Elena' s AI Blog
  AI Python Life chatGPT Apps Git TensorFlow ML Blogging DL MAC Preprocessing NLP SEO Conda PhD Regression genAI AI Law CNN Classification Data Fine Tuning Kaggle LLM Mixed Precision RS Robots Study Transfer Learning

TensorFlow: Evaluating the Saved Bird Species Prediction Model


Elena Daehnhardt ·

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


Elena Daehnhardt ·

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


Elena Daehnhardt ·

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


Elena Daehnhardt ·

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...

TensorFlow: Convolutional Neural Networks for Image Classification


Elena Daehnhardt ·

In this post, I have demonstrated CNN usage for birds recognition using TensorFlow and Kaggle 400 birds species dataset. We observed how the model works with the original and augmented images. Read more...

TensorFlow: Multiclass Classification Model


Elena Daehnhardt ·

In Machine Learning, the classification problem is categorising input data into different classes. For instance, we can categorise email messages into two groups, spam or not spam. In this case, we have two classes, we talk about binary classification. When we have more than two classes, we talk about multiclass classification. In this post, I am going to address the latest multiclass classification, on the example of categorising clothing items into clothing types. Read more...

Feature preprocessing


Elena Daehnhardt ·

Machine Learning algorithms often require that data is in a specific type. For instance, we can use only numerical data. In other cases, ML algorithms would perform better or converge faster when we preprocess data before training the model. Since we do this step before training the model, we call it preprocessing. Read more...

TensorFlow: Evaluating the Regression Model


Elena Daehnhardt ·

In this post, we have performed the evaluation of four regression models using TensorFlow. MAE and MSE error metrics were used to compare the Sequential models while finding the best neural network architecture regarding the defined hyperparameters. Read more...

TensorFlow: Regression Model


Elena Daehnhardt ·

I have described regression modeling in TensorFlow. We have predicted a numerical value and adjusted hyperparameters to better model performance with a simple neural network. We generated a dataset, demonstrated a simple data split into training and testing sets, visualised our data and the created neural network, evaluated our model using a testing dataset. Read more...

TensorFlow: Global and Operation-level Seeds


Elena Daehnhardt ·

In training Machine Learning models, we want to avoid any ordering biases in the data. In some cases, such as in Cross-Validation experiments, it is essential to mix data and ensure that the order of data is the same between different runs or system restarts. We can use operation-level and global seeds to achieve the reproducibility of results. Read more...

1 2 3 4 5 6 7 8 9 10 11
Copyright © Elena Daehnhardt
Privacy and Terms