Home › All rules › Community › Tensorflow Deep Learning Cursor Rules
Tensorflow Deep Learning Cursor Rules
TensorFlow and deep learning rules for building, training, evaluating, and deploying neural network models
CursorAny stackCommunity (CC0)
How to use
Save this as .cursor/rules/tensorflow-deep-learning.mdc in your project, commit it, and Cursor will load it. Review it first: community files can be opinionated or out of date.
Note: Review and test before use. Provided as is, without warranty. See Terms.
.cursor/rules/tensorflow-deep-learning.mdcDownload ---
description: TensorFlow and deep learning rules for building, training, evaluating, and deploying neural network models
globs: ["**/*.py", "**/*.ipynb", "pyproject.toml", "requirements*.txt", "environment*.yml"]
alwaysApply: false
---
# TensorFlow and Deep Learning Rules
## Project Structure
- Separate data loading, model definition, training, evaluation, and serving code.
- Use `tf.data` pipelines for scalable input processing.
- Keep model hyperparameters in typed config files or dataclasses.
- Store checkpoints, logs, and exported models outside source directories.
- Keep notebooks exploratory; move repeatable training code into modules.
## Model Development
- Start with a small baseline model and a tiny overfit test before scaling.
- Use Keras layers and models unless lower-level TensorFlow APIs are required.
- Prefer explicit input shapes and named inputs/outputs.
- Use callbacks for checkpointing, early stopping, learning-rate scheduling, and TensorBoard logging.
- Use mixed precision only after validating numerical stability.
- Pin random seeds where reproducibility matters, while documenting nondeterministic GPU behavior.
## Training
- Validate data shapes, dtypes, label ranges, and class balance before training.
- Split data before augmentation or normalization fitting.
- Use validation data for tuning and a separate test set for final reporting.
- Track loss curves, metrics, learning rate, and resource use.
- Save the best checkpoint by validation metric, not by final epoch.
## Evaluation
- Report task-appropriate metrics such as AUROC, F1, calibration, perplexity, BLEU/ROUGE, or MAE/RMSE.
- Include confusion matrices or error slices for classification tasks.
- Evaluate on edge cases and distribution shifts when data allows.
- Compare against non-neural baselines when the dataset is small or tabular.
## Deployment
- Export models with clear input signatures.
- Keep preprocessing consistent between training and serving.
- Add smoke tests that load the exported model and run inference on sample inputs.
- Monitor latency, memory, prediction drift, and input schema changes.
## Common Mistakes
- Do not tune architecture before verifying labels and data quality.
- Do not leak validation data through preprocessing or augmentation.
- Do not rely on accuracy alone for imbalanced data.
- Do not deploy a notebook-only model.
- Do not ignore batch size, dtype, and device differences between training and inference.