Hugging Face's logo

biglam
/
detr-resnet-50_fine_tuned_loc-2023

Object Detection
Transformers
PyTorch
TensorBoard
detr
lam
newspapers
Inference Endpoints
Model card Files Metrics Community
1
davanstrien HF staff commited on
Commit
598fe3e
·
1 Parent(s): 143b0cf

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +122 -0
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - loc_beyond_words
7
+ model-index:
8
+ - name: detr-resnet-50_fine_tuned_loc-2023
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
+ # detr-resnet-50_fine_tuned_loc-2023
16
+
17
+ This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the loc_beyond_words dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8784
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 100
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 3.731 | 0.16 | 50 | 2.6356 |
51
+ | 2.4875 | 0.31 | 100 | 2.2348 |
52
+ | 2.1786 | 0.47 | 150 | 2.1148 |
53
+ | 1.9845 | 0.62 | 200 | 1.8847 |
54
+ | 1.8507 | 0.78 | 250 | 1.8331 |
55
+ | 1.6813 | 0.94 | 300 | 1.5620 |
56
+ | 1.5613 | 1.09 | 350 | 1.5898 |
57
+ | 1.4966 | 1.25 | 400 | 1.4161 |
58
+ | 1.4831 | 1.41 | 450 | 1.4831 |
59
+ | 1.4587 | 1.56 | 500 | 1.3218 |
60
+ | 1.433 | 1.72 | 550 | 1.3529 |
61
+ | 1.33 | 1.88 | 600 | 1.2453 |
62
+ | 1.2842 | 2.03 | 650 | 1.2956 |
63
+ | 1.2807 | 2.19 | 700 | 1.1993 |
64
+ | 1.1767 | 2.34 | 750 | 1.1557 |
65
+ | 1.2134 | 2.5 | 800 | 1.1393 |
66
+ | 1.1897 | 2.66 | 850 | 1.2016 |
67
+ | 1.1784 | 2.81 | 900 | 1.1235 |
68
+ | 1.2016 | 2.97 | 950 | 1.1378 |
69
+ | 1.06 | 3.12 | 1000 | 1.0803 |
70
+ | 1.1124 | 3.28 | 1050 | 1.1145 |
71
+ | 1.1191 | 3.44 | 1100 | 1.0523 |
72
+ | 1.0819 | 3.59 | 1150 | 1.0165 |
73
+ | 1.1196 | 3.75 | 1200 | 1.0349 |
74
+ | 1.0534 | 3.91 | 1250 | 1.0441 |
75
+ | 1.0365 | 4.06 | 1300 | 1.1177 |
76
+ | 0.9853 | 4.22 | 1350 | 1.0721 |
77
+ | 0.9984 | 4.38 | 1400 | 0.9923 |
78
+ | 0.9802 | 4.53 | 1450 | 1.0079 |
79
+ | 1.04 | 4.69 | 1500 | 1.0198 |
80
+ | 1.098 | 4.84 | 1550 | 0.9788 |
81
+ | 1.079 | 5.0 | 1600 | 1.0291 |
82
+ | 1.0664 | 5.16 | 1650 | 0.9691 |
83
+ | 0.9715 | 5.31 | 1700 | 0.9380 |
84
+ | 0.9723 | 5.47 | 1750 | 1.0164 |
85
+ | 1.0019 | 5.62 | 1800 | 1.0064 |
86
+ | 0.9895 | 5.78 | 1850 | 1.0364 |
87
+ | 0.9835 | 5.94 | 1900 | 0.9848 |
88
+ | 0.994 | 6.09 | 1950 | 0.9353 |
89
+ | 0.9693 | 6.25 | 2000 | 0.9425 |
90
+ | 0.9413 | 6.41 | 2050 | 0.9173 |
91
+ | 0.9375 | 6.56 | 2100 | 0.9663 |
92
+ | 0.952 | 6.72 | 2150 | 0.8951 |
93
+ | 0.8927 | 6.88 | 2200 | 0.9099 |
94
+ | 0.8777 | 7.03 | 2250 | 0.9238 |
95
+ | 0.8976 | 7.19 | 2300 | 0.9715 |
96
+ | 0.9451 | 7.34 | 2350 | 0.9373 |
97
+ | 0.8972 | 7.5 | 2400 | 0.8959 |
98
+ | 0.9393 | 7.66 | 2450 | 1.0062 |
99
+ | 0.9 | 7.81 | 2500 | 0.8920 |
100
+ | 0.915 | 7.97 | 2550 | 0.8833 |
101
+ | 0.9018 | 8.12 | 2600 | 0.8671 |
102
+ | 0.8272 | 8.28 | 2650 | 0.9304 |
103
+ | 0.943 | 8.44 | 2700 | 0.8593 |
104
+ | 0.8667 | 8.59 | 2750 | 0.8875 |
105
+ | 0.871 | 8.75 | 2800 | 0.8457 |
106
+ | 0.9023 | 8.91 | 2850 | 0.8448 |
107
+ | 0.8733 | 9.06 | 2900 | 0.8261 |
108
+ | 0.8686 | 9.22 | 2950 | 0.8489 |
109
+ | 0.8412 | 9.38 | 3000 | 0.8244 |
110
+ | 0.8385 | 9.53 | 3050 | 0.8830 |
111
+ | 0.891 | 9.69 | 3100 | 0.8349 |
112
+ | 0.8692 | 9.84 | 3150 | 0.8672 |
113
+ | 0.8247 | 10.0 | 3200 | 0.8811 |
114
+ | 0.799 | 10.16 | 3250 | 0.8784 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - Transformers 4.27.4
120
+ - Pytorch 2.0.0+cu118
121
+ - Datasets 2.11.0
122
+ - Tokenizers 0.13.3