Scripts:
- main.py: The selection menu for GloriosaAI
/scripts/
- trainer.py: Runs GloriosaAI trainer
- modelout.py: Output images from trained models with GloriosaAI
- video_encoder.py: Encode a video using GloriosaAI
- image-processor.py: Prepare images for GloriosaAI
- preprocessor_data.py: Dependency for GloriosaAI
- install_dependencies.py: Install dependencies
Prerequisite Folders:
Trainer
training_data/class
Video Encoder
output/video_frames(Also created by the Trainer)
ModelOut
input/input_models(Copy the architecture and weights of both the discriminator and generator.)
Image-Processor
unprocessed_images
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:
- TensorFlow 2.14.0
- Numpy 1.26.2
- Matplotlib 3.8.2
- Pillow 10.1.0
- OpenCV-Python 4.8.1.78
- Flask==2.1.1
Compiler:
- PyInstaller
Optional:
- A dataset of images for training (128 x 128 resolution, RGB format)
How to Run:
pip install -r requirements.txt
pip install opencv-contrib-python
For GPU
nvidia-smi pip install --upgrade pip pip install --extra-index-url https://pypi.nvidia.com tensorrt-bindings==8.6.1 tensorrt-libs==8.6.1 pip install -U tensorflow[and-cuda]
For CPU
Additional Packages
pip install numpy pip install matplotlib pip install Pillow pip install opencv-python pip install pyinstaller pip install flask
To make the setup script executable, run the following command in your terminal:
Cursed Entertainment 2024
