Overview
This prompt guides programmers in modifying a cWGAN-GP training script to enhance data augmentation. Developers working with unbalanced datasets will benefit from these instructions to improve model performance.
Prompt Overview
Purpose: This script modification aims to enhance the training of a cWGAN-GP model using effective image augmentations.
Audience: This update is intended for machine learning practitioners familiar with GANs and the MONAI framework.
Distinctive Feature: The new augmentation pipeline incorporates small random rotations, y-axis rotations, Gaussian noise, and contrast adjustments.
Outcome: The result will be a balanced dataset with increased sample size, improving model robustness and performance.
Quick Specs
- Media: Text
- Use case: Generation
- Industry: CRM & Sales Software, Development Tools & DevOps, Machine Learning & Data Science
- Techniques: Decomposition, Prompt Templates, Structured Output
- Models: Claude 3.5 Sonnet, Gemini 2.0 Flash, GPT-4o, Llama 3.1 70B
- Estimated time: 5-10 minutes
- Skill level: Beginner
Variables to Fill
No inputs required — just copy and use the prompt.
Example Variables Block
No example values needed for this prompt.
The Prompt
{“prompt”:”You have implemented a cWGAN-GP model that was originally trained on an unbalanced dataset. After using data augmentation for balancing, you now possess a balanced dataset and need to adjust your existing training script accordingly.nnModify your script to **remove data augmentation for balancing** purposes. Instead, implement **default image augmentation** that **increases the number of samples** by applying transformations using the MONAI framework. Ensure your augmentation pipeline includes the following transformations with appropriate parameters:nn- Small random rotations (limited degree range)n- Rotation along the y-axisn- Gaussian noise additionn- Contrast adjustmentnnUpdate all relevant code cells or script sections affected by these changes.nn# Stepsnn1. Identify parts of your script where data augmentation was applied for balancing. Remove or disable any balancing-specific augmentation logic.n2. Implement a MONAI-based augmentation pipeline applying the four transformations above:n – For rotations: apply small random rotations around relevant axes.n – For rotation along the y-axis, configure a spatial transform that achieves this.n – Add Gaussian noise with moderate variance.n – Adjust contrast slightly to augment image appearance.n3. Apply this augmentation pipeline as default to all images during data loading or training.n4. Adjust the dataset or dataloader code to ensure that the augmented dataset size increases, meaning augmentation creates additional synthetic samples beyond the original data count.n5. Test your updated script to verify the changes.nn# Output FormatnnProvide the updated script or relevant code cells with MONAI augmentation integrated as specified, along with comments clarifying changes made for the default augmentation pipeline.nn# Notesnn- Ensure compatibility with MONAI’s transforms and pipeline conventions.n- Maintain the original training logic aside from augmentation changes.n- Keep augmentation parameters moderate to avoid unrealistic distortions.nn# Response Formatsnn## promptnn{“prompt”:”[The full clear instruction and code adjustments as detailed above]”,”name”:”Adjust cWGAN-GP Augmentation”,”short_description”:”Modify cWGAN-GP training script to replace balancing augmentations with default MONAI augmentations.”,”icon”:”SparklesIcon”,”category”:”programming”,”tags”:[“Machine Learning”,”Data Augmentation”,”MONAI”,”GAN”],”should_index”:true}”}
Screenshot Examples
How to Use This Prompt
- Copy the prompt provided above.
- Identify your existing training script for cWGAN-GP.
- Remove any balancing-specific data augmentation logic.
- Implement the MONAI augmentation pipeline with specified transformations.
- Update the dataset or dataloader for increased sample size.
- Test the updated script to ensure functionality.
Tips for Best Results
- Remove Balancing Augmentation: Eliminate any data augmentation logic that was specifically used for balancing the dataset.
- Implement MONAI Pipeline: Create an augmentation pipeline using MONAI that includes small random rotations, y-axis rotation, Gaussian noise, and contrast adjustment.
- Apply Augmentation During Loading: Ensure the augmentation pipeline is applied to all images during data loading or training to increase the dataset size.
- Test Changes Thoroughly: After implementing the new augmentation, run tests to verify that the changes work as intended without affecting the original training logic.
FAQ
- What is the purpose of data augmentation in machine learning?
Data augmentation increases the diversity of training data, helping models generalize better. - How does MONAI assist in image augmentation?
MONAI provides a framework with pre-built transformations for medical imaging, simplifying augmentation processes. - What transformations should be included in the augmentation pipeline?
Include small random rotations, y-axis rotation, Gaussian noise, and contrast adjustment. - Why remove balancing-specific augmentations?
To focus on default augmentations that enhance sample diversity without biasing the dataset.
Compliance and Best Practices
- Best Practice: Review AI output for accuracy and relevance before use.
- Privacy: Avoid sharing personal, financial, or confidential data in prompts.
- Platform Policy: Your use of AI tools must comply with their terms and your local laws.
Revision History
- Version 1.0 (February 2026): Initial release.
