MedicalVision
/

yolos_tiny_50ep

@@ -3,197 +3,106 @@ library_name: transformers
 tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 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 ] = 0.000
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.000
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.000
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
+ 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 ] = 0.000
+ 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 ] = 0.013
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.030
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.006
+ 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 ] = 0.013
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.071
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.141
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.159
+ 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 ] = 0.164
+```
+## Config
+- dataset: NIH
+- original model: hustvl/yolos-tiny
+- lr: 0.0001
+- dropout_rate: 0.1
+- weight_decay: 0.001
+- max_epochs: 50
+- train samples: 885
+## Logging
+### Training process
+```
+{'validation_loss': tensor(6.9980, device='cuda:0'), 'validation_loss_ce': tensor(2.0774, device='cuda:0'), 'validation_loss_bbox': tensor(0.5764, device='cuda:0'), 'validation_loss_giou': tensor(1.0194, device='cuda:0'), 'validation_cardinality_error': tensor(96.1875, device='cuda:0')}
+{'training_loss': tensor(1.9591, device='cuda:0'), 'train_loss_ce': tensor(0.3168, device='cuda:0'), 'train_loss_bbox': tensor(0.1506, device='cuda:0'), 'train_loss_giou': tensor(0.4447, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3060, device='cuda:0'), 'validation_loss_ce': tensor(0.4328, device='cuda:0'), 'validation_loss_bbox': tensor(0.1669, device='cuda:0'), 'validation_loss_giou': tensor(0.5192, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.6421, device='cuda:0'), 'train_loss_ce': tensor(0.4176, device='cuda:0'), 'train_loss_bbox': tensor(0.2296, device='cuda:0'), 'train_loss_giou': tensor(0.5382, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3129, device='cuda:0'), 'validation_loss_ce': tensor(0.4220, device='cuda:0'), 'validation_loss_bbox': tensor(0.1653, device='cuda:0'), 'validation_loss_giou': tensor(0.5321, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0230, device='cuda:0'), 'train_loss_ce': tensor(0.3812, device='cuda:0'), 'train_loss_bbox': tensor(0.1228, device='cuda:0'), 'train_loss_giou': tensor(0.5139, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5272, device='cuda:0'), 'validation_loss_ce': tensor(0.4293, device='cuda:0'), 'validation_loss_bbox': tensor(0.1835, device='cuda:0'), 'validation_loss_giou': tensor(0.5901, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.9008, device='cuda:0'), 'train_loss_ce': tensor(0.4246, device='cuda:0'), 'train_loss_bbox': tensor(0.1294, device='cuda:0'), 'train_loss_giou': tensor(0.4146, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3039, device='cuda:0'), 'validation_loss_ce': tensor(0.4134, device='cuda:0'), 'validation_loss_bbox': tensor(0.1584, device='cuda:0'), 'validation_loss_giou': tensor(0.5492, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1614, device='cuda:0'), 'train_loss_ce': tensor(0.4317, device='cuda:0'), 'train_loss_bbox': tensor(0.1515, device='cuda:0'), 'train_loss_giou': tensor(0.4861, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3038, device='cuda:0'), 'validation_loss_ce': tensor(0.4126, device='cuda:0'), 'validation_loss_bbox': tensor(0.1583, device='cuda:0'), 'validation_loss_giou': tensor(0.5497, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.5595, device='cuda:0'), 'train_loss_ce': tensor(0.4053, device='cuda:0'), 'train_loss_bbox': tensor(0.0866, device='cuda:0'), 'train_loss_giou': tensor(0.3605, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1651, device='cuda:0'), 'validation_loss_ce': tensor(0.4196, device='cuda:0'), 'validation_loss_bbox': tensor(0.1478, device='cuda:0'), 'validation_loss_giou': tensor(0.5031, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0434, device='cuda:0'), 