Update README file

README.md

@@ -13,28 +13,28 @@ IoU metric: bbox
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.011
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.011
+ 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 ] = 0.004
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.011
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.004
 ```
 
 ## After training result
 ```
 IoU metric: bbox
- Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.008
- Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.026
- Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.001
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.040
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.071
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.047
  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 ] = 0.008
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.040
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.049
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.056
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.044
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.131
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.198
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.227
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.056
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.018
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.247
 ```
 
 ## Config
@@ -42,44 +42,44 @@ IoU metric: bbox
 - original model: hustvl/yolos-tiny
 - lr: 0.0001
 - dropout_rate: 0.1
-- weight_decay: 10.0
+- weight_decay: 0.1
 - max_epochs: 30
 - train samples: 885
 
 ## Logging
 ### Training process
 ```
-{'validation_loss': tensor(6.4845, device='cuda:0'), 'validation_loss_ce': tensor(2.0703, device='cuda:0'), 'validation_loss_bbox': tensor(0.5406, device='cuda:0'), 'validation_loss_giou': tensor(0.8556, device='cuda:0'), 'validation_cardinality_error': tensor(79.9062, device='cuda:0')}
-{'training_loss': tensor(2.7016, device='cuda:0'), 'train_loss_ce': tensor(0.4314, device='cuda:0'), 'train_loss_bbox': tensor(0.2228, device='cuda:0'), 'train_loss_giou': tensor(0.5781, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3099, device='cuda:0'), 'validation_loss_ce': tensor(0.4543, device='cuda:0'), 'validation_loss_bbox': tensor(0.1610, device='cuda:0'), 'validation_loss_giou': tensor(0.5252, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2841, device='cuda:0'), 'train_loss_ce': tensor(0.4562, device='cuda:0'), 'train_loss_bbox': tensor(0.1660, device='cuda:0'), 'train_loss_giou': tensor(0.4990, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3262, device='cuda:0'), 'validation_loss_ce': tensor(0.4318, device='cuda:0'), 'validation_loss_bbox': tensor(0.1678, device='cuda:0'), 'validation_loss_giou': tensor(0.5276, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.0995, device='cuda:0'), 'train_loss_ce': tensor(0.4676, device='cuda:0'), 'train_loss_bbox': tensor(0.1685, device='cuda:0'), 'train_loss_giou': tensor(0.3948, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2856, device='cuda:0'), 'validation_loss_ce': tensor(0.4396, device='cuda:0'), 'validation_loss_bbox': tensor(0.1619, device='cuda:0'), 'validation_loss_giou': tensor(0.5182, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.8772, device='cuda:0'), 'train_loss_ce': tensor(0.4828, device='cuda:0'), 'train_loss_bbox': tensor(0.1217, device='cuda:0'), 'train_loss_giou': tensor(0.3929, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2444, device='cuda:0'), 'validation_loss_ce': tensor(0.4270, device='cuda:0'), 'validation_loss_bbox': tensor(0.1613, device='cuda:0'), 