Choosing the Right Hardware Accelerator in Kaggle Notebooks
Learn how to choose between CPU, GPU, and TPU in Kaggle Notebooks to optimize training speed and manage your weekly hardware quotas effectively.
Loading…
ReadMeFeed / Community knowledge
#machine-learning
Real questions. Useful conversations. Find the people who know your stack.
kaggleEmbedding Preprocessing in Keras Models with Normalization, StringLookup, and CategoryEncoding
Learn how to embed data preprocessing directly into a Keras model using preprocessing layers, ensuring consistent transforms at training and serving time.
keras
tensorflowArchitecting Production ML Pipelines with scikit-learn ColumnTransformer
Avoid training-serving skew by using scikit-learn's Pipeline and ColumnTransformer to encapsulate preprocessing and estimation into a single, deployable object.
Reducing Kernel Overhead: Managing Tensor Lifecycles in Jeet
Learn how Jeet uses declarative computation graphs to reduce GPU kernel overhead and automate tensor lifecycle management for more efficient ML execution.
jeetAvoid Data Leakage in Scikit‑Learn: The Power of Pipelines for Preprocessing and Modeling
Learn how scikit‑learn’s Pipeline keeps preprocessing and modeling separate, prevents data leakage, and streamlines hyper‑parameter tuning. A hands‑on example shows a clean workflow from training to deployment.
scikitlearnOptimizing GPU Acceleration in Google Colab for Machine Learning
Learn how to properly configure, verify, and utilize GPU acceleration in Google Colab to speed up machine learning workloads and avoid common device placement errors.
pytorch
googlecolabSolving ML Reproducibility with Kubeflow Pipelines Caching
Stop rerunning expensive ML preprocessing steps. Learn how Kubeflow Pipelines use containerized components and caching to ensure reproducibility and save compute costs.
kubeflow
kubernetesTuning with GridSearchCV Inside a Pipeline: A Step‑by‑Step Guide
Avoid data leakage and manage runtime while hyper‑parameter tuning in scikit‑learn by embedding GridSearchCV inside a Pipeline. Follow a concrete Iris example, validate results, and learn recovery strategies.
What does model.eval() do in pytorch?
When should I use .eval() ? I understand it is supposed to allow me to "evaluate my model". How do I turn it back off for training? Example training code using .eval() .
python