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
d6fb424
·
1 Parent(s): 8c9f77e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -55
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: 6388.8809
21
 
22
  ## Model description
23
 
@@ -42,62 +40,22 @@ The following hyperparameters were used during training:
42
  - seed: 1337
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 50.0
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 1.0 | 4 | 6398.4209 |
52
- | No log | 2.0 | 8 | 6397.8584 |
53
- | 6370.2805 | 3.0 | 12 | 6397.4790 |
54
- | 6370.2805 | 4.0 | 16 | 6396.8320 |
55
- | 6424.3547 | 5.0 | 20 | 6396.2930 |
56
- | 6424.3547 | 6.0 | 24 | 6395.7231 |
57
- | 6424.3547 | 7.0 | 28 | 6395.1377 |
58
- | 6477.4051 | 8.0 | 32 | 6394.8188 |
59
- | 6477.4051 | 9.0 | 36 | 6394.4785 |
60
- | 6381.9848 | 10.0 | 40 | 6394.2212 |
61
- | 6381.9848 | 11.0 | 44 | 6394.0664 |
62
- | 6381.9848 | 12.0 | 48 | 6393.9253 |
63
- | 6343.784 | 13.0 | 52 | 6393.7344 |
64
- | 6343.784 | 14.0 | 56 | 6393.6128 |
65
- | 6458.8668 | 15.0 | 60 | 6393.4380 |
66
- | 6458.8668 | 16.0 | 64 | 6393.2393 |
67
- | 6458.8668 | 17.0 | 68 | 6393.1040 |
68
- | 6414.077 | 18.0 | 72 | 6392.9575 |
69
- | 6414.077 | 19.0 | 76 | 6392.8301 |
70
- | 6417.8516 | 20.0 | 80 | 6392.3057 |
71
- | 6417.8516 | 21.0 | 84 | 6391.8311 |
72
- | 6417.8516 | 22.0 | 88 | 6391.5532 |
73
- | 6333.3547 | 23.0 | 92 | 6391.3403 |
74
- | 6333.3547 | 24.0 | 96 | 6391.1934 |
75
- | 6455.1539 | 25.0 | 100 | 6390.9741 |
76
- | 6455.1539 | 26.0 | 104 | 6390.8228 |
77
- | 6455.1539 | 27.0 | 108 | 6390.7607 |
78
- | 6399.7898 | 28.0 | 112 | 6390.6655 |
79
- | 6399.7898 | 29.0 | 116 | 6390.5859 |
80
- | 6410.9336 | 30.0 | 120 | 6390.4907 |
81
- | 6410.9336 | 31.0 | 124 | 6390.3389 |
82
- | 6410.9336 | 32.0 | 128 | 6390.1978 |
83
- | 6409.2 | 33.0 | 132 | 6390.0342 |
84
- | 6409.2 | 34.0 | 136 | 6389.9624 |
85
- | 6406.6211 | 35.0 | 140 | 6389.9111 |
86
- | 6406.6211 | 36.0 | 144 | 6389.6875 |
87
- | 6406.6211 | 37.0 | 148 | 6389.4756 |
88
- | 6371.1539 | 38.0 | 152 | 6389.3516 |
89
- | 6371.1539 | 39.0 | 156 | 6389.2695 |
90
- | 6409.1055 | 40.0 | 160 | 6389.2495 |
91
- | 6409.1055 | 41.0 | 164 | 6389.2090 |
92
- | 6409.1055 | 42.0 | 168 | 6389.1099 |
93
- | 6453.5285 | 43.0 | 172 | 6389.0405 |
94
- | 6453.5285 | 44.0 | 176 | 6388.9937 |
95
- | 6391.1004 | 45.0 | 180 | 6388.9541 |
96
- | 6391.1004 | 46.0 | 184 | 6388.9238 |
97
- | 6391.1004 | 47.0 | 188 | 6388.9077 |
98
- | 6416.6641 | 48.0 | 192 | 6388.8911 |
99
- | 6416.6641 | 49.0 | 196 | 6388.8828 |
100
- | 6397.6828 | 50.0 | 200 | 6388.8809 |
101
 
102
 
103
  ### 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: 5.2792
19
 
20
  ## Model description
21
 
 
40
  - seed: 1337
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 10.0
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 4 | 5.5331 |
50
+ | No log | 2.0 | 8 | 5.5277 |
51
+ | 5.4377 | 3.0 | 12 | 5.4450 |
52
+ | 5.4377 | 4.0 | 16 | 5.3960 |
53
+ | 5.1582 | 5.0 | 20 | 5.3349 |
54
+ | 5.1582 | 6.0 | 24 | 5.3144 |
55
+ | 5.1582 | 7.0 | 28 | 5.2738 |
56
+ | 5.0556 | 8.0 | 32 | 5.2641 |
57
+ | 5.0556 | 9.0 | 36 | 5.2848 |
58
+ | 4.9784 | 10.0 | 40 | 5.2792 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions