Skip to content
ModelListedExternal
Download

Mnist Classifier

A deliberately trivial MNIST convnet -- the champion selected by an Optuna search and registered in MLflow, exported here as TorchScript and served by revision from this repo.

Sourcehuggingface.co/rfflpllcn/mnist-classifier/tree/4f029127e5815e38ee66a578e8ef8f7c8c99a227
KindOtherVersionRevision 4f02912

Model source

Kind
Other
File size
827 KB
Version
vRevision 4f02912
Updated
Sep 28, 2026
Downloads
4
Source
Hugging Face

Source description

mnist-classifier (champion v2)

A deliberately trivial MNIST conv_net -- the champion selected by an Optuna search and registered in MLflow, exported here as TorchScript and served by revision from this repo.

  • Test accuracy: 0.9866
  • Expected calibration error (ECE): 0.0023
  • Hyperparameters: lr=0.0013292918943162175, conv_channels=16, dropout=0.07800932022121826, hidden_dim=128
  • Source MLflow run: 4863fc86bb854bd4a8644dd3d49fc216

Preprocessing: grayscale, normalize with mean 0.1307, std 0.3081 on a centred 28x28 digit. See the write-up for the full MLflow/Optuna story.

Sources

1 source
Hugging FacePrimaryVersion 4f029127e5815e38ee66a578e8ef8f7c8c99a227
huggingface.co/rfflpllcn/mnist-classifier/tree/4f029127e5815e38ee66a578e8ef8f7c8c99a227

Verified Sep 28

Model artifacts

1 artifact

model.pt

pt · 827 KB · SHA-256 acb45ff655de…1f9d · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeSep 28huggingface.co/rfflpllcn/mnist-classifier

--- license: mit tags: - image-classification - mnist - mlflow --- # mnist-classifier (champion v2) A deliberately trivial MNIST `conv_net` -- the **champion** selected by an Optuna search and registered in MLflow, exported here as TorchScript and served *by revision* from this repo. - **Test accuracy:** 0.9866 - **Expected calibration error (ECE):** 0.0023 - **Hyperparameters:** `lr=0.0013292918943162175`, `conv_channels=16`, `dropout=0.07800932022121826`, `hidden_dim=128` - **Source MLflow run:** `4863fc86bb854bd4a8644dd3d49fc216` Preprocessing: grayscale, normalize with mean `0.1307`, std `0.3081` on a centred 28x28 digit. See the write-up for the full MLflow/Optuna story.

NoteSep 28huggingface.co/rfflpllcn/mnist-classifier

Source context: 4 downloads · 0 likes · Pipeline image-classification · Repo rfflpllcn/mnist-classifier