Downloads · 30 days
0
photo-to-monet-cyclegan
blah7/photo-to-monet-cyclegan
photo-to-monet-cyclegan is a machine learning model from blah7. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for tf-keras.
Trained for 237 epochs on Kaggle GAN dataset.
Access
Public
Updated Nov 16, 2025
Repo size
287 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data-00000-of-00001286 MB · 100%
At a glance
- Library
- tf-keras
- Access
- Public
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025
- SHA
- e2181cbd
Model card
From the Hugging Face model README
Photo-to-Monet CycleGAN
Trained for 237 epochs on Kaggle GAN dataset.
For Continued Training
- Recreate models/optimizers under strategy.scope() (from Cells 1-5).
- Define custom layers (Cell 4).
- Load:
ckpt.restore(tf.train.latest_checkpoint('./checkpoints')) - Resume:
train(train_ds, epochs=additional_epochs)
For Inference
- Use SavedModel:
loaded_G = tf.saved_model.load('savedmodel_G'); output = loaded_G(input_tensor) - Preprocess: Resize to 256x256, normalize to [-1,1].
- Or load from checkpoint and call
G.predict().
Requirements
- TensorFlow >=2.0
- Custom layers: See original notebook Cells 1-4.
- Library
- tf-keras
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025