Siladittya MannainThe OwlHow to save both ‘logs’ and ‘print’ statement outputs in the same file using Python?While doing one experiment, I needed to save the logs and the print statement outputs, in the same log file. Both the logs and print…Apr 11Apr 11
Siladittya MannainThe OwlThe most PyTorch way to extract output from any intermediate layer in a pre-trained modelwith a little knowledge of the model architectureApr 8Apr 8
Siladittya MannainThe OwlAutomating Ablation Studies of Deep Learning Models using Batch ScriptIn this article, we will look at a short example of how we can automate running ablation study experiments on our deep learning models…Oct 9, 2023Oct 9, 2023
Siladittya MannainThe OwlChanging the Python version on Google Colaband associated issuesSep 27, 20231Sep 27, 20231
Siladittya MannainThe OwlHosting Machine Learning Model Demos with Hugging Face Spaces and StreamlitThis article will describe the steps required to set up a demo for a machine / deep learning model on Hugging Face Spaces using Streamlit.Sep 14, 20231Sep 14, 20231
Siladittya MannainThe OwlTrain FasterRCNN faster with 16-bit precision in Detectron2One of the features of Detectron2 is that it is faster than its previous versions. Now, with the release of the wonderful library PyTorch…Sep 2, 2023Sep 2, 2023
Siladittya MannainThe OwlGuide to fine-tuning a Pre-trained model for Object Detection tasks with Faster RCNN using…In this article, we will be going through the steps needed to fine-tune a pre-trained model for object detection tasks using Faster RCNN as…Sep 1, 2023Sep 1, 2023
Siladittya MannainThe OwlThe Art of Loading Custom Objects and Functions in Kerasin the simplest possible wayAug 28, 2023Aug 28, 2023
Siladittya MannainThe OwlWeighted Categorical Cross-Entropy Loss in KerasIn this article, we will be looking at the implementation of the Weighted Categorical Cross-Entropy loss.Aug 28, 2023Aug 28, 2023
Siladittya MannainThe OwlWeighted Binary Cross-Entropy Loss in KerasWhile there are several implementations to calculate weighted binary and cross-entropy losses widely available on the web, in this article…Aug 28, 2023Aug 28, 2023