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.
慧眼识垃圾系统——垃圾分类全套技术方案
Pytorch implementation of FCN, UNet, PSPNet, and various encoder models.
ResNet-ZCA (Journal of Infrared Physics & Technology 2019, Highly Cited Paper), MatLab
EPIC-KITCHENS-55 baselines for Action Recognition
Multiclass image classification using Convolutional Neural Network
Takes 2 images and says how similar they are based on Euclidean distance of feature vectors
Experiments to show the usage of deep learning to detect breast cancer from breast histopathology images
Content-Based Image Retrieval (CBIR) using Faiss (Facebook) and many different feature extraction methods ( VGG16, ResNet50, Local Binary Pattern, RGBHistogram)
Some example projects that was made using Tensorflow (mostly). This repository contains the projects that I've experimented-tried when I was new in Deep Learning.
Our Solution of the Flipkart Grid Challenge
Weakly supervised 3D classification of multi-disease chest CT scans using multi-resolution deep segmentation features via dual-stage CNN architecture (DenseVNet, 3D Residual U-Net).
ArchitecturalStyle Recognition is a image classifier of 25 different architectural styles, using deep learning.
🔎 PicTrace is a highly efficient image matching platform that leverages computer vision using OpenCV, deep learning with TensorFlow and the ResNet50 model, asynchronous processing with aiohttp, and the FastAPI web framework for rapid and accurate image search.
Image Similarity search build on Milvus
Framework to perform PAD (Presentation Attack Detection) on Facial Recognition systems through intrinsic properties and Deep Neural Networks - Still Under Development
Add a description, image, and links to the resnet50 topic page so that developers can more easily learn about it.
To associate your repository with the resnet50 topic, visit your repo's landing page and select "manage topics."