edadaltocg / resnet34_supcon_cifar100

Model Card for resnet34_supcon_cifar100

This model is a small resnet34 trained on cifar100.

• Test Accuracy: 0.6740999999999999
• License: MIT

How to Get Started with the Model

Use the code below to get started with the model.

import detectors
import timm

model = timm.create_model("resnet34_supcon_cifar100", pretrained=True)

Training Data

Training data is cifar100.

Training Hyperparameters

• config : None

• model : resnet34_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

Testing data is cifar100.

This model card was created by Eduardo Dadalto.