Today I Learned,
-
Updated
Mar 21, 2019
Today I Learned,
A short evaluation of CNN architectures/papers for German Traffic Sign Recognition Benchmark (GTSRB)
Rede Neural Convolucional para predição de Dígitos Manuscritos em Python, usando o framework TensorFlow com Keras
Looking for the best parameters using a genetic algorithm
We implemented a Multi-Layer Perceptron (MLP) model from scratch and compared its performance based on image classification accuracy on the "Fashion-MNIST" dataset to the performance of the Tensorflow Keras library's Convolutional Neural Network (CNN).
Facial Keypoint Recognition in Pytorch
Use Convolutional Neural Network to learn from dataset and identify dog breeds using dog images
Deep Learning Specialization
Transformed raw text data into images with the help of Stanford developed GloVe word embeddings. Used with a custom designed ConvNet, in 1D.
Unet per la segmentazione di immagini biomediche
Implement VGG19 based NN to design Artistic-Style-Transfer Neural Net using the concept of Generative Adversial Neural Network.
Experimented with different architectures and kernels on MNIST dataset using Convolutional Neural Networks.
This project was done for the udacity deeplearning nanodegree.
Trying to code Resnet50 on pytorch and testing it on CIFAR10 dataset
Implementation of CNN (Convolutional neural network) from scratch
Find App Link below. This project involves using CNNs to predict facial landmarks on images of cat faces. It utilizes Python, OpenCV, TensorFlow, and Keras libraries for image processing, modeling, and training. The ResNet50 architecture is employed as the base model, augmented with dense layers for facial landmark prediction
The aim of this project is to implement/use pretrained popular architectures such as VGG16, VGG19, ResNet, AlexNet etc.
Add a description, image, and links to the cnn-architecture topic page so that developers can more easily learn about it.
To associate your repository with the cnn-architecture topic, visit your repo's landing page and select "manage topics."