README.md

metadata

language: en
license: mit
library_name: timm
tags:
  - image-classification
  - resnet50
  - cifar10
datasets: cifar10
metrics:
  - accuracy
model-index:
  - name: resnet50_supcon_cifar10
    results:
      - task:
          type: image-classification
        dataset:
          name: CIFAR-10
          type: cifar10
        metrics:
          - type: accuracy
            value: 0.9518000000000001

Model Card for resnet50_supcon_cifar10

This model is a small resnet50 trained on cifar10.

• Test Accuracy: 0.9518000000000001
• 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_supcon_cifar10", pretrained=True)

Training Data

Training data is cifar10.

Training Hyperparameters

• config: None

• model: resnet50_supcon_cifar10

• batch_size: 512

• epochs: 501

• lr: 0.5

• warmup_epochs: 10

• validation_frequency: 50

• output_features_dim: 128

• seed: 1

• debug: False

• dataset: cifar10

• training_mode: supcon

Testing Data

Testing data is cifar10.

---

This model card was created by Eduardo Dadalto.