This model is a small resnet50 trained on cifar100.
Use the code below to get started with the model.
1import detectors
2import timm
3
4model = timm.create_model("resnet50_supcon_cifar100", pretrained=True)
Training data is cifar100.
-
config: None
-
model: resnet50_supcon_cifar100
-
batch_size: 512
-
epochs: 501
-
lr: 0.5
-
warmup_epochs: 10
-
validation_frequency: 50
-
output_features_dim: 128
-
seed: 1
-
debug: False
-
dataset: cifar100
-
training_mode: supcon
Testing data is cifar100.
This model card was created by Eduardo Dadalto.