'train_loss_ce': tensor(0.3087, device='cuda:0'), 'train_loss_bbox': tensor(0.1553, device='cuda:0'), 'train_loss_giou': tensor(0.4792, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2701, device='cuda:0'), 'validation_loss_ce': tensor(0.3932, device='cuda:0'), 'validation_loss_bbox': tensor(0.1609, device='cuda:0'), 'validation_loss_giou': tensor(0.5361, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.3151, device='cuda:0'), 'train_loss_ce': tensor(0.3850, device='cuda:0'), 'train_loss_bbox': tensor(0.1603, device='cuda:0'), 'train_loss_giou': tensor(0.5642, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7141, device='cuda:0'), 'validation_loss_ce': tensor(0.4040, device='cuda:0'), 'validation_loss_bbox': tensor(0.2126, device='cuda:0'), 'validation_loss_giou': tensor(0.6236, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.7767, device='cuda:0'), 'train_loss_ce': tensor(0.4482, device='cuda:0'), 'train_loss_bbox': tensor(0.2168, device='cuda:0'), 'train_loss_giou': tensor(0.6224, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4795, device='cuda:0'), 'validation_loss_ce': tensor(0.4138, device='cuda:0'), 'validation_loss_bbox': tensor(0.1788, device='cuda:0'), 'validation_loss_giou': tensor(0.5857, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.5112, device='cuda:0'), 'train_loss_ce': tensor(0.4653, device='cuda:0'), 'train_loss_bbox': tensor(0.1600, device='cuda:0'), 'train_loss_giou': tensor(0.6229, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5765, device='cuda:0'), 'validation_loss_ce': tensor(0.4042, device='cuda:0'), 'validation_loss_bbox': tensor(0.1957, device='cuda:0'), 'validation_loss_giou': tensor(0.5970, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2503, device='cuda:0'), 'train_loss_ce': tensor(0.4681, device='cuda:0'), 'train_loss_bbox': tensor(0.1526, device='cuda:0'), 'train_loss_giou': tensor(0.5096, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5902, device='cuda:0'), 'validation_loss_ce': tensor(0.4213, device='cuda:0'), 'validation_loss_bbox': tensor(0.1939, device='cuda:0'), 'validation_loss_giou': tensor(0.5997, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.9702, device='cuda:0'), 'train_loss_ce': tensor(0.4538, device='cuda:0'), 'train_loss_bbox': tensor(0.2257, device='cuda:0'), 'train_loss_giou': tensor(0.6939, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5045, device='cuda:0'), 'validation_loss_ce': tensor(0.4158, device='cuda:0'), 'validation_loss_bbox': tensor(0.1966, device='cuda:0'), 'validation_loss_giou': tensor(0.5528, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1300, device='cuda:0'), 'train_loss_ce': tensor(0.3665, device='cuda:0'), 'train_loss_bbox': tensor(0.1390, device='cuda:0'), 'train_loss_giou': tensor(0.5341, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3374, device='cuda:0'), 'validation_loss_ce': tensor(0.4036, device='cuda:0'), 'validation_loss_bbox': tensor(0.1654, device='cuda:0'), 'validation_loss_giou': tensor(0.5534, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2715, device='cuda:0'), 'train_loss_ce': tensor(0.4282, device='cuda:0'), 'train_loss_bbox': tensor(0.1883, device='cuda:0'), 'train_loss_giou': tensor(0.4509, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3349, device='cuda:0'), 'validation_loss_ce': tensor(0.3914, device='cuda:0'), 'validation_loss_bbox': tensor(0.1709, device='cuda:0'), 'validation_loss_giou': tensor(0.5445, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7526, device='cuda:0'), 'train_loss_ce': tensor(0.3276, device='cuda:0'), 'train_loss_bbox': tensor(0.1172, device='cuda:0'), 'train_loss_giou': tensor(0.4195, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2411, device='cuda:0'), 'validation_loss_ce': tensor(0.3867, device='cuda:0'), 'validation_loss_bbox': tensor(0.1625, device='cuda:0'), 'validation_loss_giou': tensor(0.5210, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7417, device='cuda:0'), 'train_loss_ce': tensor(0.3457, device='cuda:0'), 'train_loss_bbox': tensor(0.1130, device='cuda:0'), 