Category Archives: Deep Learning

Upsampling, deconvolution, unpooling

This blog is inspired from my previous blog on Fully Convolutional Networks (FCN). It is important to know about upsampling, deconvolution and unpooling to fully understand FCNs. Upsampling In image processing, the process of upsampling is something, where we try to stretch up image resolution.  Traditionally, upsampling is performed using techniques like: Bi-linear interpolation Bi-cubic… Read More »

Libraries-list of python libraries for deep learning

Quick Install: List of Useful Python Libraries for Deep Learning Here is a list of Python libraries with installation commands that are very useful if you are working in deep learning, AI, Computer Vision. Run these commands in bash or shell. Note: If you are using Python virtualenv, then do not forget to activate virtualenv… Read More »

SSLError, URLError – URL fetch error occurs Keras, Python

SSLError, URLError – URL fetch error occurs Keras, Python Recently, I was trying to use pre-trained InceptionResNetV2 model in one of my project on Mac. The following error(sslerror) occurred when the program tried to download the weights of the pre-trained model: “SSLError: [SSL: TLSV1_ALERT_PROTOCOL_VERSION] tlsv1 alert protocol version (_ssl.c:645)” “URLError: <urlopen error [SSL: TLSV1_ALERT_PROTOCOL_VERSION] tlsv1… Read More »

model-how to save and load keras model ?

How to save and load keras model ? The easiest way to save and load keras model is: Save model

Load model

This technique of saving the model is very useful. This approach saves: Architecture of the model Weights of the model Training state (like loss, optimizer etc.) State of the optimizer, which… Read More »