End of training
Browse files
README.md
CHANGED
@@ -16,6 +16,54 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# detr2
|
17 |
|
18 |
This model is a fine-tuned version of [b09501048/detr](https://huggingface.co/b09501048/detr) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -43,6 +91,22 @@ The following hyperparameters were used during training:
|
|
43 |
- num_epochs: 10
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
### Framework versions
|
47 |
|
48 |
- Transformers 4.44.2
|
|
|
16 |
# detr2
|
17 |
|
18 |
This model is a fine-tuned version of [b09501048/detr](https://huggingface.co/b09501048/detr) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.6756
|
21 |
+
- Map: 0.1051
|
22 |
+
- Map 50: 0.1903
|
23 |
+
- Map 75: 0.1015
|
24 |
+
- Map Small: 0.0033
|
25 |
+
- Map Medium: 0.0045
|
26 |
+
- Map Large: 0.118
|
27 |
+
- Mar 1: 0.0866
|
28 |
+
- Mar 10: 0.1571
|
29 |
+
- Mar 100: 0.1653
|
30 |
+
- Mar Small: 0.0035
|
31 |
+
- Mar Medium: 0.0137
|
32 |
+
- Mar Large: 0.1915
|
33 |
+
- Map Person: 0.5572
|
34 |
+
- Mar 100 Person: 0.6813
|
35 |
+
- Map Ear: 0.0504
|
36 |
+
- Mar 100 Ear: 0.2096
|
37 |
+
- Map Earmuffs: 0.0
|
38 |
+
- Mar 100 Earmuffs: 0.0
|
39 |
+
- Map Face: 0.4079
|
40 |
+
- Mar 100 Face: 0.5174
|
41 |
+
- Map Face-guard: 0.0
|
42 |
+
- Mar 100 Face-guard: 0.0
|
43 |
+
- Map Face-mask-medical: 0.0
|
44 |
+
- Mar 100 Face-mask-medical: 0.0
|
45 |
+
- Map Foot: 0.0
|
46 |
+
- Mar 100 Foot: 0.0
|
47 |
+
- Map Tools: 0.0065
|
48 |
+
- Mar 100 Tools: 0.1896
|
49 |
+
- Map Glasses: 0.0074
|
50 |
+
- Mar 100 Glasses: 0.0812
|
51 |
+
- Map Gloves: 0.0007
|
52 |
+
- Mar 100 Gloves: 0.009
|
53 |
+
- Map Helmet: 0.0
|
54 |
+
- Mar 100 Helmet: 0.0
|
55 |
+
- Map Hands: 0.2666
|
56 |
+
- Mar 100 Hands: 0.4266
|
57 |
+
- Map Head: 0.473
|
58 |
+
- Mar 100 Head: 0.5522
|
59 |
+
- Map Medical-suit: 0.0
|
60 |
+
- Mar 100 Medical-suit: 0.0
|
61 |
+
- Map Shoes: 0.0168
|
62 |
+
- Mar 100 Shoes: 0.1435
|
63 |
+
- Map Safety-suit: 0.0
|
64 |
+
- Mar 100 Safety-suit: 0.0
|
65 |
+
- Map Safety-vest: 0.0
|
66 |
+
- Mar 100 Safety-vest: 0.0
|
67 |
|
68 |
## Model description
|
69 |
|
|
|
91 |
- num_epochs: 10
|
92 |
- mixed_precision_training: Native AMP
|
93 |
|
94 |
+
### Training results
|
95 |
+
|
96 |
+
| 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 Person | Mar 100 Person | Map Ear | Mar 100 Ear | Map Earmuffs | Mar 100 Earmuffs | Map Face | Mar 100 Face | Map Face-guard | Mar 100 Face-guard | Map Face-mask-medical | Mar 100 Face-mask-medical | Map Foot | Mar 100 Foot | Map Tools | Mar 100 Tools | Map Glasses | Mar 100 Glasses | Map Gloves | Mar 100 Gloves | Map Helmet | Mar 100 Helmet | Map Hands | Mar 100 Hands | Map Head | Mar 100 Head | Map Medical-suit | Mar 100 Medical-suit | Map Shoes | Mar 100 Shoes | Map Safety-suit | Mar 100 Safety-suit | Map Safety-vest | Mar 100 Safety-vest |
|
97 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:----------:|:--------------:|:-------:|:-----------:|:------------:|:----------------:|:--------:|:------------:|:--------------:|:------------------:|:---------------------:|:-------------------------:|:--------:|:------------:|:---------:|:-------------:|:-----------:|:---------------:|:----------:|:--------------:|:----------:|:--------------:|:---------:|:-------------:|:--------:|:------------:|:----------------:|:--------------------:|:---------:|:-------------:|:---------------:|:-------------------:|:---------------:|:-------------------:|
|
98 |
+
| No log | 1.0 | 230 | 2.1829 | 0.0605 | 0.1167 | 0.0552 | 0.0009 | 0.0013 | 0.0672 | 0.0586 | 0.1154 | 0.1211 | 0.0007 | 0.0051 | 0.138 | 0.4117 | 0.609 | 0.0032 | 0.1099 | 0.0 | 0.0 | 0.1725 | 0.4168 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0001 | 0.0268 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1194 | 0.3523 | 0.3179 | 0.4968 | 0.0 | 0.0 | 0.0041 | 0.0467 | 0.0 | 0.0 | 0.0 | 0.0 |
|
99 |
+
| No log | 2.0 | 460 | 2.0866 | 0.0711 | 0.1339 | 0.0672 | 0.0013 | 0.0011 | 0.079 | 0.0641 | 0.1206 | 0.126 | 0.0018 | 0.0084 | 0.1438 | 0.454 | 0.609 | 0.0052 | 0.1209 | 0.0 | 0.0 | 0.1989 | 0.4211 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0004 | 0.0785 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1608 | 0.3471 | 0.3852 | 0.507 | 0.0 | 0.0 | 0.0038 | 0.058 | 0.0 | 0.0 | 0.0 | 0.0 |
|
100 |
+
| 2.5763 | 3.0 | 690 | 1.9861 | 0.0827 | 0.1539 | 0.0797 | 0.0009 | 0.0019 | 0.0922 | 0.0692 | 0.1281 | 0.1324 | 0.0007 | 0.0068 | 0.1522 | 0.4877 | 0.6318 | 0.0221 | 0.1291 | 0.0 | 0.0 | 0.3016 | 0.4585 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0006 | 0.0826 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1826 | 0.3567 | 0.4063 | 0.5112 | 0.0 | 0.0 | 0.0048 | 0.0814 | 0.0 | 0.0 | 0.0 | 0.0 |
|
101 |
+
| 2.5763 | 4.0 | 920 | 1.8935 | 0.0862 | 0.1625 | 0.0806 | 0.0002 | 0.0033 | 0.0962 | 0.0728 | 0.1312 | 0.136 | 0.0007 | 0.0101 | 0.1562 | 0.4722 | 0.6241 | 0.0232 | 0.1592 | 0.0 | 0.0 | 0.351 | 0.4621 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0009 | 0.1066 | 0.0004 | 0.0044 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1775 | 0.3583 | 0.4342 | 0.5186 | 0.0 | 0.0 | 0.0066 | 0.079 | 0.0 | 0.0 | 0.0 | 0.0 |
|
102 |
+
| 2.32 | 5.0 | 1150 | 1.8171 | 0.0932 | 0.1746 | 0.0899 | 0.0028 | 0.0033 | 0.1042 | 0.079 | 0.1399 | 0.1469 | 0.0028 | 0.0106 | 0.1685 | 0.4946 | 0.6561 | 0.0379 | 0.1757 | 0.0 | 0.0 | 0.3903 | 0.4897 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0011 | 0.1625 | 0.0042 | 0.0262 | 0.0004 | 0.002 | 0.0 | 0.0 | 0.1991 | 0.3702 | 0.4482 | 0.5292 | 0.0 | 0.0 | 0.009 | 0.0858 | 0.0 | 0.0 | 0.0 | 0.0 |
|
103 |
+
| 2.32 | 6.0 | 1380 | 1.7576 | 0.0981 | 0.1822 | 0.0942 | 0.0015 | 0.0038 | 0.11 | 0.0818 | 0.1474 | 0.1541 | 0.0015 | 0.0123 | 0.1785 | 0.5247 | 0.658 | 0.0522 | 0.1868 | 0.0 | 0.0 | 0.3726 | 0.499 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0083 | 0.1448 | 0.0067 | 0.06 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2357 | 0.4101 | 0.4543 | 0.5349 | 0.0 | 0.0 | 0.0125 | 0.1263 | 0.0 | 0.0 | 0.0 | 0.0 |
|
104 |
+
| 2.1983 | 7.0 | 1610 | 1.7219 | 0.1017 | 0.1871 | 0.0961 | 0.0021 | 0.0059 | 0.1138 | 0.0854 | 0.1531 | 0.1601 | 0.0024 | 0.0153 | 0.1847 | 0.547 | 0.6753 | 0.0411 | 0.207 | 0.0 | 0.0 | 0.3952 | 0.4981 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0042 | 0.1893 | 0.0108 | 0.0662 | 0.0005 | 0.0035 | 0.0 | 0.0 | 0.256 | 0.4141 | 0.4619 | 0.5478 | 0.0 | 0.0 | 0.0123 | 0.1201 | 0.0 | 0.0 | 0.0 | 0.0 |
|
105 |
+
| 2.1983 | 8.0 | 1840 | 1.7015 | 0.1025 | 0.1879 | 0.099 | 0.0028 | 0.0048 | 0.1149 | 0.0852 | 0.1556 | 0.1625 | 0.0029 | 0.0143 | 0.1884 | 0.5415 | 0.6693 | 0.0436 | 0.2041 | 0.0 | 0.0 | 0.4018 | 0.5101 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0056 | 0.1713 | 0.0086 | 0.0962 | 0.0 | 0.002 | 0.0 | 0.0 | 0.2632 | 0.4221 | 0.4633 | 0.5424 | 0.0 | 0.0 | 0.0155 | 0.1456 | 0.0 | 0.0 | 0.0 | 0.0 |
|
106 |
+
| 2.0688 | 9.0 | 2070 | 1.6853 | 0.1042 | 0.1896 | 0.0994 | 0.0033 | 0.0046 | 0.117 | 0.0862 | 0.156 | 0.1636 | 0.0033 | 0.014 | 0.1895 | 0.5507 | 0.6784 | 0.0481 | 0.206 | 0.0 | 0.0 | 0.4047 | 0.5127 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.005 | 0.1716 | 0.009 | 0.0887 | 0.0004 | 0.006 | 0.0 | 0.0 | 0.2662 | 0.4255 | 0.4697 | 0.5484 | 0.0 | 0.0 | 0.0169 | 0.1435 | 0.0 | 0.0 | 0.0 | 0.0 |
|
107 |
+
| 2.0688 | 10.0 | 2300 | 1.6756 | 0.1051 | 0.1903 | 0.1015 | 0.0033 | 0.0045 | 0.118 | 0.0866 | 0.1571 | 0.1653 | 0.0035 | 0.0137 | 0.1915 | 0.5572 | 0.6813 | 0.0504 | 0.2096 | 0.0 | 0.0 | 0.4079 | 0.5174 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0065 | 0.1896 | 0.0074 | 0.0812 | 0.0007 | 0.009 | 0.0 | 0.0 | 0.2666 | 0.4266 | 0.473 | 0.5522 | 0.0 | 0.0 | 0.0168 | 0.1435 | 0.0 | 0.0 | 0.0 | 0.0 |
|
108 |
+
|
109 |
+
|
110 |
### Framework versions
|
111 |
|
112 |
- Transformers 4.44.2
|