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

Code examples for training AlexNet using Keras and Theano

An all-in-one Deep Learning toolkit for image classification to fine-tuning pretrained models using MXNet.

From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction

Code for our paper "Generalized Orderless Pooling Performs Implicit Salient Matching" published at ICCV 2017.

Fine-tuning an already learned model, adapts the architecture to other datasets

Pretrained VGG-16 network as feature extractor for Object Recognition (Python, Keras, Scikit-Learn)

Keras implementation of multi-label classification of movie genres from IMDB posters

This repository not only contains experience about parameter finetune, but also other in-practice experience such as model ensemble (boosting, bagging and stacking) in Kaggle or other competitions.

QuickCNN is high-level library written in Python, and backed by the Keras, TensorFlow, and Scikit-learn libraries. It was developed to exercise faster experimentation with Convolutional Neural Networks(CNN). Majorly, it is intended to use the Google-Colaboratory to quickly play with the ConvNet architectures. It also allow to train on your local…

Switching from GPU to the future of Machine learning the TPU. Over 1 million images trained Resnet50 in under 20 mins compared to days or weeks on GPU and all for 0$ free on Google Colab Notebooks in Google Drive, clone repo and jump right in!!

Implementation on tensorflow fine tuning of generic CNN based model

Ongoing minor project

Mask RCNN model for instance segmentation of power cables for infrastructure inspection purposes.

Image classification using both non-DL and DL approaches. Some interesting techniques are included like SIFT-feature extraction and multiple kernel learning (MLK).

A Convolution Neural Network Model for predicting various types of food.

Using Pytorch with Django To distinguish Cats from Dogs by Fine Tuning pretrained Model.

animal is good

The provided code demonstrates transfer learning by adapting a model trained using synthetic data to classify circles, squares, and triangles to classify new shapes like stars and pentagons. By fine-tuning a pre-trained model originally designed for a different task, the repository showcases how to efficiently adapt a model to a new domain.