Image Classification using Pre-Trained ImageNet Models in TensorFlow & Keras
In this article, we use ImageNet pre-trained CNN models for image classification tasks.
Mean Average Precision (mAP) in Object Detection
Mean Average Precision (mAP) is a performance metric used for evaluating machine learning models. We have covered mAP evaluation in detail to clear all your confusions regarding model evaluation metrics.
Transfer Learning for Medical Images
Our consulting company, Big Vision, has a long history of solving challenging computer vision and AI problems in diverse fields ranging from document analysis, security, manufacturing, real estate, beauty and fashion, automotive, and medical diagnostics, to name a few. The spectacular growth of AI also means that the knowledge we acquired just a year back […]
CNN Receptive Field Computation Using Backprop with TensorFlow
In our recent post about receptive field computation, we examined the concept of receptive fields using PyTorch. We learned receptive field is the proper tool to understand what the network ‘sees’ and analyze to predict the answer, whereas the scaled response map is only a rough approximation of it. Several readers of the PyTorch post […]
CNN Fully Convolutional Image Classification (FCN CNN) with TensorFlow –
In a previous post, we covered the concept of fully convolutional neural networks (FCN) in PyTorch, where we showed how we could solve the classification task using the input image of arbitrary size. We received several requests for the same post in Tensorflow (TF). By popular demand, in this post, we implement the concept using […]