'validation_loss_giou': tensor(0.5056, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4697, device='cuda:0'), 'train_loss_ce': tensor(0.4485, device='cuda:0'), 'train_loss_bbox': tensor(0.1694, device='cuda:0'), 'train_loss_giou': tensor(0.5871, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3423, device='cuda:0'), 'validation_loss_ce': tensor(0.4061, device='cuda:0'), 'validation_loss_bbox': tensor(0.1712, device='cuda:0'), 'validation_loss_giou': tensor(0.5401, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.2742, device='cuda:0'), 'train_loss_ce': tensor(0.3894, device='cuda:0'), 'train_loss_bbox': tensor(0.2832, device='cuda:0'), 'train_loss_giou': tensor(0.7344, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8731, device='cuda:0'), 'validation_loss_ce': tensor(0.4232, device='cuda:0'), 'validation_loss_bbox': tensor(0.2260, device='cuda:0'), 'validation_loss_giou': tensor(0.6598, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.7366, device='cuda:0'), 'train_loss_ce': tensor(0.4021, device='cuda:0'), 'train_loss_bbox': tensor(0.1880, device='cuda:0'), 'train_loss_giou': tensor(0.6971, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7447, device='cuda:0'), 'validation_loss_ce': tensor(0.4046, device='cuda:0'), 'validation_loss_bbox': tensor(0.2111, device='cuda:0'), 'validation_loss_giou': tensor(0.6423, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.5912, device='cuda:0'), 'train_loss_ce': tensor(0.4474, device='cuda:0'), 'train_loss_bbox': tensor(0.2692, device='cuda:0'), 'train_loss_giou': tensor(0.8990, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7000, device='cuda:0'), 'validation_loss_ce': tensor(0.3900, device='cuda:0'), 'validation_loss_bbox': tensor(0.2162, device='cuda:0'), 'validation_loss_giou': tensor(0.6146, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.1424, device='cuda:0'), 'train_loss_ce': tensor(0.4654, device='cuda:0'), 'train_loss_bbox': tensor(0.2374, device='cuda:0'), 'train_loss_giou': tensor(0.7449, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6695, device='cuda:0'), 'validation_loss_ce': tensor(0.4214, device='cuda:0'), 'validation_loss_bbox': tensor(0.2038, device='cuda:0'), 'validation_loss_giou': tensor(0.6146, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.3901, device='cuda:0'), 'train_loss_ce': tensor(0.3745, device='cuda:0'), 'train_loss_bbox': tensor(0.3009, device='cuda:0'), 'train_loss_giou': tensor(0.7555, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8418, device='cuda:0'), 'validation_loss_ce': tensor(0.4005, device='cuda:0'), 'validation_loss_bbox': tensor(0.2356, device='cuda:0'), 'validation_loss_giou': tensor(0.6315, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.1228, device='cuda:0'), 'train_loss_ce': tensor(0.4134, device='cuda:0'), 'train_loss_bbox': tensor(0.1691, device='cuda:0'), 'train_loss_giou': tensor(0.4320, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8125, device='cuda:0'), 'validation_loss_ce': tensor(0.4067, device='cuda:0'), 'validation_loss_bbox': tensor(0.2164, device='cuda:0'), 'validation_loss_giou': tensor(0.6619, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8465, device='cuda:0'), 'train_loss_ce': tensor(0.4752, device='cuda:0'), 'train_loss_bbox': tensor(0.2065, device='cuda:0'), 'train_loss_giou': tensor(0.6694, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5769, device='cuda:0'), 'validation_loss_ce': tensor(0.4146, device='cuda:0'), 'validation_loss_bbox': tensor(0.1986, device='cuda:0'), 'validation_loss_giou': tensor(0.5845, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.0633, device='cuda:0'), 'train_loss_ce': tensor(0.4504, device='cuda:0'), 'train_loss_bbox': tensor(0.1999, device='cuda:0'), 