda:0'), 'validation_loss_ce': tensor(0.4203, device='cuda:0'), 'validation_loss_bbox': tensor(0.1730, device='cuda:0'), 'validation_loss_giou': tensor(0.5346, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.6995, device='cuda:0'), 'train_loss_ce': tensor(0.4739, device='cuda:0'), 'train_loss_bbox': tensor(0.2123, device='cuda:0'), 'train_loss_giou': tensor(0.5820, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3790, device='cuda:0'), 'validation_loss_ce': tensor(0.4226, device='cuda:0'), 'validation_loss_bbox': tensor(0.1763, device='cuda:0'), 'validation_loss_giou': tensor(0.5375, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.9513, device='cuda:0'), 'train_loss_ce': tensor(0.4720, device='cuda:0'), 'train_loss_bbox': tensor(0.0936, device='cuda:0'), 'train_loss_giou': tensor(0.5057, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4871, device='cuda:0'), 'validation_loss_ce': tensor(0.3954, device='cuda:0'), 'validation_loss_bbox': tensor(0.1899, device='cuda:0'), 'validation_loss_giou': tensor(0.5711, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8887, device='cuda:0'), 'train_loss_ce': tensor(0.4222, device='cuda:0'), 'train_loss_bbox': tensor(0.1872, device='cuda:0'), 'train_loss_giou': tensor(0.7651, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3490, device='cuda:0'), 'validation_loss_ce': tensor(0.4116, device='cuda:0'), 'validation_loss_bbox': tensor(0.1671, device='cuda:0'), 'validation_loss_giou': tensor(0.5511, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.0653, device='cuda:0'), 'train_loss_ce': tensor(0.3967, device='cuda:0'), 'train_loss_bbox': tensor(0.2608, device='cuda:0'), 'train_loss_giou': tensor(0.6824, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3907, device='cuda:0'), 'validation_loss_ce': tensor(0.3930, device='cuda:0'), 'validation_loss_bbox': tensor(0.1780, device='cuda:0'), 'validation_loss_giou': tensor(0.5538, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.6032, device='cuda:0'), 'train_loss_ce': tensor(0.4456, device='cuda:0'), 'train_loss_bbox': tensor(0.1778, device='cuda:0'), 'train_loss_giou': tensor(0.6342, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5283, device='cuda:0'), 'validation_loss_ce': tensor(0.3733, device='cuda:0'), 'validation_loss_bbox': tensor(0.1893, device='cuda:0'), 'validation_loss_giou': tensor(0.6041, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2535, device='cuda:0'), 'train_loss_ce': tensor(0.4025, device='cuda:0'), 'train_loss_bbox': tensor(0.1915, device='cuda:0'), 'train_loss_giou': tensor(0.4469, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5700, device='cuda:0'), 'validation_loss_ce': tensor(0.3973, device='cuda:0'), 'validation_loss_bbox': tensor(0.2018, device='cuda:0'), 'validation_loss_giou': tensor(0.5819, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.3217, device='cuda:0'), 'train_loss_ce': tensor(0.3088, device='cuda:0'), 'train_loss_bbox': tensor(0.1950, device='cuda:0'), 'train_loss_giou': tensor(0.5188, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4046, device='cuda:0'), 'validation_loss_ce': tensor(0.3842, device='cuda:0'), 'validation_loss_bbox': tensor(0.1765, device='cuda:0'), 'validation_loss_giou': tensor(0.5688, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.0773, device='cuda:0'), 'train_loss_ce': tensor(0.3404, device='cuda:0'), 'train_loss_bbox': tensor(0.1290, device='cuda:0'), 'train_loss_giou': tensor(0.5459, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3971, device='cuda:0'), 'validation_loss_ce': tensor(0.3989, device='cuda:0'), 'validation_loss_bbox': tensor(0.1737, device='cuda:0'), 'validation_loss_giou': tensor(0.5648, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.3780, device='cuda:0'), 'train_loss_ce': tensor(0.4421, device='cuda:0'), 'train_loss_bbox': tensor(0.2007, device='cuda:0'), 'train_loss_giou': tensor(0.4663, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5065, device='cuda:0'), 'validation_loss_ce': tensor(0.3807, device='cuda:0'), 'validation_loss_bbox': tensor(0.1850, device='cuda:0'), 'validation_loss_giou': tensor(0.6004, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.9553, device='cuda:0'), 'train_loss_ce': tensor(0.2818, device='cuda:0'), 'train_loss_bbox': tensor(0.1281, device='cuda:0'), 'train_loss_giou': tensor(0.5166, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6497, device='cuda:0'), 'validation_loss_ce': tensor(0.4114, device='cuda:0'), 'validation_loss_bbox': tensor(0.2036, device='cuda:0'), 'validation_loss_giou': tensor(0.6101, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.0033, device='cuda:0'), 'train_loss_ce': tensor(0.4743, device='cuda:0'), 'train_loss_bbox': tensor(0.2637, device='cuda:0'), 'train_loss_giou': tensor(0.6052, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7365, device='cuda:0'), 'validation_loss_ce': tensor(0.3921, device='cuda:0'), 'validation_loss_bbox': tensor(0.2165, device='cuda:0'), 'validation_loss_giou': tensor(0.6309, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4115, device='cuda:0'), 'train_loss_ce': tensor(0.4218, device='cuda:0'), 'train_loss_bbox': tensor(0.1878, device='cuda:0'), 'train_loss_giou': tensor(0.5255, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7406, device='cuda:0'), 'validation_loss_ce': tensor(0.3620, device='cuda:0'), 'validation_loss_bbox': tensor(0.2215, device='cuda:0'), 'validation_loss_giou': tensor(0.6356, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.6330, device='cuda:0'), 'train_loss_ce': tensor(0.3572, device='cuda:0'), 'train_loss_bbox': tensor(0.2481, device='cuda:0'), 'train_loss_giou': tensor(0.5176, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5378, device='cuda:0'), 'validation_loss_ce': tensor(0.3836, device='cuda:0'), 'validation_loss_bbox': tensor(0.1972, device='cuda:0'), 'validation_loss_giou': tensor(0.5842, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4576, device='cuda:0'), 'train_loss_ce': tensor(0.3233, device='cuda:0'), 'train_loss_bbox': tensor(0.1875, device='cuda:0'), 'train_loss_giou': tensor(0.5983, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4691, device='cuda:0'), 'validation_loss_ce': tensor(0.3929, device='cuda:0'), 'validation_loss_bbox': tensor(0.1909, device='cuda:0'), 'validation_loss_giou': tensor(0.5609, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4825, device='cuda:0'), 'train_loss_ce': tensor(0.4494, device='cuda:0'), 'train_loss_bbox': tensor(0.1926, device='cuda:0'), 'train_loss_giou': tensor(0.5351, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6155, device='cuda:0'), 'validation_loss_ce': tensor(0.4034, device='cuda:0'), 'validation_loss_bbox': tensor(0.2007, device='cuda:0'), 'validation_loss_giou': tensor(0.6043, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.6028, device='cuda:0'), 'train_loss_ce': tensor(0.4207, device='cuda:0'), 'train_loss_bbox': tensor(0.1980, device='cuda:0'), 'train_loss_giou': tensor(0.5962, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6668, device='cuda:0'), 'validation_loss_ce': tensor(0.3779, device='cuda:0'), 'validation_loss_bbox': tensor(0.2057, device='cuda:0'), 'validation_loss_giou': tensor(0.6303, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.9037, device='cuda:0'), 'train_loss_ce': tensor(0.2973, device='cuda:0'), 'train_loss_bbox': tensor(0.1633, device='cuda:0'), 'train_loss_giou': tensor(0.3951, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5248, device='cuda:0'), 'validation_loss_ce': tensor(0.3994, device='cuda:0'), 'validation_loss_bbox': tensor(0.1943, device='cuda:0'), 'validation_loss_giou': tensor(0.5770, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.6755, device='cuda:0'), 'train_loss_ce': tensor(0.3837, device='cuda:0'), 'train_loss_bbox': tensor(0.2018, device='cuda:0'), 'train_loss_giou': tensor(0.6414, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7245, device='cuda:0'), 'validation_loss_ce': tensor(0.4018, device='cuda:0'), 'validation_loss_bbox': tensor(0.2082, device='cuda:0'), 'validation_loss_giou': tensor(0.6410, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8687, device='cuda:0'), 'train_loss_ce': tensor(0.4472, device='cuda:0'), 'train_loss_bbox': tensor(0.2041, device='cuda:0'), 'train_loss_giou': tensor(0.7005, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4158, device='cuda:0'), 'validation_loss_ce': tensor(0.4104, device='cuda:0'), 'validation_loss_bbox': tensor(0.1761, device='cuda:0'), 'validation_loss_giou': tensor(0.5626, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8324, device='cuda:0'), 'train_loss_ce': tensor(0.4533, device='cuda:0'), 'train_loss_bbox': tensor(0.1971, device='cuda:0'), 'train_loss_giou': tensor(0.6968, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3753, device='cuda:0'), 'validation_loss_ce': tensor(0.4029, device='cuda:0'), 'validation_loss_bbox': tensor(0.1723, device='cuda:0'), 'validation_loss_giou': tensor(0.5555, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8085, device='cuda:0'), 'train_loss_ce': tensor(0.3939, device='cuda:0'), 'train_loss_bbox': tensor(0.2750, device='cuda:0'), 'train_loss_giou': tensor(0.5198, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3772, device='cuda:0'), 'validation_loss_ce': tensor(0.4097, device='cuda:0'), 'validation_loss_bbox': tensor(0.1783, device='cuda:0'), 'validation_loss_giou': tensor(0.5380, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'validation_loss': tensor(6.9559, device='cuda:0'), 'validation_loss_ce': tensor(2.4853, device='cuda:0'), 'validation_loss_bbox': tensor(0.5189, device='cuda:0'), 'validation_loss_giou': tensor(0.9380, device='cuda:0'), 'validation_cardinality_error': tensor(99., device='cuda:0')}
+{'training_loss': tensor(2.5294, device='cuda:0'), 'train_loss_ce': tensor(0.5418, device='cuda:0'), 'train_loss_bbox': tensor(0.1860, device='cuda:0'), 'train_loss_giou': tensor(0.5287, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5128, device='cuda:0'), 'validation_loss_ce': tensor(0.4620, device='cuda:0'), 'validation_loss_bbox': tensor(0.1888, device='cuda:0'), 'validation_loss_giou': tensor(0.5533, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2589, device='cuda:0'), 'train_loss_ce': tensor(0.4520, device='cuda:0'), 'train_loss_bbox': tensor(0.1275, device='cuda:0'), 'train_loss_giou': tensor(0.5847, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1865, device='cuda:0'), 'validation_loss_ce': tensor(0.4225, device='cuda:0'), 'validation_loss_bbox': tensor(0.1510, device='cuda:0'), 'validation_loss_giou': tensor(0.5045, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2895, device='cuda:0'), 'train_loss_ce': tensor(0.5192, device='cuda:0'), 'train_loss_bbox': tensor(0.1477, device='cuda:0'), 'train_loss_giou': tensor(0.5158, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1751, device='cuda:0'), 'validation_loss_ce': tensor(0.4340, device='cuda:0'), 'validation_loss_bbox': tensor(0.1528, device='cuda:0'), 'validation_loss_giou': tensor(0.4887, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1921, device='cuda:0'), 'train_loss_ce': tensor(0.4626, device='cuda:0'), 'train_loss_bbox': tensor(0.1593, device='cuda:0'), 'train_loss_giou': tensor(0.4666, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3439, device='cuda:0'), 'validation_loss_ce': tensor(0.4168, device='cuda:0'), 'validation_loss_bbox': tensor(0.1764, device='cuda:0'), 'validation_loss_giou': tensor(0.5226, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.6664, device='cuda:0'), 'train_loss_ce': tensor(0.4768, device='cuda:0'), 'train_loss_bbox': tensor(0.0885, device='cuda:0'), 'train_loss_giou': tensor(0.3736, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1216, device='cuda:0'), 'validation_loss_ce': tensor(0.4001, device='cuda:0'), 