Displaying 1 to 8 from 8 results

cnn-models - ImageNet pre-trained models with batch normalization for the Caffe framework

  •    Python

This repository contains convolutional neural network (CNN) models trained on ImageNet by Marcel Simon at the Computer Vision Group Jena (CVGJ) using the Caffe framework as published in the accompanying technical report. Each model is in a separate subfolder and contains everything needed to reproduce the results. This repository focuses currently contains the batch-normalization-variants of AlexNet and VGG19 as well as the training code for Residual Networks (Resnet). No mean subtraction is required for the pre-trained models! We have a batch-normalization layer which basically does the same.

12306-captcha - 基于深度学习的12306验证码识别

  •    Python

可以根据实际情况对src/image/model/image_solver.prototxt和src/words/model/words_solver.prototxt文件进行修改.具体修改方法可参考其他模型. src/image/scripts/image_train.sh和src/image/scripts/image_finetune_train.sh脚本分别用来进行从头训练/微调训练, 训练方法可参考caffe模型训练方法.

ResNetCAM-keras - Keras implementation of a ResNet-CAM model

  •    Python

The original Matlab implementation and paper (for AlexNet, GoogLeNet, and VGG16) can be found here. A Keras implementation of VGG-CAM can be found here. This implementation is written in Keras and uses ResNet-50, which was not explored in the original paper.


  •    Jupyter

This repo also contains a notebook that shows the result of the different steps in the convolutional architectures.

model-zoo - Implementations of various Deep Learning models in PyTorch and TensorFlow.

  •    Python

This repository contains implementations of various deep learning research papers. The models are broadly categorised into the folders Generative (e.g. various generative models), NLP (e.g. various recurrent neural networks (RNNs) and natural language processing (NLP) models), Classification (e.g. various CNN models to classify images), Object Detection, Multimodal , Super resolution , 3D Computer Vision. See the READMEs of respective models for more information.

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.