'train_loss_giou': tensor(0.8068, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7978, device='cuda:0'), 'validation_loss_ce': tensor(0.4000, device='cuda:0'), 'validation_loss_bbox': tensor(0.2214, device='cuda:0'), 'validation_loss_giou': tensor(0.6452, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.3091, device='cuda:0'), 'train_loss_ce': tensor(0.4060, device='cuda:0'), 'train_loss_bbox': tensor(0.1832, device='cuda:0'), 'train_loss_giou': tensor(0.4936, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6313, device='cuda:0'), 'validation_loss_ce': tensor(0.4259, device='cuda:0'), 'validation_loss_bbox': tensor(0.2090, device='cuda:0'), 'validation_loss_giou': tensor(0.5803, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8676, device='cuda:0'), 'train_loss_ce': tensor(0.4144, device='cuda:0'), 'train_loss_bbox': tensor(0.2126, device='cuda:0'), 'train_loss_giou': tensor(0.6952, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6389, device='cuda:0'), 'validation_loss_ce': tensor(0.4249, device='cuda:0'), 'validation_loss_bbox': tensor(0.2028, device='cuda:0'), 'validation_loss_giou': tensor(0.6000, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8933, device='cuda:0'), 'train_loss_ce': tensor(0.4095, device='cuda:0'), 'train_loss_bbox': tensor(0.2215, device='cuda:0'), 'train_loss_giou': tensor(0.6881, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7148, device='cuda:0'), 'validation_loss_ce': tensor(0.4285, device='cuda:0'), 'validation_loss_bbox': tensor(0.2068, device='cuda:0'), 'validation_loss_giou': tensor(0.6262, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.8105, device='cuda:0'), 'train_loss_ce': tensor(0.4766, device='cuda:0'), 'train_loss_bbox': tensor(0.2018, device='cuda:0'), 'train_loss_giou': tensor(0.6625, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6955, device='cuda:0'), 'validation_loss_ce': tensor(0.4442, device='cuda:0'), 'validation_loss_bbox': tensor(0.2032, device='cuda:0'), 'validation_loss_giou': tensor(0.6176, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.9315, device='cuda:0'), 'train_loss_ce': tensor(0.5202, device='cuda:0'), 'train_loss_bbox': tensor(0.2002, device='cuda:0'), 'train_loss_giou': tensor(0.7052, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.9419, device='cuda:0'), 'validation_loss_ce': tensor(0.4325, device='cuda:0'), 'validation_loss_bbox': tensor(0.2266, device='cuda:0'), 'validation_loss_giou': tensor(0.6881, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4729, device='cuda:0'), 'train_loss_ce': tensor(0.4755, device='cuda:0'), 'train_loss_bbox': tensor(0.1909, device='cuda:0'), 'train_loss_giou': tensor(0.5214, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7052, device='cuda:0'), 'validation_loss_ce': tensor(0.4322, device='cuda:0'), 'validation_loss_bbox': tensor(0.2143, device='cuda:0'), 'validation_loss_giou': tensor(0.6007, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.7326, device='cuda:0'), 'train_loss_ce': tensor(0.3718, device='cuda:0'), 'train_loss_bbox': tensor(0.2027, device='cuda:0'), 'train_loss_giou': tensor(0.6737, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7806, device='cuda:0'), 'validation_loss_ce': tensor(0.4508, device='cuda:0'), 'validation_loss_bbox': tensor(0.2179, device='cuda:0'), 'validation_loss_giou': tensor(0.6201, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.5336, device='cuda:0'), 'train_loss_ce': tensor(0.4251, device='cuda:0'), 'train_loss_bbox': tensor(0.2083, device='cuda:0'), 'train_loss_giou': tensor(0.5336, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.9040, device='cuda:0'), 'validation_loss_ce': tensor(0.4602, device='cuda:0'), 'validation_loss_bbox': tensor(0.2258, device='cuda:0'), 