Elena' s AI Blog

Reverting Commits in GitHub


This post is about reverting your changes in GitHub. Sometimes it's good to step back and think about something different, right? With the use of git reset, revert and rebase we can remove changes from commits or even history. Read more...

MAC OS Speed Up


After a while, my Mac OS computer started to work slower. I have searched for possible solutions to run my computer faster without much latency. We can upgrade our computer storage and install a more powerful processor unit to speed up Mac OS. In this blog post, I will, however, focus on a more straightforward way without any system upgrades, which are costly and take time. Read more...

TensorFlow: Romancing with TensorFlow and NLP


In this post we will create a simple poem generation model with Keras Sequential API. Read more...

Collaboration in GitHub


In this post, I have covered GitHub collaboration when working with other team members. Git branching, forking, pull requests, and issues were briefly explained. Read more...

Floating-point format and Mixed Precision in TensorFlow


When creating large Machine Learning models, we want to minimise the training time. In TensorFlow, it is possible to do mixed precision model training, which helps in significant performance improvement because it uses lower-precision operations with 16 bits (such as float16) together with single-precision operations (f.i. using float32 data type). Google TPUs and NVIDIA GPUs devices can perform operations with 16-bit datatype much faster Read more...

Coding in Portugal


I am in Portugal. I live and breathe the freshness of the Ocean. Its vivid colors and wind make me happy, and I feel like a part of something bigger, omnipresent, and eternal. The springtime is the best time to be here when you like flowers and delicate fragrances loating in the air. Read more...

TensorFlow: Evaluating the Saved Bird Species Prediction Model


In this post, I have described the process of in-depth model evaluation. I have reused the previously created EffecientNetB0 model, which is fine-tuned with the 400 Bird Species Kaggle dataset. As a result, I have found out which bird species are not well predicted. Read more...

TensorFlow: Transfer Learning (Fine-Tuning) in Image Classification


We used a 400 species birds dataset for building bird species predictive models based on EffeicientNetB0 from Keras. The baseline model showed already an excellent Accuracy=0.9845. However, data augmentation did not help in improving accuracy, which slightly lowered to 0.9690. Further, this model with a data augmentation layer was partially unfrozen, retrained with a lower learning rate, and reached an Accuracy=0.9850. Read more...

Anaconda Environments


It might be challenging to manage different projects and their requirements when we do Python coding with loads of varying package versions and intricate setups. Luckily, we have a secret tool for managing and switching between different setups or environments. Conda is a package manager allowing us to work with different environments from a command line. Please do not mix it up with the Anaconda, which is helpful in scientific computing and includes a set of packages including NumPy, Scipy, Jupiter notebooks, and Conda. Read more...

TensorFlow: Transfer Learning (Feature Extraction) in Image Classification


Image classification is a complex task. However, we can approach the problem while reusing state-of-the-art pre-trained models. Using previously learned patterns from other models is named "Transfer Learning." This way, we can efficiently apply well-tested models, potentially leading to excellent performance. Read more...

1 2 3 4 5 6 7 8 9