Rt Detrv2 Finetuned Trashify Box Detector v1
This model is a fine-tuned version of PekingU/rtdetrv2r50vd on an unknown dataset. It achieves the following results on the evaluation set: Loss: 9.8777 Map: 0.4063 Map 50: 0.5812 Map 75: 0.4696 Map Small: 0.0 Map...
Model source
- Kind
- Other
- File size
- 164 MB
- Base model
- PekingU/rtdetr_v2_r50vd
- Version
- vRevision 2ea1853
- Updated
- Oct 10, 2026
- Downloads
- 7
- Source
- Hugging Face
Source description
rt_detrv2_finetuned_trashify_box_detector_v1
This model is a fine-tuned version of PekingU/rtdetr_v2_r50vd on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 9.8777
- Map: 0.4063
- Map 50: 0.5812
- Map 75: 0.4696
- Map Small: 0.0
- Map Medium: 0.2154
- Map Large: 0.4213
- Mar 1: 0.4971
- Mar 10: 0.68
- Mar 100: 0.7186
- Mar Small: 0.0
- Mar Medium: 0.6017
- Mar Large: 0.7307
- Map Bin: 0.7693
- Mar Bin: 0.8602
- Map Hand: 0.5453
- Mar Hand: 0.7753
- Map Not Bin: 0.0821
- Mar Not Bin: 0.6455
- Map Not Hand: 0.0062
- Mar Not Hand: 0.6
- Map Not Trash: 0.1991
- Mar Not Trash: 0.5944
- Map Trash: 0.6217
- Mar Trash: 0.7833
- Map Trash Arm: 0.6203
- Mar Trash Arm: 0.7714
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Bin | Mar Bin | Map Hand | Mar Hand | Map Not Bin | Mar Not Bin | Map Not Hand | Mar Not Hand | Map Not Trash | Mar Not Trash | Map Trash | Mar Trash | Map Trash Arm | Mar Trash Arm |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 125.6384 | 1.0 | 50 | 37.6923 | 0.0834 | 0.1442 | 0.0839 | 0.0 | 0.0079 | 0.0865 | 0.1363 | 0.2933 | 0.2999 | 0.0 | 0.0216 | 0.3163 | 0.2779 | 0.5539 | 0.1123 | 0.3765 | 0.0014 | 0.1071 | -1.0 | -1.0 | 0.0088 | 0.1111 | 0.0961 | 0.2177 | 0.0036 | 0.4333 |
| 35.9436 | 2.0 | 100 | 15.1525 | 0.3763 | 0.5266 | 0.4267 | 0.0 | 0.0352 | 0.4024 | 0.433 | 0.576 | 0.6206 | 0.0 | 0.1375 | 0.6705 | 0.6674 | 0.8007 | 0.4107 | 0.7647 | 0.1191 | 0.5286 | -1.0 | -1.0 | 0.1109 | 0.4 | 0.4515 | 0.6965 | 0.498 | 0.5333 |
| 21.7112 | 3.0 | 150 | 11.2377 | 0.476 | 0.6327 | 0.5326 | 0.0208 | 0.3131 | 0.5013 | 0.485 | 0.697 | 0.7371 | 0.1 | 0.5119 | 0.7757 | 0.7563 | 0.8539 | 0.5948 | 0.802 | 0.1158 | 0.6286 | -1.0 | -1.0 | 0.1742 | 0.5056 | 0.6452 | 0.7991 | 0.5699 | 0.8333 |
| 17.6387 | 4.0 | 200 | 10.1056 | 0.5144 | 0.6638 | 0.5723 | 0.0406 | 0.304 | 0.5379 | 0.5509 | 0.7315 | 0.7734 | 0.25 | 0.575 | 0.8052 | 0.7854 | 0.8759 | 0.5764 | 0.8078 | 0.1273 | 0.6786 | -1.0 | -1.0 | 0.1969 | 0.5861 | 0.6409 | 0.792 | 0.7596 | 0.9 |
| 15.7398 | 5.0 | 250 | 9.5453 | 0.5128 | 0.6793 | 0.5766 | 0.1021 | 0.2854 | 0.5362 | 0.563 | 0.7215 | 0.7592 | 0.3 | 0.5494 | 0.7934 | 0.7967 | 0.8766 | 0.5882 | 0.8127 | 0.1308 | 0.6357 | -1.0 | -1.0 | 0.2046 | 0.6042 | 0.6572 | 0.7929 | 0.699 | 0.8333 |
| 14.3980 | 6.0 | 300 | 9.4995 | 0.5285 | 0.6899 | 0.588 | 0.0708 | 0.3182 | 0.5561 | 0.5619 | 0.7537 | 0.7736 | 0.3 | 0.5562 | 0.8106 | 0.7968 | 0.8773 | 0.5852 | 0.8108 | 0.1779 | 0.6857 | -1.0 | -1.0 | 0.2146 | 0.6125 | 0.6377 | 0.7885 | 0.7586 | 0.8667 |