'validation_loss_giou': tensor(0.6575, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.5256, device='cuda:0'), 'train_loss_ce': tensor(0.4589, device='cuda:0'), 'train_loss_bbox': tensor(0.2075, device='cuda:0'), 'train_loss_giou': tensor(0.5147, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6811, device='cuda:0'), 'validation_loss_ce': tensor(0.4428, device='cuda:0'), 'validation_loss_bbox': tensor(0.2018, device='cuda:0'), 'validation_loss_giou': tensor(0.6145, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.0975, device='cuda:0'), 'train_loss_ce': tensor(0.4765, device='cuda:0'), 'train_loss_bbox': tensor(0.1326, device='cuda:0'), 'train_loss_giou': tensor(0.4790, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7996, device='cuda:0'), 'validation_loss_ce': tensor(0.4371, device='cuda:0'), 'validation_loss_bbox': tensor(0.2147, device='cuda:0'), 'validation_loss_giou': tensor(0.6446, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4838, device='cuda:0'), 'train_loss_ce': tensor(0.4119, device='cuda:0'), 'train_loss_bbox': tensor(0.1899, device='cuda:0'), 'train_loss_giou': tensor(0.5612, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7380, device='cuda:0'), 'validation_loss_ce': tensor(0.4168, device='cuda:0'), 'validation_loss_bbox': tensor(0.2185, device='cuda:0'), 'validation_loss_giou': tensor(0.6143, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4045, device='cuda:0'), 'train_loss_ce': tensor(0.4238, device='cuda:0'), 'train_loss_bbox': tensor(0.1777, device='cuda:0'), 'train_loss_giou': tensor(0.5461, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7113, device='cuda:0'), 'validation_loss_ce': tensor(0.4276, device='cuda:0'), 'validation_loss_bbox': tensor(0.2102, device='cuda:0'), 'validation_loss_giou': tensor(0.6164, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.2236, device='cuda:0'), 'train_loss_ce': tensor(0.3068, device='cuda:0'), 'train_loss_bbox': tensor(0.2612, device='cuda:0'), 'train_loss_giou': tensor(0.8055, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7548, device='cuda:0'), 'validation_loss_ce': tensor(0.4379, device='cuda:0'), 'validation_loss_bbox': tensor(0.2177, device='cuda:0'), 'validation_loss_giou': tensor(0.6142, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.0097, device='cuda:0'), 'train_loss_ce': tensor(0.4255, device='cuda:0'), 'train_loss_bbox': tensor(0.2340, device='cuda:0'), 'train_loss_giou': tensor(0.7071, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7268, device='cuda:0'), 'validation_loss_ce': tensor(0.4118, device='cuda:0'), 'validation_loss_bbox': tensor(0.2167, device='cuda:0'), 'validation_loss_giou': tensor(0.6157, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2934, device='cuda:0'), 'train_loss_ce': tensor(0.4336, device='cuda:0'), 'train_loss_bbox': tensor(0.1805, device='cuda:0'), 'train_loss_giou': tensor(0.4787, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7026, device='cuda:0'), 'validation_loss_ce': tensor(0.4199, device='cuda:0'), 'validation_loss_bbox': tensor(0.2155, device='cuda:0'), 'validation_loss_giou': tensor(0.6026, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2257, device='cuda:0'), 'train_loss_ce': tensor(0.4414, device='cuda:0'), 'train_loss_bbox': tensor(0.1801, device='cuda:0'), 'train_loss_giou': tensor(0.4420, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8028, device='cuda:0'), 'validation_loss_ce': tensor(0.4215, device='cuda:0'), 'validation_loss_bbox': tensor(0.2218, device='cuda:0'), 'validation_loss_giou': tensor(0.6361, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(3.2935, device='cuda:0'), 'train_loss_ce': tensor(0.4851, device='cuda:0'), 'train_loss_bbox': tensor(0.2494, device='cuda:0'), 