Hugging Face's logo

mfly-auton
/
suas-2025-rtdetr-finetuned-e10-b32-lr1e-5

Object Detection
Transformers
Safetensors
rt_detr
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
emvisee commited on
Commit
bab1b34
·
verified ·
1 Parent(s): 262a75f

Model save

Browse files
Files changed (5) hide show
  1. README.md +110 -0
  2. config.json +125 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +29 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: PekingU/rtdetr_r50vd
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: suas-2025-rtdetr-finetuned-e10-b32-lr1e-5
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # suas-2025-rtdetr-finetuned-e10-b32-lr1e-5
16
+
17
+ This model is a fine-tuned version of [PekingU/rtdetr_r50vd](https://huggingface.co/PekingU/rtdetr_r50vd) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 5.7755
20
+ - Map: 0.8259
21
+ - Map 50: 0.9053
22
+ - Map 75: 0.8962
23
+ - Map Small: 0.7396
24
+ - Map Medium: 0.8978
25
+ - Map Large: 0.8904
26
+ - Mar 1: 0.7897
27
+ - Mar 10: 0.9079
28
+ - Mar 100: 0.911
29
+ - Mar Small: 0.8045
30
+ - Mar Medium: 0.9449
31
+ - Mar Large: 0.974
32
+ - Map Baseball-bat: 0.8535
33
+ - Mar 100 Baseball-bat: 0.9223
34
+ - Map Basketball: 0.8181
35
+ - Mar 100 Basketball: 0.9213
36
+ - Map Car: -1.0
37
+ - Mar 100 Car: -1.0
38
+ - Map Football: 0.4419
39
+ - Mar 100 Football: 0.516
40
+ - Map Human: 0.8513
41
+ - Mar 100 Human: 0.9473
42
+ - Map Luggage: 0.8768
43
+ - Mar 100 Luggage: 0.9398
44
+ - Map Mattress: 0.5281
45
+ - Mar 100 Mattress: 0.9959
46
+ - Map Motorcycle: 0.9311
47
+ - Mar 100 Motorcycle: 0.9635
48
+ - Map Skis: 0.9687
49
+ - Mar 100 Skis: 0.9975
50
+ - Map Snowboard: 0.9779
51
+ - Mar 100 Snowboard: 0.9953
52
+ - Map Soccer-ball: 0.8253
53
+ - Mar 100 Soccer-ball: 0.8679
54
+ - Map Stop-sign: 0.9582
55
+ - Mar 100 Stop-sign: 0.9838
56
+ - Map Tennis-racket: 0.8887
57
+ - Mar 100 Tennis-racket: 0.9275
58
+ - Map Umbrella: 0.8417
59
+ - Mar 100 Umbrella: 0.9128
60
+ - Map Volleyball: 0.8015
61
+ - Mar 100 Volleyball: 0.8632
62
+
63
+ ## Model description
64
+
65
+ More information needed
66
+
67
+ ## Intended uses & limitations
68
+
69
+ More information needed
70
+
71
+ ## Training and evaluation data
72
+
73
+ More information needed
74
+
75
+ ## Training procedure
76
+
77
+ ### Training hyperparameters
78
+
79
+ The following hyperparameters were used during training:
80
+ - learning_rate: 1e-05
81
+ - train_batch_size: 32
82
+ - eval_batch_size: 32
83
+ - seed: 1337
84
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
85
+ - lr_scheduler_type: linear
86
+ - num_epochs: 10.0
87
+ - mixed_precision_training: Native AMP
88
+
89
+ ### Training results
90
+
91
+ | 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 |
92
