edadaltocg/resnet50_cifar100

Model Card for Model ID

This model is a small resnet50 trained on cifar100.

• —Test Accuracy: 0.8093
• —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("resnet50_cifar100", pretrained=True)

Training Data

Training data is cifar100.

Training Hyperparameters

• —config: scripts/train_configs/cifar100.json

• —model: resnet50_cifar100

• —dataset: cifar100

• —batch_size: 128

• —epochs: 300

• —validation_frequency: 5

• —seed: 1

• —criterion: CrossEntropyLoss

• —criterion_kwargs: {}

• —optimizer: SGD

• —lr: 0.1

• —optimizer_kwargs: {'momentum': 0.9, 'weight_decay': 0.0005}

• —scheduler: CosineAnnealingLR

• —scheduler_kwargs: {'T_max': 280}

• —debug: False

Testing Data

Testing data is cifar100.

This model card was created by Eduardo Dadalto.