'validation_loss_bbox': tensor(0.1456, device='cuda:0'), 'validation_loss_giou': tensor(0.4969, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.5535, device='cuda:0'), 'train_loss_ce': tensor(0.4144, device='cuda:0'), 'train_loss_bbox': tensor(0.1866, device='cuda:0'), 'train_loss_giou': tensor(0.6031, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3127, device='cuda:0'), 'validation_loss_ce': tensor(0.3946, device='cuda:0'), 'validation_loss_bbox': tensor(0.1638, device='cuda:0'), 'validation_loss_giou': tensor(0.5496, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1711, device='cuda:0'), 'train_loss_ce': tensor(0.4254, device='cuda:0'), 'train_loss_bbox': tensor(0.1532, device='cuda:0'), 'train_loss_giou': tensor(0.4897, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0774, device='cuda:0'), 'validation_loss_ce': tensor(0.4161, device='cuda:0'), 'validation_loss_bbox': tensor(0.1417, device='cuda:0'), 'validation_loss_giou': tensor(0.4764, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7319, device='cuda:0'), 'train_loss_ce': tensor(0.4199, device='cuda:0'), 'train_loss_bbox': tensor(0.0986, device='cuda:0'), 'train_loss_giou': tensor(0.4096, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0720, device='cuda:0'), 'validation_loss_ce': tensor(0.3979, device='cuda:0'), 'validation_loss_bbox': tensor(0.1357, device='cuda:0'), 'validation_loss_giou': tensor(0.4978, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.5806, device='cuda:0'), 'train_loss_ce': tensor(0.3604, device='cuda:0'), 'train_loss_bbox': tensor(0.1325, device='cuda:0'), 'train_loss_giou': tensor(0.2790, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9735, device='cuda:0'), 'validation_loss_ce': tensor(0.3799, device='cuda:0'), 'validation_loss_bbox': tensor(0.1335, device='cuda:0'), 'validation_loss_giou': tensor(0.4631, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0937, device='cuda:0'), 'train_loss_ce': tensor(0.4021, device='cuda:0'), 'train_loss_bbox': tensor(0.1257, device='cuda:0'), 'train_loss_giou': tensor(0.5315, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9569, device='cuda:0'), 'validation_loss_ce': tensor(0.3864, device='cuda:0'), 'validation_loss_bbox': tensor(0.1335, device='cuda:0'), 'validation_loss_giou': tensor(0.4515, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.1840, device='cuda:0'), 'train_loss_ce': tensor(0.3635, device='cuda:0'), 'train_loss_bbox': tensor(0.0550, device='cuda:0'), 'train_loss_giou': tensor(0.2729, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9329, device='cuda:0'), 'validation_loss_ce': tensor(0.3740, device='cuda:0'), 'validation_loss_bbox': tensor(0.1274, device='cuda:0'), 'validation_loss_giou': tensor(0.4610, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0942, device='cuda:0'), 'train_loss_ce': tensor(0.3967, device='cuda:0'), 'train_loss_bbox': tensor(0.1509, device='cuda:0'), 'train_loss_giou': tensor(0.4715, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9473, device='cuda:0'), 'validation_loss_ce': tensor(0.3690, device='cuda:0'), 'validation_loss_bbox': tensor(0.1283, device='cuda:0'), 'validation_loss_giou': tensor(0.4683, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.6510, device='cuda:0'), 'train_loss_ce': tensor(0.2956, device='cuda:0'), 'train_loss_bbox': tensor(0.0785, device='cuda:0'), 'train_loss_giou': tensor(0.4814, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8971, device='cuda:0'), 'validation_loss_ce': tensor(0.3623, device='cuda:0'), 'validation_loss_bbox': tensor(0.1229, device='cuda:0'), 'validation_loss_giou': tensor(0.4603, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.3376, device='cuda:0'), 'train_loss_ce': tensor(0.2663, device='cuda:0'), 'train_loss_bbox': tensor(0.0985, device='cuda:0'), 'train_loss_giou': tensor(0.2893, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8048, device='cuda:0'), 'validation_loss_ce': tensor(0.3550, device='cuda:0'), 'validation_loss_bbox': tensor(0.1180, device='cuda:0'), 'validation_loss_giou': tensor(0.4298, device='cuda:0'), 'validation_cardinality_error': tensor(0.9899, device='cuda:0')}