| 13.5016 | 7.0 | 350 | 9.3702 | 0.5644 | 0.7296 | 0.6263 | 0.0839 | 0.2914 | 0.5951 | 0.586 | 0.7588 | 0.7791 | 0.3 | 0.5528 | 0.8173 | 0.8052 | 0.873 | 0.5996 | 0.8059 | 0.2201 | 0.6857 | -1.0 | -1.0 | 0.2289 | 0.6222 | 0.6328 | 0.7876 | 0.9 | 0.9 |
| 12.7463 | 8.0 | 400 | 9.4010 | 0.5326 | 0.6996 | 0.5913 | 0.0503 | 0.3078 | 0.5617 | 0.5723 | 0.7403 | 0.7648 | 0.3 | 0.5585 | 0.7988 | 0.8039 | 0.8773 | 0.576 | 0.7902 | 0.213 | 0.6714 | -1.0 | -1.0 | 0.2183 | 0.5958 | 0.6256 | 0.7876 | 0.7586 | 0.8667 |
| 12.3229 | 9.0 | 450 | 9.4434 | 0.5513 | 0.7262 | 0.62 | 0.0505 | 0.2788 | 0.582 | 0.5866 | 0.7457 | 0.7747 | 0.3 | 0.5642 | 0.8114 | 0.7968 | 0.8681 | 0.5797 | 0.7922 | 0.2169 | 0.7214 | -1.0 | -1.0 | 0.2352 | 0.6111 | 0.6131 | 0.7885 | 0.8663 | 0.8667 |
| 12.0052 | 10.0 | 500 | 9.4528 | 0.5391 | 0.7098 | 0.6025 | 0.0504 | 0.294 | 0.5687 | 0.5733 | 0.7379 | 0.7658 | 0.3 | 0.5784 | 0.7963 | 0.8019 | 0.873 | 0.5721 | 0.7882 | 0.2104 | 0.6714 | -1.0 | -1.0 | 0.2356 | 0.6125 | 0.6156 | 0.7832 | 0.799 | 0.8667 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
Sources
1 source
Sources
1 sourceVerified Oct 10
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
3 excerpts
Source excerpts
3 excerpts--- library_name: transformers license: apache-2.0 base_model: PekingU/rtdetr_v2_r50vd tags: - generated_from_trainer model-index: - name: rt_detrv2_finetuned_trashify_box_detector_v1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # rt_detrv2_finetuned_trashify_box_detector_v1 This model is a fine-tuned version of [PekingU/rtdetr_v2_r50vd](https://huggingface.co/PekingU/rtdetr_v2_r50vd) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 9.8777 - Map: 0.4063 - Map 50: 0.5812 - Map 75: 0.4696 - Map Small: 0.0 - Map Medium: 0.2154 - Map Large: 0.4213 - Mar 1: 0.4971 - Mar 10: 0.68 - Mar 100: 0.7186 - Mar Small: 0.0 - Mar Medium: 0.6017 - Mar Large: 0.7307 - Map Bin: 0.7693 - Mar Bin: 0.8602 - Map Hand: 0.5453 - Mar Hand: 0.7753 - Map Not Bin: 0.0821 - Mar Not Bin: 0.6455 - Map Not Hand: 0.0062 - Mar Not Hand: 0.6 - Map Not Trash: 0.1991 - Mar Not Trash: 0.5944 - Map Trash: 0.6217 - Mar Trash: 0.7833 - Map Trash Arm: 0.6203 - Mar Trash Arm: 0.7714 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 0.05 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Bin | Mar Bin | Map Hand | Mar Hand | Map Not Bin | Mar Not Bin | Map Not Hand | Mar Not Hand | Map Not Trash | Mar Not Trash | Map Trash | Mar Trash | Map Trash Arm | Mar Trash Arm | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------:|:-------:|:--------:|:--------:|:-----------:|:----...
Source context: 7 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo Starmaster7/rt_detrv2_finetuned_trashify_box_detector_v1
Source context: 19 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo Starmaster7/rt_detrv2_finetuned_trashify_box_detector_v1
