MEAL V2: Boosting Vanilla ResNet-50 to 80% Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.
-
Updated
Dec 24, 2021 - Python
MEAL V2: Boosting Vanilla ResNet-50 to 80% Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.
This repository contains the source code of our work on designing efficient CNNs for computer vision
Pytorch Imagenet Models Example Transfer Learning (and fine-tuning)
ImageNet file xml format to Darknet text format
VGG16 Net implementation from PyTorch Examples scripts for ImageNet dataset
SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
ImageNet-1K data download, processing for using as a dataset
A PyTorch implementation of universal adversarial perturbation (UAP) which is more easy to understand and implement.
Code for the paper "A Study of Face Obfuscation in ImageNet"
Object Detection for Video with MXNet and GluonCV using YOLOv3
We use pretrained networks VGGnet, AlexNet, GoogLeNet, ResNet which trained on the ImageNet dataset as a feature extractor to classify images.
A Distributed ResNet on multi-machines each with one GPU card.
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
Android app containing an Image classifier based on transfer learning CNN using Tensorflow 1.4.1 on Stanford's Imagenet cars dataset
Deep Learning model which uses Computer Vision and NLP to generate captions for images
Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curve.
Creates subsets of ImageNet (e.g. ImageNet100)
A demo for mapping class labels from ImageNet to COCO.
Tensorflow Faster R-CNN for Windows and Python 3.5
[TPAMI-22] Bottom-up, voting based video object detection method
Add a description, image, and links to the imagenet-dataset topic page so that developers can more easily learn about it.
To associate your repository with the imagenet-dataset topic, visit your repo's landing page and select "manage topics."