You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Do you want to train a custom convolution neural network with minimal steps and 0 coding efforts. Here is how you can train custom image classification model with minimal steps. Clone this repository and enjoy the model training sipping hot coffee.
OCR from scratch using Chars74 Dataset: http://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/ applied to the case of Spanish car license plates or any other with format NNNNAAA. The hit rate is lower than that achieved by pytesseract: in a test with 21 images, 12 hits are reached while with pytesseract the hits are 17.
Class Activation Map (CAM and Grad-CAM) Analysis of fine-tuned CNNs with transfer learning for Pokemon classification task to understand the features learned by deep CNN
Simple image classification on the IMAGENET dataset using CNNs; Recognition of handwritten digits in the MNIST dataset using feed-forward neural network; Implementation of the LENET Architecture using Pytorch