'train_loss_giou': tensor(0.4154, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3407, device='cuda:0'), 'validation_loss_ce': tensor(0.3910, device='cuda:0'), 'validation_loss_bbox': tensor(0.1646, device='cuda:0'), 'validation_loss_giou': tensor(0.5634, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.7487, device='cuda:0'), 'train_loss_ce': tensor(0.3850, device='cuda:0'), 'train_loss_bbox': tensor(0.1692, device='cuda:0'), 'train_loss_giou': tensor(0.7589, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4066, device='cuda:0'), 'validation_loss_ce': tensor(0.4094, device='cuda:0'), 'validation_loss_bbox': tensor(0.1719, device='cuda:0'), 'validation_loss_giou': tensor(0.5690, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.7448, device='cuda:0'), 'train_loss_ce': tensor(0.4563, device='cuda:0'), 'train_loss_bbox': tensor(0.2001, device='cuda:0'), 'train_loss_giou': tensor(0.6441, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2312, device='cuda:0'), 'validation_loss_ce': tensor(0.3842, device='cuda:0'), 'validation_loss_bbox': tensor(0.1588, device='cuda:0'), 'validation_loss_giou': tensor(0.5265, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.9861, device='cuda:0'), 'train_loss_ce': tensor(0.4062, device='cuda:0'), 'train_loss_bbox': tensor(0.1622, device='cuda:0'), 'train_loss_giou': tensor(0.3844, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2770, device='cuda:0'), 'validation_loss_ce': tensor(0.3843, device='cuda:0'), 'validation_loss_bbox': tensor(0.1617, device='cuda:0'), 'validation_loss_giou': tensor(0.5421, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4871, device='cuda:0'), 'train_loss_ce': tensor(0.3550, device='cuda:0'), 'train_loss_bbox': tensor(0.1734, device='cuda:0'), 'train_loss_giou': tensor(0.6325, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3588, device='cuda:0'), 'validation_loss_ce': tensor(0.3915, device='cuda:0'), 'validation_loss_bbox': tensor(0.1721, device='cuda:0'), 'validation_loss_giou': tensor(0.5533, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4463, device='cuda:0'), 'train_loss_ce': tensor(0.4212, device='cuda:0'), 'train_loss_bbox': tensor(0.1563, device='cuda:0'), 'train_loss_giou': tensor(0.6217, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1789, device='cuda:0'), 'validation_loss_ce': tensor(0.3907, device='cuda:0'), 'validation_loss_bbox': tensor(0.1505, device='cuda:0'), 'validation_loss_giou': tensor(0.5179, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.8296, device='cuda:0'), 'train_loss_ce': tensor(0.3541, device='cuda:0'), 'train_loss_bbox': tensor(0.1274, device='cuda:0'), 'train_loss_giou': tensor(0.4192, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2105, device='cuda:0'), 'validation_loss_ce': tensor(0.3775, device='cuda:0'), 'validation_loss_bbox': tensor(0.1559, device='cuda:0'), 'validation_loss_giou': tensor(0.5268, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.3388, device='cuda:0'), 'train_loss_ce': tensor(0.3709, device='cuda:0'), 'train_loss_bbox': tensor(0.1459, device='cuda:0'), 'train_loss_giou': tensor(0.6191, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1570, device='cuda:0'), 'validation_loss_ce': tensor(0.3723, device='cuda:0'), 'validation_loss_bbox': tensor(0.1484, device='cuda:0'), 'validation_loss_giou': tensor(0.5215, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2575, device='cuda:0'), 'train_loss_ce': tensor(0.4642, device='cuda:0'), 'train_loss_bbox': tensor(0.1563, device='cuda:0'), 'train_loss_giou': tensor(0.5059, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2539, device='cuda:0'), 'validation_loss_ce': tensor(0.3751, device='cuda:0'), 'validation_loss_bbox': tensor(0.1614, device='cuda:0'), 'validation_loss_giou': tensor(0.5358, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.3852, device='cuda:0'), 'train_loss_ce': tensor(0.4486, device='cuda:0'), 'train_loss_bbox': tensor(0.1840, device='cuda:0'), 'train_loss_giou': tensor(0.5083, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2098, device='cuda:0'), 'validation_loss_ce': tensor(0.3731, device='cuda:0'), 'validation_loss_bbox': tensor(0.1589, device='cuda:0'), 'validation_loss_giou': tensor(0.5212, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0163, device='cuda:0'), 'train_loss_ce': tensor(0.3895, device='cuda:0'), 'train_loss_bbox': tensor(0.1363, device='cuda:0'), 'train_loss_giou': tensor(0.4726, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1935, device='cuda:0'), 'validation_loss_ce': tensor(0.3829, device='cuda:0'), 'validation_loss_bbox': tensor(0.1517, device='cuda:0'), 'validation_loss_giou': tensor(0.5262, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
+{'training_loss': tensor(1.8352, device='cuda:0'), 'train_loss_ce': tensor(0.3180, device='cuda:0'), 'train_loss_bbox': tensor(0.1492, device='cuda:0'), 'train_loss_giou': tensor(0.3855, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2605, device='cuda:0'), 'validation_loss_ce': tensor(0.3676, device='cuda:0'), 'validation_loss_bbox': tensor(0.1609, device='cuda:0'), 'validation_loss_giou': tensor(0.5442, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.3223, device='cuda:0'), 'train_loss_ce': tensor(0.3044, device='cuda:0'), 'train_loss_bbox': tensor(0.1013, device='cuda:0'), 'train_loss_giou': tensor(0.2556, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2185, device='cuda:0'), 'validation_loss_ce': tensor(0.3744, device='cuda:0'), 'validation_loss_bbox': tensor(0.1587, device='cuda:0'), 'validation_loss_giou': tensor(0.5252, device='cuda:0'), 'validation_cardinality_error': tensor(0.9495, device='cuda:0')}
+{'training_loss': tensor(1.9661, device='cuda:0'), 'train_loss_ce': tensor(0.3483, device='cuda:0'), 'train_loss_bbox': tensor(0.1175, device='cuda:0'), 'train_loss_giou': tensor(0.5150, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(2.2522, device='cuda:0'), 'validation_loss_ce': tensor(0.3802, device='cuda:0'), 'validation_loss_bbox': tensor(0.1586, device='cuda:0'), 'validation_loss_giou': tensor(0.5394, device='cuda:0'), 'validation_cardinality_error': tensor(0.7778, device='cuda:0')}
+{'training_loss': tensor(2.3235, device='cuda:0'), 'train_loss_ce': tensor(0.3712, device='cuda:0'), 'train_loss_bbox': tensor(0.1939, device='cuda:0'), 'train_loss_giou': tensor(0.4915, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1720, device='cuda:0'), 'validation_loss_ce': tensor(0.3719, device='cuda:0'), 'validation_loss_bbox': tensor(0.1527, device='cuda:0'), 'validation_loss_giou': tensor(0.5184, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
+{'training_loss': tensor(1.5666, device='cuda:0'), 'train_loss_ce': tensor(0.3918, device='cuda:0'), 'train_loss_bbox': tensor(0.0777, device='cuda:0'), 'train_loss_giou': tensor(0.3931, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0891, device='cuda:0'), 'validation_loss_ce': tensor(0.3705, device='cuda:0'), 'validation_loss_bbox': tensor(0.1437, device='cuda:0'), 'validation_loss_giou': tensor(0.4999, device='cuda:0'), 'validation_cardinality_error': tensor(0.9899, device='cuda:0')}
+{'training_loss': tensor(2.0268, device='cuda:0'), 'train_loss_ce': tensor(0.3945, device='cuda:0'), 'train_loss_bbox': tensor(0.1465, device='cuda:0'), 'train_loss_giou': tensor(0.4499, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1654, device='cuda:0'), 'validation_loss_ce': tensor(0.3704, device='cuda:0'), 'validation_loss_bbox': tensor(0.1474, device='cuda:0'), 'validation_loss_giou': tensor(0.5291, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0776, device='cuda:0'), 'train_loss_ce': tensor(0.4210, device='cuda:0'), 'train_loss_bbox': tensor(0.1471, device='cuda:0'), 'train_loss_giou': tensor(0.4607, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(2.1170, device='cuda:0'), 'validation_loss_ce': tensor(0.3763, device='cuda:0'), 'validation_loss_bbox': tensor(0.1431, device='cuda:0'), 'validation_loss_giou': tensor(0.5127, device='cuda:0'), 'validation_cardinality_error': tensor(0.3232, device='cuda:0')}
