--- library_name: transformers license: apache-2.0 base_model: PekingU/rtdetr_r50vd tags: - object-detection - vision - generated_from_trainer model-index: - name: suas-2025-rtdetr-finetuned-b16-lr3e-5 results: [] --- # suas-2025-rtdetr-finetuned-b16-lr3e-5 This model is a fine-tuned version of [PekingU/rtdetr_r50vd](https://huggingface.co/PekingU/rtdetr_r50vd) on the mfly-auton/suas-2025-synthetic-data dataset. It achieves the following results on the evaluation set: - Loss: 9.1849 - Map: 0.4811 - Map 50: 0.6742 - Map 75: 0.5153 - Map Small: 0.385 - Map Medium: 0.5129 - Map Large: 0.5739 - Mar 1: 0.5409 - Mar 10: 0.7299 - Mar 100: 0.7598 - Mar Small: 0.6142 - Mar Medium: 0.7825 - Mar Large: 0.8269 - Map Baseball-bat: 0.49 - Mar 100 Baseball-bat: 0.6707 - Map Basketball: 0.561 - Mar 100 Basketball: 0.6806 - Map Car: -1.0 - Mar 100 Car: -1.0 - Map Football: 0.3393 - Mar 100 Football: 0.6131 - Map Human: 0.7301 - Mar 100 Human: 0.9417 - Map Luggage: 0.6005 - Mar 100 Luggage: 0.8216 - Map Mattress: 0.048 - Mar 100 Mattress: 0.6785 - Map Motorcycle: 0.5833 - Mar 100 Motorcycle: 0.6382 - Map Skis: 0.8396 - Mar 100 Skis: 0.9198 - Map Snowboard: 0.6757 - Mar 100 Snowboard: 0.8016 - Map Soccer-ball: 0.3701 - Mar 100 Soccer-ball: 0.7694 - Map Stop-sign: 0.4419 - Mar 100 Stop-sign: 0.9539 - Map Tennis-racket: 0.4382 - Mar 100 Tennis-racket: 0.7518 - Map Umbrella: 0.2355 - Mar 100 Umbrella: 0.7241 - Map Volleyball: 0.382 - Mar 100 Volleyball: 0.6728 ## 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: 3e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 1337 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 10.0 - 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 Baseball-bat | Mar 100 Baseball-bat | Map Basketball | Mar 100 Basketball | Map Car | Mar 100 Car | Map Football | Mar 100 Football | Map Human | Mar 100 Human | Map Luggage | Mar 100 Luggage | Map Mattress | Mar 100 Mattress | Map Motorcycle | Mar 100 Motorcycle | Map Skis | Mar 100 Skis | Map Snowboard | Mar 100 Snowboard | Map Soccer-ball | Mar 100 Soccer-ball | Map Stop-sign | Mar 100 Stop-sign | Map Tennis-racket | Mar 100 Tennis-racket | Map Umbrella | Mar 100 Umbrella | Map Volleyball | Mar 100 Volleyball | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:----------------:|:--------------------:|:--------------:|:------------------:|:-------:|:-----------:|:------------:|:----------------:|:---------:|:-------------:|:-----------:|:---------------:|:------------:|:----------------:|:--------------:|:------------------:|:--------:|:------------:|:-------------:|:-----------------:|:---------------:|:-------------------:|:-------------:|:-----------------:|:-----------------:|:---------------------:|:------------:|:----------------:|:--------------:|:------------------:| | 23.0537 | 1.0 | 438 | 9.2431 | 0.6183 | 0.7399 | 0.7053 | 0.4862 | 0.6975 | 0.6277 | 0.698 | 0.8445 | 0.863 | 0.727 | 0.8914 | 0.9333 | 0.6135 | 0.8496 | 0.4784 | 0.7922 | -1.0 | -1.0 | 0.5092 | 0.7406 | 0.7931 | 0.9349 | 0.7264 | 0.8453 | 0.4151 | 0.9649 | 0.7746 | 0.8995 | 0.7873 | 0.9153 | 0.7978 | 0.9122 | 0.3779 | 0.6828 | 0.8549 | 0.957 | 0.6769 | 0.885 | 0.377 | 0.9438 | 0.4746 | 0.7593 | | 9.6444 | 2.0 | 876 | 8.4354 | 0.5654 | 0.6543 | 0.6454 | 0.4377 | 0.6759 | 0.6517 | 0.6178 | 0.8051 | 0.8567 | 0.7616 | 0.8748 | 0.9001 | 0.6536 | 0.8175 | 0.4753 | 0.7836 | -1.0 | -1.0 | 0.4716 | 0.7781 | 0.7632 | 0.925 | 0.7675 | 0.8975 | 0.1446 | 0.8849 | 0.7513 | 