Edit model card

Model description

Simple DCGAN implementation in TensorFlow to generate CryptoPunks.

Generated samples

Project repository: CryptoGANs.


You can play with the HuggingFace space demo.

Or try it yourself

import tensorflow as tf
import matplotlib.pyplot as plt
from huggingface_hub import from_pretrained_keras

seed = 42
n_images = 36
codings_size = 100
generator = from_pretrained_keras("huggan/crypto-gan")

def generate(generator, seed):
    noise = tf.random.normal(shape=[n_images, codings_size], seed=seed)
    generated_images = generator(noise, training=False)

    fig = plt.figure(figsize=(10, 10))
    for i in range(generated_images.shape[0]):
        plt.subplot(6, 6, i+1)
        plt.imshow(generated_images[i, :, :, :])
generate(generator, seed)

Training data

For training, I used the 10000 CryptoPunks images.

Model Plot

View Model Plot

Model Image

Downloads last month
Hosted inference API

Inference API does not yet support keras models for this pipeline type.

Spaces using huggan/crypto-gan 2