+{'training_loss': tensor(1.4932, device='cuda:0'), 'train_loss_ce': tensor(0.3657, device='cuda:0'), 'train_loss_bbox': tensor(0.0990, device='cuda:0'), 'train_loss_giou': tensor(0.3163, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0869, device='cuda:0'), 'validation_loss_ce': tensor(0.3713, device='cuda:0'), 'validation_loss_bbox': tensor(0.1457, device='cuda:0'), 'validation_loss_giou': tensor(0.4936, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.8174, device='cuda:0'), 'train_loss_ce': tensor(0.3460, device='cuda:0'), 'train_loss_bbox': tensor(0.1162, device='cuda:0'), 'train_loss_giou': tensor(0.4452, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0891, device='cuda:0'), 'validation_loss_ce': tensor(0.3620, device='cuda:0'), 'validation_loss_bbox': tensor(0.1402, device='cuda:0'), 'validation_loss_giou': tensor(0.5130, device='cuda:0'), 'validation_cardinality_error': tensor(0.9596, device='cuda:0')}
+{'training_loss': tensor(2.1190, device='cuda:0'), 'train_loss_ce': tensor(0.3552, device='cuda:0'), 'train_loss_bbox': tensor(0.1349, device='cuda:0'), 'train_loss_giou': tensor(0.5447, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0378, device='cuda:0'), 'validation_loss_ce': tensor(0.3590, device='cuda:0'), 'validation_loss_bbox': tensor(0.1388, device='cuda:0'), 'validation_loss_giou': tensor(0.4923, device='cuda:0'), 'validation_cardinality_error': tensor(0.9899, device='cuda:0')}
+{'training_loss': tensor(1.8194, device='cuda:0'), 'train_loss_ce': tensor(0.3136, device='cuda:0'), 'train_loss_bbox': tensor(0.1044, device='cuda:0'), 'train_loss_giou': tensor(0.4920, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0059, device='cuda:0'), 'validation_loss_ce': tensor(0.3623, device='cuda:0'), 'validation_loss_bbox': tensor(0.1370, device='cuda:0'), 'validation_loss_giou': tensor(0.4794, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0199, device='cuda:0'), 'train_loss_ce': tensor(0.3735, device='cuda:0'), 'train_loss_bbox': tensor(0.1110, device='cuda:0'), 'train_loss_giou': tensor(0.5458, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0734, device='cuda:0'), 'validation_loss_ce': tensor(0.3659, device='cuda:0'), 'validation_loss_bbox': tensor(0.1376, device='cuda:0'), 'validation_loss_giou': tensor(0.5096, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.5889, device='cuda:0'), 'train_loss_ce': tensor(0.3230, device='cuda:0'), 'train_loss_bbox': tensor(0.0800, device='cuda:0'), 'train_loss_giou': tensor(0.4330, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9917, device='cuda:0'), 'validation_loss_ce': tensor(0.3621, device='cuda:0'), 'validation_loss_bbox': tensor(0.1349, device='cuda:0'), 'validation_loss_giou': tensor(0.4775, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
+{'training_loss': tensor(1.5126, device='cuda:0'), 'train_loss_ce': tensor(0.3984, device='cuda:0'), 'train_loss_bbox': tensor(0.0810, device='cuda:0'), 'train_loss_giou': tensor(0.3545, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(2.0611, device='cuda:0'), 'validation_loss_ce': tensor(0.3687, device='cuda:0'), 'validation_loss_bbox': tensor(0.1368, device='cuda:0'), 'validation_loss_giou': tensor(0.5041, device='cuda:0'), 'validation_cardinality_error': tensor(0.7576, device='cuda:0')}
+{'training_loss': tensor(1.8280, device='cuda:0'), 'train_loss_ce': tensor(0.4029, device='cuda:0'), 'train_loss_bbox': tensor(0.0999, device='cuda:0'), 'train_loss_giou': tensor(0.4629, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0638, device='cuda:0'), 'validation_loss_ce': tensor(0.3683, device='cuda:0'), 'validation_loss_bbox': tensor(0.1420, device='cuda:0'), 'validation_loss_giou': tensor(0.4927, device='cuda:0'), 'validation_cardinality_error': tensor(0.9899, device='cuda:0')}
+{'training_loss': tensor(1.7057, device='cuda:0'), 'train_loss_ce': tensor(0.4136, device='cuda:0'), 'train_loss_bbox': tensor(0.0915, device='cuda:0'), 'train_loss_giou': tensor(0.4172, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0228, device='cuda:0'), 'validation_loss_ce': tensor(0.3651, device='cuda:0'), 'validation_loss_bbox': tensor(0.1387, device='cuda:0'), 'validation_loss_giou': tensor(0.4822, device='cuda:0'), 'validation_cardinality_error': tensor(0.9596, device='cuda:0')}