'train_loss_giou': tensor(0.7807, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7375, device='cuda:0'), 'validation_loss_ce': tensor(0.4192, device='cuda:0'), 'validation_loss_bbox': tensor(0.2163, device='cuda:0'), 'validation_loss_giou': tensor(0.6184, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'validation_loss': tensor(7.0933, device='cuda:0'), 'validation_loss_ce': tensor(2.6325, device='cuda:0'), 'validation_loss_bbox': tensor(0.5049, device='cuda:0'), 'validation_loss_giou': tensor(0.9681, device='cuda:0'), 'validation_cardinality_error': tensor(99., device='cuda:0')}
+{'training_loss': tensor(2.2101, device='cuda:0'), 'train_loss_ce': tensor(0.4669, device='cuda:0'), 'train_loss_bbox': tensor(0.1601, device='cuda:0'), 'train_loss_giou': tensor(0.4713, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4272, device='cuda:0'), 'validation_loss_ce': tensor(0.4454, device='cuda:0'), 'validation_loss_bbox': tensor(0.1814, device='cuda:0'), 'validation_loss_giou': tensor(0.5375, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7165, device='cuda:0'), 'train_loss_ce': tensor(0.4522, device='cuda:0'), 'train_loss_bbox': tensor(0.1315, device='cuda:0'), 'train_loss_giou': tensor(0.3035, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2316, device='cuda:0'), 'validation_loss_ce': tensor(0.4329, device='cuda:0'), 'validation_loss_bbox': tensor(0.1506, device='cuda:0'), 'validation_loss_giou': tensor(0.5228, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4262, device='cuda:0'), 'train_loss_ce': tensor(0.4559, device='cuda:0'), 'train_loss_bbox': tensor(0.1564, device='cuda:0'), 'train_loss_giou': tensor(0.5942, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1372, device='cuda:0'), 'validation_loss_ce': tensor(0.4360, device='cuda:0'), 'validation_loss_bbox': tensor(0.1478, device='cuda:0'), 'validation_loss_giou': tensor(0.4811, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1364, device='cuda:0'), 'train_loss_ce': tensor(0.4127, device='cuda:0'), 'train_loss_bbox': tensor(0.1297, device='cuda:0'), 'train_loss_giou': tensor(0.5375, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1923, device='cuda:0'), 'validation_loss_ce': tensor(0.4127, device='cuda:0'), 'validation_loss_bbox': tensor(0.1510, device='cuda:0'), 'validation_loss_giou': tensor(0.5122, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1083, device='cuda:0'), 'train_loss_ce': tensor(0.3250, device='cuda:0'), 'train_loss_bbox': tensor(0.1613, device='cuda:0'), 'train_loss_giou': tensor(0.4884, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0341, device='cuda:0'), 'validation_loss_ce': tensor(0.4116, device='cuda:0'), 'validation_loss_bbox': tensor(0.1375, device='cuda:0'), 'validation_loss_giou': tensor(0.4674, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1673, device='cuda:0'), 'train_loss_ce': tensor(0.4102, device='cuda:0'), 'train_loss_bbox': tensor(0.1334, device='cuda:0'), 'train_loss_giou': tensor(0.5452, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0928, device='cuda:0'), 'validation_loss_ce': tensor(0.3856, device='cuda:0'), 'validation_loss_bbox': tensor(0.1463, device='cuda:0'), 'validation_loss_giou': tensor(0.4878, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7178, device='cuda:0'), 'train_loss_ce': tensor(0.4061, device='cuda:0'), 'train_loss_bbox': tensor(0.0982, device='cuda:0'), 'train_loss_giou': tensor(0.4103, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1328, device='cuda:0'), 'validation_loss_ce': tensor(0.3973, device='cuda:0'), 'validation_loss_bbox': tensor(0.1413, device='cuda:0'), 'validation_loss_giou': tensor(0.5145, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2961, device='cuda:0'), 'train_loss_ce': tensor(0.3717, device='cuda:0'), 'train_loss_bbox': tensor(0.1444, device='cuda:0'), 'train_loss_giou': tensor(0.6012, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9445, device='cuda:0'), 'validation_loss_ce': tensor(0.3745, device='cuda:0'), 'validation_loss_bbox': tensor(0.1293, device='cuda:0'), 'validation_loss_giou': tensor(0.4619, device='cuda:0'), 'validation_cardinality_error': tensor(0.8990, device='cuda:0')}