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:----------------:|:--------------------:|:--------------:|:------------------:|:-------:|:-----------:|:------------:|:----------------:|:---------:|:-------------:|:-----------:|:---------------:|:------------:|:----------------:|:--------------:|:------------------:|:--------:|:------------:|:-------------:|:-----------------:|:---------------:|:-------------------:|:-------------:|:-----------------:|:-----------------:|:---------------------:|:------------:|:----------------:|:--------------:|:------------------:|
93
+ | 31.6046 | 1.0 | 219 | 12.5434 | 0.3553 | 0.4457 | 0.3805 | 0.2717 | 0.4559 | 0.4479 | 0.5615 | 0.7432 | 0.7718 | 0.5413 | 0.873 | 0.9496 | 0.6878 | 0.9023 | 0.0337 | 0.5289 | -1.0 | -1.0 | 0.1746 | 0.4829 | 0.4718 | 0.8344 | 0.1939 | 0.8512 | 0.139 | 0.9643 | 0.5451 | 0.9288 | 0.9133 | 0.9891 | 0.4051 | 0.9817 | 0.3034 | 0.4481 | 0.3931 | 0.9455 | 0.3464 | 0.615 | 0.2395 | 0.8765 | 0.1274 | 0.4561 |
94
+ | 11.2376 | 2.0 | 438 | 8.7086 | 0.7492 | 0.8518 | 0.8382 | 0.6809 | 0.8229 | 0.7802 | 0.7521 | 0.8824 | 0.8898 | 0.7682 | 0.9257 | 0.9652 | 0.8225 | 0.9069 | 0.7335 | 0.8417 | -1.0 | -1.0 | 0.5246 | 0.6187 | 0.8272 | 0.9075 | 0.8351 | 0.91 | 0.2917 | 0.9978 | 0.8814 | 0.9449 | 0.9763 | 0.9916 | 0.9795 | 0.9963 | 0.7605 | 0.8211 | 0.9176 | 0.9746 | 0.8631 | 0.9088 | 0.4335 | 0.9109 | 0.6428 | 0.7265 |
95
+ | 7.5378 | 3.0 | 657 | 7.5895 | 0.7926 | 0.8861 | 0.874 | 0.7165 | 0.8732 | 0.8452 | 0.7772 | 0.8976 | 0.9033 | 0.7944 | 0.9368 | 0.9808 | 0.8325 | 0.9096 | 0.7675 | 0.8908 | -1.0 | -1.0 | 0.5341 | 0.6171 | 0.8536 | 0.9323 | 0.8621 | 0.9288 | 0.3232 | 0.9995 | 0.9099 | 0.9534 | 0.9589 | 0.9851 | 0.9779 | 0.9968 | 0.7949 | 0.8422 | 0.9557 | 0.9799 | 0.874 | 0.9187 | 0.7466 | 0.908 | 0.7061 | 0.7833 |
96
+ | 6.7821 | 4.0 | 876 | 6.9548 | 0.7906 | 0.8773 | 0.8662 | 0.6944 | 0.8658 | 0.8692 | 0.7707 | 0.8882 | 0.8931 | 0.763 | 0.9347 | 0.9677 | 0.8386 | 0.9153 | 0.738 | 0.8742 | -1.0 | -1.0 | 0.4264 | 0.5058 | 0.83 | 0.9254 | 0.8657 | 0.9297 | 0.4204 | 0.9995 | 0.9153 | 0.9537 | 0.955 | 0.9891 | 0.9727 | 0.9924 | 0.8047 | 0.8542 | 0.9495 | 0.9869 | 0.8817 | 0.9254 | 0.7954 | 0.8976 | 0.6753 | 0.7549 |
97
+ | 6.4517 | 5.0 | 1095 | 6.2876 | 0.8217 | 0.9052 | 0.8965 | 0.7345 | 0.8867 | 0.884 | 0.7885 | 0.9066 | 0.9107 | 0.8055 | 0.9448 | 0.9705 | 0.8384 | 0.92 | 0.7994 | 0.9156 | -1.0 | -1.0 | 0.4948 | 0.5703 | 0.8404 | 0.9363 | 0.8765 | 0.9391 | 0.5335 | 0.9946 | 0.927 | 0.9651 | 0.9504 | 0.995 | 0.9766 | 0.9947 | 0.8183 | 0.8602 | 0.946 | 0.9813 | 0.8881 | 0.9259 | 0.8387 | 0.9205 | 0.7759 | 0.8306 |
98
+ | 6.1454 | 6.0 | 1314 | 5.8688 | 0.8355 | 0.9186 | 0.9086 | 0.7416 | 0.8939 | 0.9026 | 0.7975 | 0.91 | 0.9135 | 0.8094 | 0.9477 | 0.973 | 0.8577 | 0.9237 | 0.7904 | 0.9206 | -1.0 | -1.0 | 0.4838 | 0.5638 | 0.8723 | 0.9423 | 0.8782 | 0.9378 | 0.6114 | 0.9982 | 0.9296 | 0.9638 | 0.9826 | 0.9965 | 0.9772 | 0.9953 | 0.8218 | 0.8638 | 0.9541 | 0.9866 | 0.887 | 0.9285 | 0.851 | 0.9228 | 0.7993 | 0.8458 |