+{'training_loss': tensor(1.5449, device='cuda:0'), 'train_loss_ce': tensor(0.3997, device='cuda:0'), 'train_loss_bbox': tensor(0.0768, device='cuda:0'), 'train_loss_giou': tensor(0.3806, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0353, device='cuda:0'), 'validation_loss_ce': tensor(0.3622, device='cuda:0'), 'validation_loss_bbox': tensor(0.1349, device='cuda:0'), 'validation_loss_giou': tensor(0.4992, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
+{'training_loss': tensor(1.7316, device='cuda:0'), 'train_loss_ce': tensor(0.4420, device='cuda:0'), 'train_loss_bbox': tensor(0.0924, device='cuda:0'), 'train_loss_giou': tensor(0.4137, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0308, device='cuda:0'), 'validation_loss_ce': tensor(0.3487, device='cuda:0'), 'validation_loss_bbox': tensor(0.1383, device='cuda:0'), 'validation_loss_giou': tensor(0.4952, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7057, device='cuda:0'), 'train_loss_ce': tensor(0.4140, device='cuda:0'), 'train_loss_bbox': tensor(0.1117, device='cuda:0'), 'train_loss_giou': tensor(0.3667, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9358, device='cuda:0'), 'validation_loss_ce': tensor(0.3484, device='cuda:0'), 'validation_loss_bbox': tensor(0.1280, device='cuda:0'), 'validation_loss_giou': tensor(0.4737, device='cuda:0'), 'validation_cardinality_error': tensor(0.4545, device='cuda:0')}
+{'training_loss': tensor(2.1335, device='cuda:0'), 'train_loss_ce': tensor(0.4015, device='cuda:0'), 'train_loss_bbox': tensor(0.1885, device='cuda:0'), 'train_loss_giou': tensor(0.3948, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9711, device='cuda:0'), 'validation_loss_ce': tensor(0.3577, device='cuda:0'), 'validation_loss_bbox': tensor(0.1309, device='cuda:0'), 'validation_loss_giou': tensor(0.4795, device='cuda:0'), 'validation_cardinality_error': tensor(0.8990, device='cuda:0')}
+{'training_loss': tensor(2.0193, device='cuda:0'), 'train_loss_ce': tensor(0.2849, device='cuda:0'), 'train_loss_bbox': tensor(0.1473, device='cuda:0'), 'train_loss_giou': tensor(0.4989, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9930, device='cuda:0'), 'validation_loss_ce': tensor(0.3653, device='cuda:0'), 'validation_loss_bbox': tensor(0.1354, device='cuda:0'), 'validation_loss_giou': tensor(0.4753, device='cuda:0'), 'validation_cardinality_error': tensor(0.9899, device='cuda:0')}
+{'training_loss': tensor(1.7410, device='cuda:0'), 'train_loss_ce': tensor(0.3670, device='cuda:0'), 'train_loss_bbox': tensor(0.1155, device='cuda:0'), 'train_loss_giou': tensor(0.3983, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(2.0600, device='cuda:0'), 'validation_loss_ce': tensor(0.3666, device='cuda:0'), 'validation_loss_bbox': tensor(0.1421, device='cuda:0'), 'validation_loss_giou': tensor(0.4914, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
+{'training_loss': tensor(1.7164, device='cuda:0'), 'train_loss_ce': tensor(0.3726, device='cuda:0'), 'train_loss_bbox': tensor(0.1148, device='cuda:0'), 'train_loss_giou': tensor(0.3849, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9918, device='cuda:0'), 'validation_loss_ce': tensor(0.3566, device='cuda:0'), 'validation_loss_bbox': tensor(0.1360, device='cuda:0'), 'validation_loss_giou': tensor(0.4777, device='cuda:0'), 'validation_cardinality_error': tensor(0.5354, device='cuda:0')}
+{'training_loss': tensor(2.4173, device='cuda:0'), 'train_loss_ce': tensor(0.2800, device='cuda:0'), 'train_loss_bbox': tensor(0.1449, device='cuda:0'), 'train_loss_giou': tensor(0.7064, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0160, device='cuda:0'), 'validation_loss_ce': tensor(0.3560, device='cuda:0'), 'validation_loss_bbox': tensor(0.1355, device='cuda:0'), 'validation_loss_giou': tensor(0.4911, device='cuda:0'), 'validation_cardinality_error': tensor(0.5859, device='cuda:0')}
+```
+## Examples
+{'size': tensor([512, 512]), 'image_id': tensor([1]), 'class_labels': tensor([4]), 'boxes': tensor([[0.2622, 0.5729, 0.0847, 0.0773]]), 'area': tensor([1717.9431]), 'iscrowd': tensor([0]), 'orig_size': tensor([1024, 1024])}
+![Example](./example.png)