metadata
tags:
- hojjatk/mnist-dataset
- handwriting-recognition
- classification
- deep-learning
metrics:
accuracy: '0.98'
precision: '0.98'
recall: '0.98'
dataset:
name: hojjatk/mnist-dataset
type: image
license: mit
downloads:
count: 0
# Handwriting Recognition Model
This is a trained model for handwriting recognition using **hojjatk/mnist-dataset** dataset.
## Usage
```python
model = torch.load("mnsit_digit_nn")
model.eval()
```
## Training Param:
epochs = 300
batch_size = 64
learning_rate = 0.001
## Model Architectue:
['(fc1): Linear(in_features=784, out_features=128, bias=True)', '(fc2): Linear(in_features=128, out_features=64, bias=True)', '(fc3): Linear(in_features=64, out_features=10, bias=True)', '(relu): ReLU()', '(dropout): Dropout(p=0.2, inplace=False)']
## Evaluation Results
- Accuracy: 0.98
- Precision: 0.98
- Recall: 0.98