+{'training_loss': tensor(2.0082, device='cuda:0'), 'train_loss_ce': tensor(0.4834, device='cuda:0'), 'train_loss_bbox': tensor(0.1454, device='cuda:0'), 'train_loss_giou': tensor(0.3990, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8980, device='cuda:0'), 'validation_loss_ce': tensor(0.3738, device='cuda:0'), 'validation_loss_bbox': tensor(0.1218, device='cuda:0'), 'validation_loss_giou': tensor(0.4576, device='cuda:0'), 'validation_cardinality_error': tensor(0.8182, device='cuda:0')}
+{'training_loss': tensor(2.5432, device='cuda:0'), 'train_loss_ce': tensor(0.4593, device='cuda:0'), 'train_loss_bbox': tensor(0.1676, device='cuda:0'), 'train_loss_giou': tensor(0.6229, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9865, device='cuda:0'), 'validation_loss_ce': tensor(0.3900, device='cuda:0'), 'validation_loss_bbox': tensor(0.1392, device='cuda:0'), 'validation_loss_giou': tensor(0.4503, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.9886, device='cuda:0'), 'train_loss_ce': tensor(0.3825, device='cuda:0'), 'train_loss_bbox': tensor(0.1169, device='cuda:0'), 'train_loss_giou': tensor(0.5109, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9185, device='cuda:0'), 'validation_loss_ce': tensor(0.3755, device='cuda:0'), 'validation_loss_bbox': tensor(0.1302, device='cuda:0'), 'validation_loss_giou': tensor(0.4460, device='cuda:0'), 'validation_cardinality_error': tensor(0.9697, device='cuda:0')}
+{'training_loss': tensor(1.4652, device='cuda:0'), 'train_loss_ce': tensor(0.3647, device='cuda:0'), 'train_loss_bbox': tensor(0.0751, device='cuda:0'), 'train_loss_giou': tensor(0.3625, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9299, device='cuda:0'), 'validation_loss_ce': tensor(0.3658, device='cuda:0'), 'validation_loss_bbox': tensor(0.1326, device='cuda:0'), 'validation_loss_giou': tensor(0.4505, device='cuda:0'), 'validation_cardinality_error': tensor(0.3434, device='cuda:0')}
+{'training_loss': tensor(1.8145, device='cuda:0'), 'train_loss_ce': tensor(0.4718, device='cuda:0'), 'train_loss_bbox': tensor(0.0969, device='cuda:0'), 'train_loss_giou': tensor(0.4291, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9555, device='cuda:0'), 'validation_loss_ce': tensor(0.3583, device='cuda:0'), 'validation_loss_bbox': tensor(0.1334, device='cuda:0'), 'validation_loss_giou': tensor(0.4650, device='cuda:0'), 'validation_cardinality_error': tensor(0.5152, device='cuda:0')}
+{'training_loss': tensor(2.0291, device='cuda:0'), 'train_loss_ce': tensor(0.3718, device='cuda:0'), 'train_loss_bbox': tensor(0.1291, device='cuda:0'), 'train_loss_giou': tensor(0.5060, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3917, device='cuda:0'), 'validation_loss_ce': tensor(0.3621, device='cuda:0'), 'validation_loss_bbox': tensor(0.1767, device='cuda:0'), 'validation_loss_giou': tensor(0.5731, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
+{'training_loss': tensor(2.1299, device='cuda:0'), 'train_loss_ce': tensor(0.4300, device='cuda:0'), 'train_loss_bbox': tensor(0.1054, device='cuda:0'), 'train_loss_giou': tensor(0.5863, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1091, device='cuda:0'), 'validation_loss_ce': tensor(0.3579, device='cuda:0'), 'validation_loss_bbox': tensor(0.1479, device='cuda:0'), 'validation_loss_giou': tensor(0.5058, device='cuda:0'), 'validation_cardinality_error': tensor(0.6061, device='cuda:0')}
