edadaltocg commited on
Commit
2964102
1 Parent(s): b23bdab

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +35 -10
README.md CHANGED
@@ -24,9 +24,9 @@ model-index:
24
 
25
  # Model Card for Model ID
26
 
27
- This model is a small resnet18 trained on cifar100. It achieves the following results on the evaluation set: Accuracy: 0.7843.
28
 
29
- - **Developed by:** Eduardo Dadalto
30
  - **License:** MIT
31
 
32
  ## How to Get Started with the Model
@@ -36,25 +36,50 @@ Use the code below to get started with the model.
36
  ```python
37
  import detectors
38
  import timm
 
39
  model = timm.create_model("resnet18_cifar100", pretrained=True)
40
  ```
41
 
42
  ## Training Data
43
 
44
- <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
45
-
46
  Training data is cifar100.
47
 
48
  ## Training Hyperparameters
49
 
50
- ## Evaluation
51
 
52
- ### Testing Data
53
 
54
- <!-- This should link to a Data Card if possible. -->
55
 
56
- Testing data is cifar100.
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
- ## Results
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
- Accuracy is 0.7843.
 
24
 
25
  # Model Card for Model ID
26
 
27
+ This model is a small resnet18 trained on cifar100.
28
 
29
+ - **Test Accuracy:** 0.7843
30
  - **License:** MIT
31
 
32
  ## How to Get Started with the Model
 
36
  ```python
37
  import detectors
38
  import timm
39
+
40
  model = timm.create_model("resnet18_cifar100", pretrained=True)
41
  ```
42
 
43
  ## Training Data
44
 
 
 
45
  Training data is cifar100.
46
 
47
  ## Training Hyperparameters
48
 
 
49
 
50
+ - config: scripts/train_configs/cifar100.json
51
 
52
+ - model: resnet18_cifar100
53
 
54
+ - dataset: cifar100
55
+
56
+ - batch_size: 64
57
+
58
+ - epochs: 200
59
+
60
+ - validation_frequency: 5
61
+
62
+ - seed: 1
63
+
64
+ - criterion: CrossEntropyLoss
65
+
66
+ - criterion_kwargs: {}
67
 
68
+ - optimizer: SGD
69
+
70
+ - lr: 0.1
71
+
72
+ - optimizer_kwargs: {'momentum': 0.9, 'weight_decay': 0.0005}
73
+
74
+ - scheduler: CosineAnnealingLR
75
+
76
+ - scheduler_kwargs: {'T_max': 190}
77
+
78
+ - debug: False
79
+
80
+
81
+ ## Testing Data
82
+
83
+ Testing data is cifar100.
84
 
85
+ This model card was created by Eduardo Dadalto.