Prerequisite Folders:

Trainer

• training_data/class

Video Encoder

• video_frames (Also created by the Trainer)

ModelOut

• input_models (Copy the architecture and weights of both the discriminator and generator.)

Styles

• image_style
• style_edit

trainer.py Hyperparameters:

• Epochs:
  • Controls the number of training iterations.
• Batch Size:
  • Determines the number of data samples processed in each training step.
• Latent Dimension:
  • Defines the size of the latent space in the generative model.
• Generation Interval:
  • Sets how often generated images are saved during training.
• Learning Rate:
  • Governs the step size during gradient descent optimization.
• Use Learning Rate Scheduler:
  • Specifies whether to use a learning rate scheduler during training.
• Random Seed:
  • Seeds the random number generator for reproducibility.

Prerequisites:

• Python 3.x
• TensorFlow (tested with TensorFlow 2.x)
• NumPy
• Matplotlib
• Pillow (PIL)
• OpenCV

Compiler:

• PyInstaller

Optional:

• A dataset of images for training (128 x 128 resolution, RGB format)

GloriosaAI - Art Showcase

Installation:

You can install the required Python packages using pip:

pip install tensorflow pip install numpy pip install matplotlib pip install Pillow pip install opencv-python pip install pyinstaller