Hugging Face's logo

davanstrien
/
test-timm

Image Classification
Transformers
TensorBoard
Safetensors
timm_wrapper
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
davanstrien HF staff commited on
Commit
885ea28
•
1 Parent(s): 7eec00c

Model save

Browse files
Files changed (2) hide show
  1. README.md +57 -14
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,10 +1,8 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: timm/resnet18.a1_in1k
5
  tags:
6
- - image-classification
7
- - vision
8
  - generated_from_trainer
9
  metrics:
10
  - accuracy
@@ -18,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # test-timm
20
 
21
- This model is a fine-tuned version of [timm/resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k) on the davanstrien/zenodo-presentations-open-labels dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.5247
24
- - Accuracy: 0.6811
25
 
26
  ## Model description
27
 
@@ -41,22 +39,67 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
- - train_batch_size: 8
45
- - eval_batch_size: 8
46
  - seed: 1337
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - num_epochs: 5.0
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.6138 | 1.0 | 180 | 0.6002 | 0.6811 |
56
- | 0.5028 | 2.0 | 360 | 0.5529 | 0.6811 |
57
- | 0.5103 | 3.0 | 540 | 0.5325 | 0.6811 |
58
- | 0.4892 | 4.0 | 720 | 0.5247 | 0.6811 |
59
- | 0.5779 | 5.0 | 900 | 0.5302 | 0.6811 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: timm/mobilenetv3_large_100.miil_in21k
5
  tags:
 
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
16
 
17
  # test-timm
18
 
19
+ This model is a fine-tuned version of [timm/mobilenetv3_large_100.miil_in21k](https://huggingface.co/timm/mobilenetv3_large_100.miil_in21k) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5000
22
+ - Accuracy: 0.7756
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
+ - train_batch_size: 64
43
+ - eval_batch_size: 64
44
  - seed: 1337
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 50.0
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.6794 | 1.0 | 23 | 0.6560 | 0.6063 |
54
+ | 0.6215 | 2.0 | 46 | 0.5833 | 0.7362 |
55
+ | 0.5784 | 3.0 | 69 | 0.5490 | 0.7598 |
56
+ | 0.5347 | 4.0 | 92 | 0.5306 | 0.7638 |
57
+ | 0.5307 | 5.0 | 115 | 0.5235 | 0.7638 |
58
+ | 0.5391 | 6.0 | 138 | 0.5090 | 0.7677 |
59
+ | 0.48 | 7.0 | 161 | 0.5108 | 0.7717 |
60
+ | 0.473 | 8.0 | 184 | 0.5028 | 0.7756 |
61
+ | 0.5014 | 9.0 | 207 | 0.5054 | 0.7717 |
62
+ | 0.496 | 10.0 | 230 | 0.5040 | 0.7717 |
63
+ | 0.4688 | 11.0 | 253 | 0.4972 | 0.7677 |
64
+ | 0.4943 | 12.0 | 276 | 0.4977 | 0.7638 |
65
+ | 0.5012 | 13.0 | 299 | 0.5057 | 0.7717 |
66
+ | 0.4639 | 14.0 | 322 | 0.5010 | 0.7717 |
67
+ | 0.4709 | 15.0 | 345 | 0.4949 | 0.7795 |
68
+ | 0.4888 | 16.0 | 368 | 0.4955 | 0.7835 |
69
+ | 0.4594 | 17.0 | 391 | 0.4986 | 0.7717 |
70
+ | 0.4745 | 18.0 | 414 | 0.5011 | 0.7677 |
71
+ | 0.4667 | 19.0 | 437 | 0.4928 | 0.7756 |
72
+ | 0.4551 | 20.0 | 460 | 0.5055 | 0.7795 |
73
+ | 0.4657 | 21.0 | 483 | 0.4928 | 0.7756 |
74
+ | 0.4818 | 22.0 | 506 | 0.5002 | 0.7756 |
75
+ | 0.4633 | 23.0 | 529 | 0.4946 | 0.7835 |
76
+ | 0.4779 | 24.0 | 552 | 0.4942 | 0.7795 |
77
+ | 0.4718 | 25.0 | 575 | 0.4963 | 0.7835 |
78
+ | 0.4511 | 26.0 | 598 | 0.5011 | 0.7717 |
79
+ | 0.4798 | 27.0 | 621 | 0.4904 | 0.7874 |
80
+ | 0.4868 | 28.0 | 644 | 0.4982 | 0.7835 |
81
+ | 0.4653 | 29.0 | 667 | 0.4988 | 0.7874 |
82
+ | 0.4613 | 30.0 | 690 | 0.4985 | 0.7795 |
83
+ | 0.4675 | 31.0 | 713 | 0.5060 | 0.7717 |
84
+ | 0.4587 | 32.0 | 736 | 0.5059 | 0.7717 |
85
+ | 0.464 | 33.0 | 759 | 0.5042 | 0.7795 |
86
+ | 0.4374 | 34.0 | 782 | 0.5063 | 0.7677 |
87
+ | 0.4864 | 35.0 | 805 | 0.5040 | 0.7677 |
88
+ | 0.4354 | 36.0 | 828 | 0.5109 | 0.7717 |
89
+ | 0.4655 | 37.0 | 851 | 0.5107 | 0.7717 |
90
+ | 0.4691 | 38.0 | 874 | 0.5093 | 0.7677 |
91
+ | 0.4826 | 39.0 | 897 | 0.5044 | 0.7717 |
92
+ | 0.4577 | 40.0 | 920 | 0.5000 | 0.7795 |
93
+ | 0.4636 | 41.0 | 943 | 0.4963 | 0.7717 |
94
+ | 0.4361 | 42.0 | 966 | 0.4958 | 0.7717 |
95
+ | 0.4534 | 43.0 | 989 | 0.5008 | 0.7795 |
96
+ | 0.4559 | 44.0 | 1012 | 0.5025 | 0.7795 |
97
+ | 0.4189 | 45.0 | 1035 | 0.5014 | 0.7756 |
98
+ | 0.4861 | 46.0 | 1058 | 0.5004 | 0.7677 |
99
+ | 0.4709 | 47.0 | 1081 | 0.5005 | 0.7795 |
100
+ | 0.4726 | 48.0 | 1104 | 0.5008 | 0.7717 |
101
+ | 0.4441 | 49.0 | 1127 | 0.4988 | 0.7756 |
102
+ | 0.4579 | 50.0 | 1150 | 0.5000 | 0.7756 |
103
 
104
 
105
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1daa255ff8ceeb6f97987b852af873d2602f29472c247e25983cc9a37fafac24
3
  size 16947712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739cd8fea5258d736167e38e97ffe40f1d6f471e4b55d039ebab90721c823827
3
  size 16947712