Hugging Face's logo

amyeroberts
/
detr-resnet-50-base-coco

Object Detection
Transformers
PyTorch
TensorBoard
detr
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
amyeroberts HF staff commited on
Commit
0afc0f8
•
1 Parent(s): 8dd5208

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +54 -26
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: facebook/detr-resnet-50
4
  tags:
5
- - object-detection
6
- - vision
7
  - generated_from_trainer
8
  model-index:
9
  - name: detr-resnet-50-base-coco
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # detr-resnet-50-base-coco
17
 
18
- This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the detection-datasets/coco dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 6395.9458
21
 
22
  ## Model description
23
 
@@ -36,38 +34,68 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 1e-05
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 1337
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 20.0
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 1.0 | 4 | 6398.7773 |
52
- | No log | 2.0 | 8 | 6398.4355 |
53
- | 6176.0926 | 3.0 | 12 | 6398.2266 |
54
- | 6176.0926 | 4.0 | 16 | 6397.8564 |
55
- | 6292.8656 | 5.0 | 20 | 6397.6299 |
56
- | 6292.8656 | 6.0 | 24 | 6397.3179 |
57
- | 6292.8656 | 7.0 | 28 | 6396.9526 |
58
- | 6231.0688 | 8.0 | 32 | 6396.7905 |
59
- | 6231.0688 | 9.0 | 36 | 6396.6748 |
60
- | 6090.4715 | 10.0 | 40 | 6396.5957 |
61
- | 6090.4715 | 11.0 | 44 | 6396.5347 |
62
- | 6090.4715 | 12.0 | 48 | 6396.4106 |
63
- | 6268.359 | 13.0 | 52 | 6396.3232 |
64
- | 6268.359 | 14.0 | 56 | 6396.2344 |
65
- | 6384.7945 | 15.0 | 60 | 6396.0957 |
66
- | 6384.7945 | 16.0 | 64 | 6396.0903 |
67
- | 6384.7945 | 17.0 | 68 | 6396.0029 |
68
- | 6325.7992 | 18.0 | 72 | 6395.9458 |
69
- | 6325.7992 | 19.0 | 76 | 6395.9780 |
70
- | 6265.4016 | 20.0 | 80 | 6395.9766 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: facebook/detr-resnet-50
4
  tags:
 
 
5
  - generated_from_trainer
6
  model-index:
7
  - name: detr-resnet-50-base-coco
 
13
 
14
  # detr-resnet-50-base-coco
15
 
16
+ This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 6388.0923
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 1337
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 50.0
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 4 | 6397.6270 |
50
+ | No log | 2.0 | 8 | 6396.9526 |
51
+ | 6175.4402 | 3.0 | 12 | 6396.9136 |
52
+ | 6175.4402 | 4.0 | 16 | 6396.2993 |
53
+ | 6291.4262 | 5.0 | 20 | 6395.5557 |
54
+ | 6291.4262 | 6.0 | 24 | 6394.5957 |
55
+ | 6291.4262 | 7.0 | 28 | 6393.7290 |
56
+ | 6228.9867 | 8.0 | 32 | 6393.1914 |
57
+ | 6228.9867 | 9.0 | 36 | 6392.2837 |
58
+ | 6087.3184 | 10.0 | 40 | 6391.6709 |
59
+ | 6087.3184 | 11.0 | 44 | 6390.7271 |
60
+ | 6087.3184 | 12.0 | 48 | 6389.6670 |
61
+ | 6263.3945 | 13.0 | 52 | 6389.4907 |
62
+ | 6263.3945 | 14.0 | 56 | 6388.8540 |
63
+ | 6378.8203 | 15.0 | 60 | 6388.6978 |
64
+ | 6378.8203 | 16.0 | 64 | 6388.6611 |
65
+ | 6378.8203 | 17.0 | 68 | 6388.5430 |
66
+ | 6319.1008 | 18.0 | 72 | 6388.4219 |
67
+ | 6319.1008 | 19.0 | 76 | 6388.5059 |
68
+ | 6258.6707 | 20.0 | 80 | 6388.3950 |
69
+ | 6258.6707 | 21.0 | 84 | 6388.3042 |
70
+ | 6258.6707 | 22.0 | 88 | 6388.2788 |
71
+ | 6290.5227 | 23.0 | 92 | 6388.2700 |
72
+ | 6290.5227 | 24.0 | 96 | 6388.3994 |
73
+ | 6450.2746 | 25.0 | 100 | 6388.4180 |
74
+ | 6450.2746 | 26.0 | 104 | 6388.2329 |
75
+ | 6450.2746 | 27.0 | 108 | 6388.3062 |
76
+ | 6321.6988 | 28.0 | 112 | 6388.2568 |
77
+ | 6321.6988 | 29.0 | 116 | 6388.1333 |
78
+ | 6468.3922 | 30.0 | 120 | 6388.1660 |
79
+ | 6468.3922 | 31.0 | 124 | 6388.1528 |
80
+ | 6468.3922 | 32.0 | 128 | 6388.1211 |
81
+ | 6305.5602 | 33.0 | 132 | 6388.0972 |
82
+ | 6305.5602 | 34.0 | 136 | 6388.0776 |
83
+ | 6349.5672 | 35.0 | 140 | 6388.0493 |
84
+ | 6349.5672 | 36.0 | 144 | 6388.0317 |
85
+ | 6349.5672 | 37.0 | 148 | 6388.0259 |
86
+ | 6244.9891 | 38.0 | 152 | 6388.0371 |
87
+ | 6244.9891 | 39.0 | 156 | 6388.0273 |
88
+ | 6383.7191 | 40.0 | 160 | 6388.1465 |
89
+ | 6383.7191 | 41.0 | 164 | 6388.2505 |
90
+ | 6383.7191 | 42.0 | 168 | 6388.1260 |
91
+ | 6260.3203 | 43.0 | 172 | 6388.0518 |
92
+ | 6260.3203 | 44.0 | 176 | 6388.0322 |
93
+ | 6254.6055 | 45.0 | 180 | 6388.0625 |
94
+ | 6254.6055 | 46.0 | 184 | 6388.0688 |
95
+ | 6254.6055 | 47.0 | 188 | 6388.0601 |
96
+ | 6351.991 | 48.0 | 192 | 6388.0825 |
97
+ | 6351.991 | 49.0 | 196 | 6388.0938 |
98
+ | 6209.7984 | 50.0 | 200 | 6388.0923 |
99
 
100
 
101
  ### Framework versions