README.md

metadata

language: en
license: mit
library_name: timm
tags:
  - image-classification
  - resnet34
  - svhn
datasets: svhn
metrics:
  - accuracy
model-index:
  - name: resnet34_svhn
    results:
      - task:
          type: image-classification
        dataset:
          name: SVHN
          type: svhn
        metrics:
          - type: accuracy
            value: 0.9626229256299939

Model Card for Model ID

This model is a small resnet34 trained on svhn.

• Test Accuracy: 0.9626229256299939
• 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_svhn", pretrained=True)

Training Data

Training data is svhn.

Training Hyperparameters

• config: scripts/train_configs/svhn.json

• model: resnet34_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.