README.md

metadata

title: Ae Gen
emoji: 💻
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 3.16.2
app_file: app.py
pinned: false
license: mit

Official release of:

• ConvAE model (from Digits that are not: Generating new types through deep neural nets)
• DeepConvAE model (from here, Section 10.1 with L=3)
• Dense K-Sparse model (from Out-of-class novelty generation)

These models were trained on MNIST only (digits), but were found to generate new kinds of symbols, see the references for more details.

Check https://huggingface.co/spaces/mehdidc/ae_gen/blob/main/README.md for more details.

Install requirements

pip install -r requirements.txt

Download models

git lfs pull

Generate samples

python cli.py test --model-path=convae.th --nb-generate=100 --folder=convae

python cli.py test --model-path=deep_convae.th --nb-generate=100 --folder=deep_convae

python cli.py test --model-path=fc_sparse.th --nb-generate=100 --folder=deep_convae

Training

python cli.py train  --dataset=mnist --folder=convae --model=convae

python cli.py train  --dataset=mnist --folder=deep_convae --model=deep_convae