conda create -n svhn --yes --file conda.txt
conda activate svhn
pip install -r requirements.txt
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% |
- Clone the source code
git clone [email protected]:MuGeminorum/SVHN-Recognition.git
cd SVHN-Recognition
- Run convert_to_lmdb.py
- Run train.py
- Run infer.py
[1] Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks