Hugging Face's logo

Sairii
/
rt_detrv2_finetuned_trashify_box_detector_v1

Object Detection
Transformers
Safetensors
rt_detr_v2
Generated from Trainer
Model card Files
xet
 Community
Sairii commited on
Commit
1ce2b76
·
verified ·
1 Parent(s): 9f5da35

upload finetuned RT-DETRv2 model on trashify dataset from learn HF course

Browse files
Files changed (3) hide show
  1. README.md +38 -43
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,33 +16,33 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [PekingU/rtdetr_v2_r50vd](https://huggingface.co/PekingU/rtdetr_v2_r50vd) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 9.6063
20
- - Map: 0.4202
21
- - Map 50: 0.5643
22
- - Map 75: 0.4899
23
- - Map Small: 0.0095
24
- - Map Medium: 0.3029
25
- - Map Large: 0.4355
26
- - Mar 1: 0.5092
27
- - Mar 10: 0.6884
28
- - Mar 100: 0.7205
29
- - Mar Small: 0.4
30
- - Mar Medium: 0.5065
31
- - Mar Large: 0.7431
32
- - Map Bin: 0.7335
33
- - Mar 100 Bin: 0.8657
34
- - Map Hand: 0.6106
35
- - Mar 100 Hand: 0.8076
36
- - Map Not Bin: 0.0811
37
- - Mar 100 Not Bin: 0.6
38
- - Map Not Hand: 0.0291
39
- - Mar 100 Not Hand: 0.65
40
- - Map Not Trash: 0.2454
41
- - Mar 100 Not Trash: 0.5905
42
- - Map Trash: 0.6478
43
- - Mar 100 Trash: 0.8015
44
- - Map Trash Arm: 0.5939
45
- - Mar 100 Trash Arm: 0.7286
46
 
47
  ## Model description
48
 
@@ -68,28 +68,23 @@ The following hyperparameters were used during training:
68
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
69
  - lr_scheduler_type: linear
70
  - lr_scheduler_warmup_ratio: 0.05
71
- - num_epochs: 15
72
  - mixed_precision_training: Native AMP
73
 
74
  ### Training results
75
 
76
  | 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 100 Bin | Map Hand | Mar 100 Hand | Map Not Bin | Mar 100 Not Bin | Map Not Hand | Mar 100 Not Hand | Map Not Trash | Mar 100 Not Trash | Map Trash | Mar 100 Trash | Map Trash Arm | Mar 100 Trash Arm |
77
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------:|:-----------:|:--------:|:------------:|:-----------:|:---------------:|:------------:|:----------------:|:-------------:|:-----------------:|:---------:|:-------------:|:-------------:|:-----------------:|
78
- | 73.109 | 1.0 | 99 | 16.3761 | 0.2025 | 0.2951 | 0.2222 | 0.0 | 0.083 | 0.2106 | 0.2614 | 0.4711 | 0.5388 | 0.0 | 0.3443 | 0.5724 | 0.4439 | 0.8638 | 0.2514 | 0.7373 | 0.0057 | 0.5286 | -1.0 | -1.0 | 0.0294 | 0.3792 | 0.4844 | 0.7239 | 0.0 | 0.0 |
79
- | 21.4588 | 2.0 | 198 | 11.0425 | 0.3271 | 0.4546 | 0.3652 | 0.025 | 0.2586 | 0.3518 | 0.453 | 0.6905 | 0.7228 | 0.2 | 0.5057 | 0.7537 | 0.4738 | 0.8716 | 0.3753 | 0.799 | 0.0232 | 0.5857 | -1.0 | -1.0 | 0.1787 | 0.5361 | 0.5916 | 0.7779 | 0.3202 | 0.7667 |
80
- | 17.2815 | 3.0 | 297 | 10.3873 | 0.4505 | 0.6276 | 0.5365 | 0.1 | 0.3035 | 0.4666 | 0.5181 | 0.693 | 0.7271 | 0.4 | 0.5676 | 0.7487 | 0.698 | 0.8844 | 0.576 | 0.7922 | 0.0287 | 0.5286 | -1.0 | -1.0 | 0.2276 | 0.6208 | 0.6434 | 0.7699 | 0.5293 | 0.7667 |
81
- | 15.4369 | 4.0 | 396 | 9.5297 | 0.5028 | 0.7008 | 0.5261 | 0.3 | 0.386 | 0.5323 | 0.5627 | 0.7156 | 0.7371 | 0.3 | 0.5903 | 0.7669 | 0.7475 | 0.8745 | 0.6178 | 0.7912 | 0.2095 | 0.6357 | -1.0 | -1.0 | 0.2652 | 0.6181 | 0.6425 | 0.7699 | 0.5345 | 0.7333 |
82
- | 14.0511 | 5.0 | 495 | 9.4446 | 0.519 | 0.7008 | 0.602 | 0.0072 | 0.2416 | 0.5457 | 0.5603 | 0.7243 | 0.7465 | 0.25 | 0.5176 | 0.7839 | 0.7669 | 0.8837 | 0.5966 | 0.7922 | 0.1194 | 0.5786 | -1.0 | -1.0 | 0.2912 | 0.5917 | 0.6242 | 0.7664 | 0.7158 | 0.8667 |
83
- | 13.0307 | 6.0 | 594 | 9.5485 | 0.5334 | 0.7163 | 0.6175 | 0.15 | 0.3302 | 0.5605 | 0.5721 | 0.7296 | 0.7654 | 0.3 | 0.5926 | 0.7913 | 0.763 | 0.8872 | 0.5955 | 0.7873 | 0.1516 | 0.6929 | -1.0 | -1.0 | 0.269 | 0.6194 | 0.6315 | 0.7726 | 0.7898 | 0.8333 |
84
- | 12.0963 | 7.0 | 693 | 9.6681 | 0.537 | 0.7156 | 0.6092 | 0.0012 | 0.3265 | 0.5613 | 0.5886 | 0.7319 | 0.7541 | 0.15 | 0.5381 | 0.7923 | 0.7052 | 0.8901 | 0.624 | 0.7853 | 0.1551 | 0.6143 | -1.0 | -1.0 | 0.2818 | 0.6194 | 0.623 | 0.7823 | 0.8327 | 0.8333 |
85
- | 11.1887 | 8.0 | 792 | 9.7416 | 0.511 | 0.7138 | 0.5506 | 0.3 | 0.3979 | 0.5412 | 0.5665 | 0.6879 | 0.7202 | 0.3 | 0.5273 | 0.7585 | 0.7603 | 0.8645 | 0.541 | 0.7529 | 0.1752 | 0.6214 | -1.0 | -1.0 | 0.2942 | 0.6028 | 0.5953 | 0.7796 | 0.7 | 0.7 |
86
- | 10.4979 | 9.0 | 891 | 9.9113 | 0.516 | 0.686 | 0.5753 | 0.001 | 0.382 | 0.5429 | 0.5912 | 0.7196 | 0.7534 | 0.15 | 0.5523 | 0.7931 | 0.7193 | 0.8745 | 0.5719 | 0.7578 | 0.1349 | 0.6357 | -1.0 | -1.0 | 0.2585 | 0.6125 | 0.6038 | 0.7735 | 0.8074 | 0.8667 |
87
- | 9.8326 | 10.0 | 990 | 9.8482 | 0.5222 | 0.6964 | 0.5933 | 0.0 | 0.4141 | 0.5497 | 0.602 | 0.7076 | 0.7439 | 0.0 | 0.5631 | 0.7815 | 0.7571 | 0.8745 | 0.5774 | 0.7549 | 0.1578 | 0.6357 | -1.0 | -1.0 | 0.244 | 0.5833 | 0.6228 | 0.7814 | 0.7738 | 0.8333 |
88
- | 9.3263 | 11.0 | 1089 | 10.1134 | 0.5029 | 0.681 | 0.5776 | 0.0 | 0.4336 | 0.528 | 0.5836 | 0.7118 | 0.7335 | 0.0 | 0.5557 | 0.771 | 0.757 | 0.8773 | 0.5608 | 0.7363 | 0.1587 | 0.65 | -1.0 | -1.0 | 0.2479 | 0.5667 | 0.6198 | 0.7708 | 0.673 | 0.8 |
89
- | 8.8364 | 12.0 | 1188 | 10.1116 | 0.5041 | 0.6872 | 0.5804 | 0.0 | 0.4058 | 0.5294 | 0.5995 | 0.6993 | 0.7365 | 0.0 | 0.5449 | 0.7776 | 0.7458 | 0.8652 | 0.5782 | 0.7294 | 0.1446 | 0.65 | -1.0 | -1.0 | 0.2642 | 0.5667 | 0.597 | 0.7743 | 0.6948 | 0.8333 |
90
- | 8.4023 | 13.0 | 1287 | 10.2547 | 0.5161 | 0.69 | 0.5893 | 0.0 | 0.4414 | 0.5437 | 0.6022 | 0.71 | 0.7433 | 0.0 | 0.5614 | 0.7811 | 0.7435 | 0.8596 | 0.5612 | 0.7441 | 0.1721 | 0.6429 | -1.0 | -1.0 | 0.2738 | 0.5625 | 0.6287 | 0.7841 | 0.7173 | 0.8667 |
91
- | 8.0638 | 14.0 | 1386 | 10.2899 | 0.5006 | 0.6759 | 0.5747 | 0.0 | 0.4306 | 0.5272 | 0.6042 | 0.7062 | 0.7374 | 0.0 | 0.567 | 0.7734 | 0.7356 | 0.8702 | 0.5563 | 0.7176 | 0.1454 | 0.6357 | -1.0 | -1.0 | 0.2711 | 0.5569 | 0.6031 | 0.777 | 0.6923 | 0.8667 |
92
- | 7.7476 | 15.0 | 1485 | 10.3998 | 0.5026 | 0.6781 | 0.5758 | 0.0 | 0.4216 | 0.5289 | 0.5981 | 0.7006 | 0.7332 | 0.0 | 0.5693 | 0.7701 | 0.729 | 0.8546 | 0.5561 | 0.7304 | 0.1568 | 0.6214 | -1.0 | -1.0 | 0.2656 | 0.5736 | 0.6131 | 0.7858 | 0.6948 | 0.8333 |
93
 
94
 
95
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [PekingU/rtdetr_v2_r50vd](https://huggingface.co/PekingU/rtdetr_v2_r50vd) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 9.1849
20
+ - Map: 0.4434
21
+ - Map 50: 0.5945
22
+ - Map 75: 0.5133
23
+ - Map Small: 0.0
24
+ - Map Medium: 0.2517
25
+ - Map Large: 0.4539
26
+ - Mar 1: 0.4959
27
+ - Mar 10: 0.7238
28
+ - Mar 100: 0.7536
29
+ - Mar Small: 0.0
30
+ - Mar Medium: 0.6084
31
+ - Mar Large: 0.7678
32
+ - Map Bin: 0.7782
33
+ - Mar 100 Bin: 0.882
34
+ - Map Hand: 0.5971
35
+ - Mar 100 Hand: 0.8338
36
+ - Map Not Bin: 0.1267
37
+ - Mar 100 Not Bin: 0.6091
38
+ - Map Not Hand: 0.0133
39
+ - Mar 100 Not Hand: 0.6667
40
+ - Map Not Trash: 0.2197
41
+ - Mar 100 Not Trash: 0.623
42
+ - Map Trash: 0.6299
43
+ - Mar 100 Trash: 0.8319
44
+ - Map Trash Arm: 0.7385
45
+ - Mar 100 Trash Arm: 0.8286
46
 
47
  ## Model description
48
 
 
68
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
69
  - lr_scheduler_type: linear
70
  - lr_scheduler_warmup_ratio: 0.05
71
+ - num_epochs: 10
72
  - mixed_precision_training: Native AMP
73
 
74
  ### Training results
75
 
76
  | 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 100 Bin | Map Hand | Mar 100 Hand | Map Not Bin | Mar 100 Not Bin | Map Not Hand | Mar 100 Not Hand | Map Not Trash | Mar 100 Not Trash | Map Trash | Mar 100 Trash | Map Trash Arm | Mar 100 Trash Arm |
77
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------:|:-----------:|:--------:|:------------:|:-----------:|:---------------:|:------------:|:----------------:|:-------------:|:-----------------:|:---------:|:-------------:|:-------------:|:-----------------:|
78
+ | 53.6652 | 1.0 | 99 | 12.6070 | 0.2868 | 0.426 | 0.3096 | 0.06 | 0.1591 | 0.2961 | 0.3889 | 0.5988 | 0.676 | 0.15 | 0.4608 | 0.7078 | 0.6044 | 0.8801 | 0.4455 | 0.7755 | 0.0112 | 0.5429 | -1.0 | -1.0 | 0.123 | 0.5222 | 0.5357 | 0.7354 | 0.001 | 0.6 |
79
+ | 19.3483 | 2.0 | 198 | 10.0845 | 0.3512 | 0.4978 | 0.3906 | 0.0221 | 0.1881 | 0.3675 | 0.378 | 0.5818 | 0.7372 | 0.3 | 0.5415 | 0.7631 | 0.7322 | 0.8553 | 0.5916 | 0.8059 | 0.0227 | 0.6071 | -1.0 | -1.0 | 0.1747 | 0.5639 | 0.5779 | 0.7575 | 0.0081 | 0.8333 |
80
+ | 16.3978 | 3.0 | 297 | 9.6624 | 0.4525 | 0.6069 | 0.5171 | 0.1167 | 0.3226 | 0.4676 | 0.5155 | 0.6747 | 0.7306 | 0.3 | 0.5983 | 0.7486 | 0.7497 | 0.8582 | 0.5793 | 0.8108 | 0.0369 | 0.4857 | -1.0 | -1.0 | 0.1842 | 0.6167 | 0.6207 | 0.8124 | 0.5441 | 0.8 |
81
+ | 14.6914 | 4.0 | 396 | 9.1117 | 0.4881 | 0.6719 | 0.5648 | 0.025 | 0.4183 | 0.5028 | 0.5307 | 0.7189 | 0.7619 | 0.15 | 0.642 | 0.7877 | 0.7998 | 0.883 | 0.6391 | 0.8147 | 0.093 | 0.7143 | -1.0 | -1.0 | 0.2148 | 0.6014 | 0.6111 | 0.7912 | 0.5706 | 0.7667 |
82
+ | 13.587 | 5.0 | 495 | 8.6400 | 0.4979 | 0.6803 | 0.5742 | 0.13 | 0.361 | 0.5183 | 0.5577 | 0.7337 | 0.7692 | 0.45 | 0.629 | 0.7986 | 0.8062 | 0.8908 | 0.6529 | 0.8265 | 0.1603 | 0.6714 | -1.0 | -1.0 | 0.2569 | 0.6472 | 0.6335 | 0.8124 | 0.4775 | 0.7667 |
83
+ | 12.472 | 6.0 | 594 | 8.9166 | 0.5336 | 0.7177 | 0.61 | 0.04 | 0.3907 | 0.5568 | 0.5598 | 0.7275 | 0.77 | 0.2 | 0.5852 | 0.8043 | 0.8053 | 0.8823 | 0.6221 | 0.8137 | 0.1712 | 0.7143 | -1.0 | -1.0 | 0.2475 | 0.6028 | 0.6142 | 0.8071 | 0.7411 | 0.8 |
84
+ | 11.3489 | 7.0 | 693 | 9.0591 | 0.5186 | 0.6943 | 0.5951 | 0.0014 | 0.4297 | 0.5424 | 0.5712 | 0.7099 | 0.7713 | 0.25 | 0.6119 | 0.8034 | 0.7968 | 0.8745 | 0.6237 | 0.8216 | 0.1237 | 0.6786 | -1.0 | -1.0 | 0.2614 | 0.6139 | 0.6321 | 0.8062 | 0.6738 | 0.8333 |
85
+ | 10.5027 | 8.0 | 792 | 9.1905 | 0.5222 | 0.7064 | 0.5981 | 0.0013 | 0.4192 | 0.5439 | 0.5557 | 0.7153 | 0.7746 | 0.2 | 0.5858 | 0.8092 | 0.8037 | 0.8851 | 0.5848 | 0.8039 | 0.2072 | 0.6857 | -1.0 | -1.0 | 0.2512 | 0.6292 | 0.6126 | 0.8106 | 0.6739 | 0.8333 |
86
+ | 9.7544 | 9.0 | 891 | 9.2007 | 0.5269 | 0.7186 | 0.6215 | 0.0 | 0.4556 | 0.5493 | 0.573 | 0.7131 | 0.759 | 0.0 | 0.6006 | 0.7926 | 0.8137 | 0.8773 | 0.5771 | 0.7863 | 0.1994 | 0.6643 | -1.0 | -1.0 | 0.2514 | 0.5875 | 0.6119 | 0.8053 | 0.7079 | 0.8333 |
87
+ | 9.2386 | 10.0 | 990 | 9.3179 | 0.5199 | 0.7161 | 0.6089 | 0.0028 | 0.4486 | 0.5426 | 0.562 | 0.7123 | 0.7571 | 0.05 | 0.5886 | 0.7925 | 0.8059 | 0.8738 | 0.579 | 0.7961 | 0.1759 | 0.6429 | -1.0 | -1.0 | 0.2393 | 0.5875 | 0.6114 | 0.8088 | 0.708 | 0.8333 |
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0638e3b7d4b4b5962ada4606b655e9f20a744d993f96fc336ce21a04eca51515
3
  size 171576780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ecd4fd157a4249c84378917938cc5bdf9e8761790349e520608a0238dcf6505
3
  size 171576780
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58d076c359c03c31d36e5320ea171a2b0c972bf19227849a40cda17f8236962
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089d434f475410c8e0c1e34adad716066fc742b36c99d488a8e840fa39261124
3
  size 5905