+{'training_loss': tensor(1.8508, device='cuda:0'), 'train_loss_ce': tensor(0.4634, device='cuda:0'), 'train_loss_bbox': tensor(0.1160, device='cuda:0'), 'train_loss_giou': tensor(0.4036, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8110, device='cuda:0'), 'validation_loss_ce': tensor(0.3658, device='cuda:0'), 'validation_loss_bbox': tensor(0.1133, device='cuda:0'), 'validation_loss_giou': tensor(0.4393, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2132, device='cuda:0'), 'train_loss_ce': tensor(0.3865, device='cuda:0'), 'train_loss_bbox': tensor(0.1733, device='cuda:0'), 'train_loss_giou': tensor(0.4802, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8956, device='cuda:0'), 'validation_loss_ce': tensor(0.3703, device='cuda:0'), 'validation_loss_bbox': tensor(0.1241, device='cuda:0'), 'validation_loss_giou': tensor(0.4525, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.4466, device='cuda:0'), 'train_loss_ce': tensor(0.4195, device='cuda:0'), 'train_loss_bbox': tensor(0.0736, device='cuda:0'), 'train_loss_giou': tensor(0.3295, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9727, device='cuda:0'), 'validation_loss_ce': tensor(0.3733, device='cuda:0'), 'validation_loss_bbox': tensor(0.1318, device='cuda:0'), 'validation_loss_giou': tensor(0.4702, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.6351, device='cuda:0'), 'train_loss_ce': tensor(0.3461, device='cuda:0'), 'train_loss_bbox': tensor(0.0929, device='cuda:0'), 'train_loss_giou': tensor(0.4122, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8800, device='cuda:0'), 'validation_loss_ce': tensor(0.3603, device='cuda:0'), 'validation_loss_bbox': tensor(0.1224, device='cuda:0'), 'validation_loss_giou': tensor(0.4539, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1954, device='cuda:0'), 'train_loss_ce': tensor(0.3990, device='cuda:0'), 'train_loss_bbox': tensor(0.1613, device='cuda:0'), 'train_loss_giou': tensor(0.4950, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8715, device='cuda:0'), 'validation_loss_ce': tensor(0.3536, device='cuda:0'), 'validation_loss_bbox': tensor(0.1234, device='cuda:0'), 'validation_loss_giou': tensor(0.4504, device='cuda:0'), 'validation_cardinality_error': tensor(0.9192, device='cuda:0')}
+{'training_loss': tensor(1.8643, device='cuda:0'), 'train_loss_ce': tensor(0.3877, device='cuda:0'), 'train_loss_bbox': tensor(0.0971, device='cuda:0'), 'train_loss_giou': tensor(0.4955, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7371, device='cuda:0'), 'validation_loss_ce': tensor(0.3362, device='cuda:0'), 'validation_loss_bbox': tensor(0.1148, device='cuda:0'), 'validation_loss_giou': tensor(0.4134, device='cuda:0'), 'validation_cardinality_error': tensor(0.9394, device='cuda:0')}
+{'training_loss': tensor(1.3830, device='cuda:0'), 'train_loss_ce': tensor(0.1839, device='cuda:0'), 'train_loss_bbox': tensor(0.0825, device='cuda:0'), 'train_loss_giou': tensor(0.3932, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8157, device='cuda:0'), 'validation_loss_ce': tensor(0.3523, device='cuda:0'), 'validation_loss_bbox': tensor(0.1163, device='cuda:0'), 'validation_loss_giou': tensor(0.4410, device='cuda:0'), 'validation_cardinality_error': tensor(0.9293, device='cuda:0')}
+{'training_loss': tensor(1.6100, device='cuda:0'), 'train_loss_ce': tensor(0.3392, device='cuda:0'), 'train_loss_bbox': tensor(0.1034, device='cuda:0'), 'train_loss_giou': tensor(0.3770, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7169, device='cuda:0'), 'validation_loss_ce': tensor(0.3482, device='cuda:0'), 'validation_loss_bbox': tensor(0.1110, device='cuda:0'), 'validation_loss_giou': tensor(0.4070, device='cuda:0'), 'validation_cardinality_error': tensor(0.9192, device='cuda:0')}
+{'training_loss': tensor(1.5429, device='cuda:0'), 'train_loss_ce': tensor(0.3210, device='cuda:0'), 'train_loss_bbox': tensor(0.0945, device='cuda:0'), 'train_loss_giou': tensor(0.3747, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7941, device='cuda:0'), 'validation_loss_ce': tensor(0.3513, device='cuda:0'), 'validation_loss_bbox': tensor(0.1161, device='cuda:0'), 'validation_loss_giou': tensor(0.4312, device='cuda:0'), 'validation_cardinality_error': tensor(0.8990, device='cuda:0')}
+{'training_loss': tensor(1.4975, device='cuda:0'), 'train_loss_ce': tensor(0.3537, device='cuda:0'), 'train_loss_bbox': tensor(0.0965, device='cuda:0'), 'train_loss_giou': tensor(0.3307, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7279, device='cuda:0'), 'validation_loss_ce': tensor(0.3444, device='cuda:0'), 'validation_loss_bbox': tensor(0.1122, device='cuda:0'), 'validation_loss_giou': tensor(0.4112, device='cuda:0'), 'validation_cardinality_error': tensor(0.8081, device='cuda:0')}
+{'training_loss': tensor(1.6512, device='cuda:0'), 'train_loss_ce': tensor(0.3698, device='cuda:0'), 'train_loss_bbox': tensor(0.1170, device='cuda:0'), 'train_loss_giou': tensor(0.3481, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8547, device='cuda:0'), 'validation_loss_ce': tensor(0.3486, device='cuda:0'), 'validation_loss_bbox': tensor(0.1224, device='cuda:0'), 'validation_loss_giou': tensor(0.4470, device='cuda:0'), 'validation_cardinality_error': tensor(0.7576, device='cuda:0')}
+{'training_loss': tensor(2.2053, device='cuda:0'), 'train_loss_ce': tensor(0.3561, device='cuda:0'), 'train_loss_bbox': tensor(0.1675, device='cuda:0'), 'train_loss_giou': tensor(0.5059, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8177, device='cuda:0'), 'validation_loss_ce': tensor(0.3480, device='cuda:0'), 'validation_loss_bbox': tensor(0.1206, device='cuda:0'), 'validation_loss_giou': tensor(0.4333, device='cuda:0'), 'validation_cardinality_error': tensor(0.7071, device='cuda:0')}
+{'training_loss': tensor(1.6742, device='cuda:0'), 'train_loss_ce': tensor(0.3054, device='cuda:0'), 'train_loss_bbox': tensor(0.1093, device='cuda:0'), 'train_loss_giou': tensor(0.4112, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7886, device='cuda:0'), 'validation_loss_ce': tensor(0.3294, device='cuda:0'), 'validation_loss_bbox': tensor(0.1209, device='cuda:0'), 'validation_loss_giou': tensor(0.4274, device='cuda:0'), 'validation_cardinality_error': tensor(0.6364, device='cuda:0')}
+{'training_loss': tensor(0.8524, device='cuda:0'), 'train_loss_ce': tensor(0.1265, device='cuda:0'), 'train_loss_bbox': tensor(0.0692, device='cuda:0'), 'train_loss_giou': tensor(0.1898, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7781, device='cuda:0'), 'validation_loss_ce': tensor(0.3431, device='cuda:0'), 'validation_loss_bbox': tensor(0.1189, device='cuda:0'), 'validation_loss_giou': tensor(0.4203, device='cuda:0'), 'validation_cardinality_error': tensor(0.6869, device='cuda:0')}
+{'training_loss': tensor(1.4292, device='cuda:0'), 'train_loss_ce': tensor(0.3210, device='cuda:0'), 'train_loss_bbox': tensor(0.0939, device='cuda:0'), 'train_loss_giou': tensor(0.3193, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8680, device='cuda:0'), 'validation_loss_ce': tensor(0.3525, device='cuda:0'), 'validation_loss_bbox': tensor(0.1307, device='cuda:0'), 'validation_loss_giou': tensor(0.4311, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
+{'training_loss': tensor(1.2447, device='cuda:0'), 'train_loss_ce': tensor(0.2517, device='cuda:0'), 'train_loss_bbox': tensor(0.0609, device='cuda:0'), 'train_loss_giou': tensor(0.3442, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7613, device='cuda:0'), 'validation_loss_ce': tensor(0.3511, device='cuda:0'), 'validation_loss_bbox': tensor(0.1156, device='cuda:0'), 'validation_loss_giou': tensor(0.4160, device='cuda:0'), 'validation_cardinality_error': tensor(0.5455, device='cuda:0')}
 ```
 
 ## Examples