0.884 | 0.8092 | 0.8936 | 0.796 | 0.9045 | 0.1811 | 0.8046 | 0.6988 | 0.9162 | 0.734 | 0.8762 | 0.2025 | 0.8361 | 0.4669 | 0.7924 | | 7.9736 | 3.0 | 1314 | 8.1233 | 0.6032 | 0.7082 | 0.6974 | 0.4632 | 0.7302 | 0.7013 | 0.6284 | 0.8059 | 0.8518 | 0.7726 | 0.8713 | 0.8919 | 0.6745 | 0.7985 | 0.5687 | 0.8135 | -1.0 | -1.0 | 0.5098 | 0.7643 | 0.8075 | 0.917 | 0.7803 | 0.8888 | 0.1936 | 0.8645 | 0.8528 | 0.9092 | 0.8126 | 0.903 | 0.8344 | 0.8903 | 0.2384 | 0.8224 | 0.8343 | 0.9179 | 0.7266 | 0.8549 | 0.2001 | 0.7809 | 0.4116 | 0.8002 | | 7.5623 | 4.0 | 1752 | 8.0717 | 0.6264 | 0.7342 | 0.7215 | 0.5182 | 0.734 | 0.7239 | 0.651 | 0.8219 | 0.8665 | 0.7837 | 0.8706 | 0.9228 | 0.7056 | 0.8205 | 0.6522 | 0.8386 | -1.0 | -1.0 | 0.5832 | 0.8142 | 0.7739 | 0.9234 | 0.808 | 0.8942 | 0.0914 | 0.8634 | 0.8597 | 0.9093 | 0.8828 | 0.9376 | 0.8274 | 0.8924 | 0.2734 | 0.8501 | 0.8612 | 0.9209 | 0.7139 | 0.8124 | 0.2524 | 0.8567 | 0.4843 | 0.7968 | | 7.2751 | 5.0 | 2190 | 8.7630 | 0.5761 | 0.6678 | 0.6549 | 0.4548 | 0.6658 | 0.6059 | 0.6224 | 0.7803 | 0.8305 | 0.7163 | 0.8521 | 0.9175 | 0.5765 | 0.7835 | 0.5702 | 0.7898 | -1.0 | -1.0 | 0.4783 | 0.7281 | 0.7352 | 0.9097 | 0.7497 | 0.8839 | 0.0284 | 0.8625 | 0.7861 | 0.8506 | 0.8352 | 0.9277 | 0.833 | 0.8627 | 0.4065 | 0.7625 | 0.7123 | 0.9137 | 0.655 | 0.8026 | 0.2883 | 0.8388 | 0.4105 | 0.7105 | | 7.2919 | 6.0 | 2628 | 8.3399 | 0.6044 | 0.7342 | 0.6966 | 0.4756 | 0.6987 | 0.7245 | 0.6285 | 0.7863 | 0.8232 | 0.6783 | 0.8579 | 0.8962 | 0.6153 | 0.7723 | 0.5137 | 0.7211 | -1.0 | -1.0 | 0.5038 | 0.7329 | 0.8326 | 0.9302 | 0.7848 | 0.8806 | 0.0252 | 0.7449 | 0.803 | 0.8632 | 0.8442 | 0.9158 | 0.8247 | 0.8912 | 0.4423 | 0.7519 | 0.8512 | 0.9458 | 0.6717 | 0.813 | 0.3123 | 0.8643 | 0.4365 | 0.6975 | | 6.9699 | 7.0 | 3066 | 8.5778 | 0.5806 | 0.7101 | 0.6569 | 0.4371 | 0.6901 | 0.7185 | 0.6187 | 0.7898 | 0.8279 | 0.6748 | 0.865 | 0.9156 | 0.6135 | 0.7665 | 0.5259 | 0.7135 | -1.0 | -1.0 | 0.3524 | 0.6591 | 0.8118 | 0.9329 | 0.7602 | 0.8796 | 0.1264 | 0.8605 | 0.7603 | 0.8343 | 0.8279 | 0.9312 | 0.8645 | 0.9105 | 0.3614 | 0.7684 | 0.711 | 0.9377 | 0.663 | 0.8212 | 0.3093 | 0.8638 | 0.4402 | 0.7118 | | 6.7247 | 8.0 | 3504 | 8.5073 | 0.5993 | 0.7448 | 0.6827 | 0.4588 | 0.6121 | 0.7777 | 0.6438 | 0.8042 | 0.8321 | 0.6614 | 0.8377 | 0.9399 | 0.6037 | 0.7583 | 0.6004 | 0.719 | -1.0 | -1.0 | 0.4472 | 0.7137 | 0.8139 | 0.9333 | 0.7039 | 0.8694 | 0.2481 | 0.9102 | 0.8006 | 0.845 | 0.885 | 0.9599 | 0.8342 | 0.8815 | 0.398 | 0.7242 | 0.5666 | 0.9377 | 0.5825 | 0.8135 | 0.4441 | 0.8946 | 0.4621 | 0.689 | | 6.5664 | 9.0 | 3942 | 9.0973 | 0.4861 | 0.6532 | 0.5236 | 0.3138 | 0.536 | 0.6237 | 0.5459 | 0.7169 | 0.7528 | 0.5389 | 0.7868 | 0.8686 | 0.442 | 0.6763 | 0.4655 | 0.6182 | -1.0 | -1.0 | 0.3113 | 0.5423 | 0.7863 | 0.9349 | 0.6849 | 0.8274 | 0.0783 | 0.7612 | 0.6747 | 0.7367 | 0.8484 | 0.9386 | 0.7503 | 0.8272 | 0.2637 | 0.644 | 0.4794 | 0.9464 | 0.4634 | 0.7295 | 0.2248 | 0.744 | 0.3317 | 0.6123 | | 6.2978 | 10.0 | 4380 | 9.1849 | 0.4811 | 0.6742 | 0.5153 | 0.385 | 0.5129 | 0.5739 | 0.5409 | 0.7299 | 0.7598 | 0.6142 | 0.7825 | 0.8269 | 0.49 | 0.6707 | 0.561 | 0.6806 | -1.0 | -1.0 | 0.3393 | 0.6131 | 0.7301 | 0.9417 | 0.6005 | 0.8216 | 0.048 | 0.6785 | 0.5833 | 0.6382 | 0.8396 | 0.9198 | 0.6757 | 0.8016 | 0.3701 | 0.7694 | 0.4419 | 0.9539 | 0.4382 | 0.7518 | 0.2355 | 0.7241 | 0.382 | 0.6728 | ### Framework versions - Transformers 4.47.0 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.21.0