🔻Some quick tips for #TensorFlow

some quick tips, mostly focused on performance, that reveal common pitfalls and may boost your model and #training performance to new levels. We'll start with preprocessing and your input pipeline, visit graph construction and move on to debugging and performance #optimizations.
1. Preprocessing and input pipelines
Keep #preprocessing clean and lean
2. Watch your queues
3. Graph construction and training
Finalize your graph
4. Profile your #graph
5. Watch your memory
6. #Debugging
Print is your friend
7. Set an operation execution timeout
—————————————————
link: https://www.deeplearningweekly.com/blog/tensorflow-quick-tips/

📌Via: @cedeeplearning

#deeplearning
#neuralnetworks
#machinelearning

👆🏻👆🏻 A Holistic Framework for Managing Data Analytics Projects

🔻 The six CRISP-DM steps are:

1. Business Understanding
2. Data Understanding
3. Data Preparation
4. Modeling
5. Evaluation
6. Deployment
—————————
📌Via: @cedeeplearning
📌Other social media: https://linktr.ee/cedeeplearning

link: https://www.kdnuggets.com/2020/05/framework-managing-data-analytics-projects.html

#data_management #datamining
#datascience #machinelearning
#preprocessing #agile #project

⭕️ How to Avoid Data Leakage When Performing Data Preparation

🔹A naive approach to preparing data applies the transform on the entire dataset before evaluating the performance of the model. This results in a problem referred to as data leakage, where knowledge of the hold-out test set leaks into the dataset used to train the model. This can result in an incorrect estimate of model performance when making predictions on new data.
————————
📌 Via: @cedeeplearnig

https://machinelearningmastery.com/data-preparation-without-data-leakage/

#machinelearning #AI
#neuralnetworks #deeplearning
#datascience #preprocessing
#datamining