This project is a PyTorch implementation that uses deep CNN to recognize multi-digit numbers using the SVHN dataset derived from Google Street View house numbers, each picture contains a set of numbers from 0 to 9, the model is tested to have 89% accuracy.
conda create -n svhn --yes --file conda.txt
conda activate svhn
pip install -r requirements.txt
- Clone the source code:
git clone git@github.com:MuGeminorum/SVHN-Recognition.git
cd SVHN-Recognition
- Run
convert_to_lmdb.py
- Run
train.py
Steps | GPU | Batch Size | Learning Rate | Patience | Decay Step | Decay Rate | Accuracy |
---|---|---|---|---|---|---|---|
122000 | GTX 1080 Ti | 512 | 0.01 | 100 | 625 | 0.9 | 89.21% |
[1] Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks