Edit model card

Model Card for Model ID

This model is a small resnet18 trained on svhn.

  • Test Accuracy: 0.9595113706207744
  • 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("resnet18_svhn", pretrained=True)

Training Data

Training data is svhn.

Training Hyperparameters

  • config: scripts/train_configs/svhn.json

  • model: resnet18_svhn

  • dataset: svhn

  • batch_size: 128

  • epochs: 300

  • validation_frequency: 5

  • seed: 1

  • criterion: CrossEntropyLoss

  • criterion_kwargs: {}

  • optimizer: SGD

  • lr: 0.01

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

  • scheduler: MultiStepLR

  • scheduler_kwargs: {'gamma': 0.1, 'milestones': [75, 100, 150, 225]}

  • debug: False

Testing Data

Testing data is svhn.


This model card was created by Eduardo Dadalto.

Downloads last month
89

Dataset used to train edadaltocg/resnet18_svhn

Space using edadaltocg/resnet18_svhn 1

Evaluation results