99
+ | 6.0567 | 7.0 | 1533 | 5.9641 | 0.8278 | 0.9084 | 0.9005 | 0.7434 | 0.8944 | 0.89 | 0.7917 | 0.9098 | 0.9135 | 0.8091 | 0.9467 | 0.9854 | 0.8531 | 0.9224 | 0.7819 | 0.9187 | -1.0 | -1.0 | 0.4727 | 0.5437 | 0.8434 | 0.9498 | 0.8774 | 0.9406 | 0.5438 | 0.9946 | 0.9232 | 0.963 | 0.9791 | 0.998 | 0.9771 | 0.994 | 0.8241 | 0.8707 | 0.9609 | 0.9785 | 0.8909 | 0.9264 | 0.8533 | 0.9254 | 0.8084 | 0.863 |
100
+ | 5.9579 | 8.0 | 1752 | 5.7184 | 0.8339 | 0.9141 | 0.9056 | 0.7448 | 0.8939 | 0.9004 | 0.7947 | 0.9099 | 0.9136 | 0.8088 | 0.9453 | 0.9871 | 0.8529 | 0.9222 | 0.8083 | 0.9175 | -1.0 | -1.0 | 0.4795 | 0.5478 | 0.8608 | 0.9444 | 0.8795 | 0.9406 | 0.5759 | 0.998 | 0.9325 | 0.9641 | 0.9711 | 0.9975 | 0.9816 | 0.9964 | 0.8218 | 0.8661 | 0.9655 | 0.9872 | 0.8942 | 0.928 | 0.8474 | 0.9251 | 0.8034 | 0.8551 |
101
+ | 5.9419 | 9.0 | 1971 | 5.7328 | 0.8305 | 0.9091 | 0.9018 | 0.7434 | 0.8955 | 0.8956 | 0.7924 | 0.9098 | 0.9136 | 0.8101 | 0.9462 | 0.9868 | 0.858 | 0.9253 | 0.8223 | 0.9197 | -1.0 | -1.0 | 0.4625 | 0.5377 | 0.8502 | 0.9471 | 0.8804 | 0.9409 | 0.5395 | 0.9939 | 0.93 | 0.9619 | 0.9787 | 0.9975 | 0.979 | 0.9959 | 0.8296 | 0.8704 | 0.9624 | 0.988 | 0.8852 | 0.9269 | 0.8393 | 0.9164 | 0.8101 | 0.8684 |
102
+ | 5.9176 | 10.0 | 2190 | 5.7755 | 0.8259 | 0.9053 | 0.8962 | 0.7396 | 0.8978 | 0.8904 | 0.7897 | 0.9079 | 0.911 | 0.8045 | 0.9449 | 0.974 | 0.8535 | 0.9223 | 0.8181 | 0.9213 | -1.0 | -1.0 | 0.4419 | 0.516 | 0.8513 | 0.9473 | 0.8768 | 0.9398 | 0.5281 | 0.9959 | 0.9311 | 0.9635 | 0.9687 | 0.9975 | 0.9779 | 0.9953 | 0.8253 | 0.8679 | 0.9582 | 0.9838 | 0.8887 | 0.9275 | 0.8417 | 0.9128 | 0.8015 | 0.8632 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.47.0
108
+ - Pytorch 2.5.1+cu124
109
+ - Datasets 3.1.0
110
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PekingU/rtdetr_r50vd",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "silu",
5
+ "anchor_image_size": null,
6
+ "architectures": [
7
+ "RTDetrForObjectDetection"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "auxiliary_loss": true,
11
+ "backbone": null,
12
+ "backbone_config": {
13
+ "model_type": "rt_detr_resnet",
14
+ "out_features": [
15
+ "stage2",
16
+ "stage3",
17
+ "stage4"
18
+ ],
19
+ "out_indices": [
20
+ 2,
21
+ 3,
22
+ 4
23
+ ]
24
+ },
25
+ "backbone_kwargs": null,
26
+ "batch_norm_eps": 1e-05,
27
+ "box_noise_scale": 1.0,
28
+ "d_model": 256,
29
+ "decoder_activation_function": "relu",
30
+ "decoder_attention_heads": 8,
31
+ "decoder_ffn_dim": 1024,
32
+ "decoder_in_channels": [
33
+ 256,
34
+ 256,
35
+ 256
36
+ ],
37
+ "decoder_layers": 6,
38
+ "decoder_n_points": 4,
39
+ "disable_custom_kernels": true,
40
+ "dropout": 0.0,
41
+ "encode_proj_layers": [
42
+ 2
43
+ ],
44