+{'training_loss': tensor(2.0963, device='cuda:0'), 'train_loss_ce': tensor(0.2759, device='cuda:0'), 'train_loss_bbox': tensor(0.1520, device='cuda:0'), 'train_loss_giou': tensor(0.5301, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0418, device='cuda:0'), 'validation_loss_ce': tensor(0.3464, device='cuda:0'), 'validation_loss_bbox': tensor(0.1385, device='cuda:0'), 'validation_loss_giou': tensor(0.5015, device='cuda:0'), 'validation_cardinality_error': tensor(0.6263, device='cuda:0')}
+{'training_loss': tensor(2.1784, device='cuda:0'), 'train_loss_ce': tensor(0.3634, device='cuda:0'), 'train_loss_bbox': tensor(0.1741, device='cuda:0'), 'train_loss_giou': tensor(0.4723, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9543, device='cuda:0'), 'validation_loss_ce': tensor(0.3518, device='cuda:0'), 'validation_loss_bbox': tensor(0.1322, device='cuda:0'), 'validation_loss_giou': tensor(0.4707, device='cuda:0'), 'validation_cardinality_error': tensor(0.9495, device='cuda:0')}
+{'training_loss': tensor(2.0823, device='cuda:0'), 'train_loss_ce': tensor(0.3437, device='cuda:0'), 'train_loss_bbox': tensor(0.1144, device='cuda:0'), 'train_loss_giou': tensor(0.5833, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8429, device='cuda:0'), 'validation_loss_ce': tensor(0.3513, device='cuda:0'), 'validation_loss_bbox': tensor(0.1216, device='cuda:0'), 'validation_loss_giou': tensor(0.4417, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
+{'training_loss': tensor(1.4899, device='cuda:0'), 'train_loss_ce': tensor(0.3300, device='cuda:0'), 'train_loss_bbox': tensor(0.0826, device='cuda:0'), 'train_loss_giou': tensor(0.3734, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8750, device='cuda:0'), 'validation_loss_ce': tensor(0.3539, device='cuda:0'), 'validation_loss_bbox': tensor(0.1210, device='cuda:0'), 'validation_loss_giou': tensor(0.4580, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
+{'training_loss': tensor(2.2234, device='cuda:0'), 'train_loss_ce': tensor(0.3947, device='cuda:0'), 'train_loss_bbox': tensor(0.1587, device='cuda:0'), 'train_loss_giou': tensor(0.5175, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9507, device='cuda:0'), 'validation_loss_ce': tensor(0.3356, device='cuda:0'), 'validation_loss_bbox': tensor(0.1303, device='cuda:0'), 'validation_loss_giou': tensor(0.4817, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
+{'training_loss': tensor(1.5594, device='cuda:0'), 'train_loss_ce': tensor(0.3898, device='cuda:0'), 'train_loss_bbox': tensor(0.1000, device='cuda:0'), 'train_loss_giou': tensor(0.3347, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9082, device='cuda:0'), 'validation_loss_ce': tensor(0.3350, device='cuda:0'), 'validation_loss_bbox': tensor(0.1296, device='cuda:0'), 'validation_loss_giou': tensor(0.4626, device='cuda:0'), 'validation_cardinality_error': tensor(0.5859, device='cuda:0')}
+{'training_loss': tensor(1.3733, device='cuda:0'), 'train_loss_ce': tensor(0.2466, device='cuda:0'), 'train_loss_bbox': tensor(0.0828, device='cuda:0'), 'train_loss_giou': tensor(0.3563, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8808, device='cuda:0'), 'validation_loss_ce': tensor(0.3422, device='cuda:0'), 'validation_loss_bbox': tensor(0.1253, device='cuda:0'), 'validation_loss_giou': tensor(0.4559, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