+ "encoder_activation_function": "gelu",
45
+ "encoder_attention_heads": 8,
46
+ "encoder_ffn_dim": 1024,
47
+ "encoder_hidden_dim": 256,
48
+ "encoder_in_channels": [
49
+ 512,
50
+ 1024,
51
+ 2048
52
+ ],
53
+ "encoder_layers": 1,
54
+ "eos_coefficient": 0.0001,
55
+ "eval_size": null,
56
+ "feat_strides": [
57
+ 8,
58
+ 16,
59
+ 32
60
+ ],
61
+ "focal_loss_alpha": 0.75,
62
+ "focal_loss_gamma": 2.0,
63
+ "freeze_backbone_batch_norms": true,
64
+ "hidden_expansion": 1.0,
65
+ "id2label": {
66
+ "0": "baseball-bat",
67
+ "1": "basketball",
68
+ "2": "car",
69
+ "3": "football",
70
+ "4": "human",
71
+ "5": "luggage",
72
+ "6": "mattress",
73
+ "7": "motorcycle",
74
+ "8": "skis",
75
+ "9": "snowboard",
76
+ "10": "soccer-ball",
77
+ "11": "stop-sign",
78
+ "12": "tennis-racket",
79
+ "13": "umbrella",
80
+ "14": "volleyball"
81
+ },
82
+ "initializer_bias_prior_prob": null,
83
+ "initializer_range": 0.01,
84
+ "is_encoder_decoder": true,
85
+ "label2id": {
86
+ "baseball-bat": 0,
87
+ "basketball": 1,
88
+ "car": 2,
89
+ "football": 3,
90
+ "human": 4,
91
+ "luggage": 5,
92
+ "mattress": 6,
93
+ "motorcycle": 7,
94
+ "skis": 8,
95
+ "snowboard": 9,
96
+ "soccer-ball": 10,
97
+ "stop-sign": 11,
98
+ "tennis-racket": 12,
99
+ "umbrella": 13,
100
+ "volleyball": 14
101
+ },
102
+ "label_noise_ratio": 0.5,
103
+ "layer_norm_eps": 1e-05,
104
+ "learn_initial_query": false,
105
+ "matcher_alpha": 0.25,
106
+ "matcher_bbox_cost": 5.0,
107
+ "matcher_class_cost": 2.0,
108
+ "matcher_gamma": 2.0,
109
+ "matcher_giou_cost": 2.0,
110
+ "model_type": "rt_detr",
111
+ "normalize_before": false,
112
+ "num_denoising": 100,
113
+ "num_feature_levels": 3,
114
+ "num_queries": 300,
115
+ "positional_encoding_temperature": 10000,
116
+ "torch_dtype": "float32",
117
+ "transformers_version": "4.47.0",
118
+ "use_focal_loss": true,
119
+ "use_pretrained_backbone": false,
120
+ "use_timm_backbone": false,
121
+ "weight_loss_bbox": 5.0,
122
+ "weight_loss_giou": 2.0,
123
+ "weight_loss_vfl": 1.0,
124
+ "with_box_refine": true
125
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75846f1380cd90ff0822a9c2fe7ff4dc829e14a1b1c87361c0c8bb43a2e55acc
3
+ size 171641556
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_annotations": true,
3
+ "do_normalize": false,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "format": "coco_detection",
8
+ "image_mean": [
9
+ 0.485,
10
+ 0.456,
11
+ 0.406
12
+ ],
13
+ "image_processor_type": "RTDetrImageProcessor",
14
+ "image_std": [
15
+ 0.229,
16
+ 0.224,
17
+ 0.225
18
+ ],
19
+ "pad_size": {
20
+ "height": 640,
21
+ "width": 640
22
+ },
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "max_height": 640,
27
+ "max_width": 640
28
+ }
29
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f822e0d298d5150496b9a16ab7cf1a1d7fcdc1dda77b1e5340f66ab32b8bb51
3
+ size 5432