+{'training_loss': tensor(1.9375, device='cuda:0'), 'train_loss_ce': tensor(0.3146, device='cuda:0'), 'train_loss_bbox': tensor(0.1273, device='cuda:0'), 'train_loss_giou': tensor(0.4931, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8543, device='cuda:0'), 'validation_loss_ce': tensor(0.3441, device='cuda:0'), 'validation_loss_bbox': tensor(0.1196, device='cuda:0'), 'validation_loss_giou': tensor(0.4561, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
+{'training_loss': tensor(1.7360, device='cuda:0'), 'train_loss_ce': tensor(0.2615, device='cuda:0'), 'train_loss_bbox': tensor(0.1172, device='cuda:0'), 'train_loss_giou': tensor(0.4441, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8177, device='cuda:0'), 'validation_loss_ce': tensor(0.3491, device='cuda:0'), 'validation_loss_bbox': tensor(0.1182, device='cuda:0'), 'validation_loss_giou': tensor(0.4387, device='cuda:0'), 'validation_cardinality_error': tensor(0.6465, device='cuda:0')}
+{'training_loss': tensor(1.4278, device='cuda:0'), 'train_loss_ce': tensor(0.4191, device='cuda:0'), 'train_loss_bbox': tensor(0.0621, device='cuda:0'), 'train_loss_giou': tensor(0.3491, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7745, device='cuda:0'), 'validation_loss_ce': tensor(0.3331, device='cuda:0'), 'validation_loss_bbox': tensor(0.1184, device='cuda:0'), 'validation_loss_giou': tensor(0.4248, device='cuda:0'), 'validation_cardinality_error': tensor(0.5152, device='cuda:0')}
+{'training_loss': tensor(1.5275, device='cuda:0'), 'train_loss_ce': tensor(0.2538, device='cuda:0'), 'train_loss_bbox': tensor(0.1081, device='cuda:0'), 'train_loss_giou': tensor(0.3666, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.7723, device='cuda:0'), 'validation_loss_ce': tensor(0.3335, device='cuda:0'), 'validation_loss_bbox': tensor(0.1156, device='cuda:0'), 'validation_loss_giou': tensor(0.4303, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
+{'training_loss': tensor(1.2553, device='cuda:0'), 'train_loss_ce': tensor(0.2647, device='cuda:0'), 'train_loss_bbox': tensor(0.0725, device='cuda:0'), 'train_loss_giou': tensor(0.3140, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.7969, device='cuda:0'), 'validation_loss_ce': tensor(0.3384, device='cuda:0'), 'validation_loss_bbox': tensor(0.1183, device='cuda:0'), 'validation_loss_giou': tensor(0.4334, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
+{'training_loss': tensor(2.2105, device='cuda:0'), 'train_loss_ce': tensor(0.4101, device='cuda:0'), 'train_loss_bbox': tensor(0.1634, device='cuda:0'), 'train_loss_giou': tensor(0.4917, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7978, device='cuda:0'), 'validation_loss_ce': tensor(0.3421, device='cuda:0'), 'validation_loss_bbox': tensor(0.1197, device='cuda:0'), 'validation_loss_giou': tensor(0.4286, device='cuda:0'), 'validation_cardinality_error': tensor(0.7677, device='cuda:0')}
+{'training_loss': tensor(1.3302, device='cuda:0'), 'train_loss_ce': tensor(0.3538, device='cuda:0'), 'train_loss_bbox': tensor(0.0723, device='cuda:0'), 'train_loss_giou': tensor(0.3074, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8850, device='cuda:0'), 'validation_loss_ce': tensor(0.3273, device='cuda:0'), 'validation_loss_bbox': tensor(0.1313, device='cuda:0'), 'validation_loss_giou': tensor(0.4507, device='cuda:0'), 'validation_cardinality_error': tensor(0.5960, device='cuda:0')}
+{'training_loss': tensor(1.5171, device='cuda:0'), 'train_loss_ce': tensor(0.3285, device='cuda:0'), 'train_loss_bbox': tensor(0.0630, device='cuda:0'), 'train_loss_giou': tensor(0.4368, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7658, device='cuda:0'), 'validation_loss_ce': tensor(0.3375, device='cuda:0'), 'validation_loss_bbox': tensor(0.1182, device='cuda:0'), 'validation_loss_giou': tensor(0.4186, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
 ```
 
 ## Examples